Images

Classifications

• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
  • G06F16/33—Querying
  • G06F16/332—Query formulation
  • G06F16/3329—Natural language query formulation
• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L15/00—Speech recognition
  • G10L15/08—Speech classification or search
  • G10L15/18—Speech classification or search using natural language modelling

Definitions

• the present invention relates to the retrieval of online information and processing of commands through a speech interface in a vehicle environment. More specifically, the invention is a fully integrated environment allowing mobile users to ask natural language speech questions or give natural language commands in a wide range of domains, supporting local or remote commands, making local and network queries to obtain information, and presenting results in a natural manner even in cases where the question asked or the responses received are incomplete, ambiguous or subjective.
• Telematics systems are systems that bring human-computer interfaces to vehicular environments.
• Conventional computer interfaces use some combination of keyboards, keypads, point and click techniques and touch screen displays. These conventional interface techniques are generally not suitable for a vehicular environment, owing to the speed of interaction and the inherent danger and distraction. Therefore, speech interfaces are being adopted in many telematics applications.
• a general-purpose telematics system must accommodate commands and queries from a wide range of domains and from many users with diverse preferences and needs. Further, multiple vehicle occupants may want to use such systems, often simultaneously. Finally, most vehicle environments are relatively noisy, making accurate speech recognition inherently difficult.
• An object of the invention is to overcome these and other drawbacks of prior speech-based telematic systems.
• systems and methods may overcome deficiencies of prior systems through the application of a complete speech-based information query, retrieval, presentation and command environment.
• This environment makes significant use of context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users making queries or commands in multiple domains.
• a speech-based natural language query, response and command environment is created.
• accommodation may be made for full or partial failure and graceful recovery.
• the robustness to partial failure is achieved through the use of probabilistic and fuzzy reasoning at several stages of the process. This robustness to partial failure promotes the feeling of a natural response to questions and commands.
• a mobile interactive natural language speech system (herein “the system”) that includes a speech unit.
• the speech unit may be incorporated into a vehicle computer device or system, or may be a separate device. If a separate device, the speech unit may be connected to the vehicle computer device via a wired or wireless connection.
• the interactive natural language speech device can be handheld.
• the handheld device may interface with vehicle computers or other electronic control systems through wired or wireless links.
• the handheld device can also operate independently of the vehicle.
• the handheld device can be used to remotely control the vehicle through a wireless local area connection, a wide area wireless connection or through other communication links.
• the system may include a stand alone or networked PC attached to a vehicle, a standalone or networked fixed computer in a home or office, a PDA, wireless phone, or other portable computer device, or other computer device or system.
• a computer includes software that is installed onto the computer, where the software includes one or more of the following modules: a speech recognition module for capturing the user input; a parser for parsing the input, a text to speech engine module for converting text to speech; a network interface for enabling the computer to interface with one or more networks; a graphical user interface module, an event manager for managing events and other modules.
• the event manager is in communication with a dictionary and phrases module, a user profile module that enables user profiles to be created, modified and accessed, a personality module that enables various personalities to be created and used, an agent module, an update manager and one or more databases.
• this software can be distributed in any way between a handheld device, a computer attached to a vehicle, a desktop computer or a server without altering the function, features, scope, or intent of the invention.
• the system may include a speech interface device that receives spoken natural language queries, commands and/or other utterances from a user, and a computer device or system that receives input from the speech unit and processes the input (e.g., retrieves information responsive to the query, takes action consistent with the command and performs other functions as detailed herein), and responds to the user with a natural language speech response.
• a speech interface device that receives spoken natural language queries, commands and/or other utterances from a user
• a computer device or system that receives input from the speech unit and processes the input (e.g., retrieves information responsive to the query, takes action consistent with the command and performs other functions as detailed herein), and responds to the user with a natural language speech response.
• the system can be interfaced by wired or wireless connections to one or more vehicle-related systems.
• vehicle-related systems can themselves be distributed between electronic controls or computers attached to the vehicle or external to the vehicle.
• Vehicle systems employed can include, electronic control systems, entertainment devices, navigation equipment, and measurement equipment or sensors.
• External systems employed include those used during vehicle operation, such as, weight sensors, payment systems, emergency assistance networks, remote ordering systems, and automated or attended customer service functions.
• Systems on the vehicle typically communicate with external systems via wireless communications networks.
• the system can be deployed in a network of devices using common base of agents, data, information, user profiles and histories. Each user can then interact with, and receive the same services and applications at any location equipped with the required device on the network.
• multiple devices on which the invention is deployed, and connected to a network can be placed at different locations throughout a home, place of business, vehicle or other location.
• the system can use the location of the particular device addressed by the user as part of the context for the questions asked.
• Agents are executables that receive, process and respond to user questions, queries and commands.
• the agents provide convenient and re-distributable packages or modules of functionality, typically for a specific domain.
• Agents can be packages of executable code, scripts, links to information, data, and other data forms, required to provide a specific/package of functionality, usually in a specific domain.
• an agent may include everything that is needed to extend the functionality of the invention to a new domain.
• agents and their associated data can be updated remotely over a network as new behavior is added or new information becomes available.
• Agents can use system resources and the services of other, typically more specialized, agents. Agents can be distributed and redistributed in a number of ways including on removable storage media, transfer over networks or attached to emails and other messages.
• An update manger is used to add new agents to the system or update existing agents.
• the software behavior and data in an agent can either be of a general-purpose nature or specific to a domain or area of functionality.
• One or more system agents include general-purpose behaviors and data, which provide core or foundation services for more specialized domain or system agents.
• general-purpose functionality include transmitting and receiving information over data networks, parsing text strings, general commands to the interactive natural language telematics speech interface, and other functions.
• a specific system agent may be used to transmit and receive information over a particular type of network, and may use the services of a more general network agent.
• Domain specific agents include the behavior and data required for a specific area of functionality. More specialized domain agents can use the functionality of more generalized domain agents. Areas of functionality or specific domains are broadly divided into two categories, query and response, and control.
• query and response domains include driving directions, travel services, entertainment scheduling, and other information
• Agents may in, turn query other agents.
• a fast food ordering agent may use the services of a restaurant ordering agent and payment agent, which may in turn, use the services of location agent and a travel services agent.
• Control domains include control of specific devices on a vehicle.
• the agent includes or has access to the data and functionality required to control the device through the appropriate interfaces.
• a specific domain agent may be used to control the windshield wipers on a vehicle.
• a domain agent for controlling the vehicle's headlights may use the services of a lighting control agent, which may use the services of an electrical device control agent.
• Some domains, and therefore agents may combine aspects of control with query and response functionality. For example, a user may wish to listen to a particular piece of music. In this case, the domain agent will make one or more queries, possibly using the services of other agents, to locate a source for the music and retrieve it. Next, the domain agent will activate a suitable player for the format of the music, again possibly using the services of other agents.
• the invention may provide license management capability allowing the sale of agents by third parties to one or more users on a one time or subscription basis.
• users with particular expertise can create agents, update existing agents by adding new behaviors and information and making these agents to other users.
• the invention may allow both users and content providers to extend the system capabilities, add data to local data sources, and add references to network data sources.
• the system may allow third party content developers to develop, distribute and sell specialized or domain specific system programs and information. Content is created though creation of new agents, scripting existing agents, adding new data to agents or databases, and adding or modifying Links to information sources. Distribution of this information is sensitive to the user's interests and use history and to their willingness to pay for it.
• the system may include mechanisms to allow users themselves to post and distribute agents and information in their particular areas of expertise, to improved system capability. Further, users can extend the system and configure it to their own preferences, add information to their profile to define new questions or queries, extend and modify existing questions and queries, add new data sources, update data sources, set preferences and specify presentation parameters for results.
• the system can be distributed between any combination of vehicle computers, handheld devices, server computers, desktop computers and other terminal devices.
• Each of these devices may have a local set of databases and agents, which may be specific to a user or users. If a given user is to see a uniform set of capability across the various platforms, the databases and agents can be synchronized.
• the synchronization of data and agents can be automatically or manually initiated. For example, changes to agents and databases can be automatically propagated to other platforms used by that user whenever and wherever network connections permit. In another example, changes on a handheld computer are propagated to a vehicle computer or vice versa when the handheld is connected to the vehicle computer on a wireless or wired link.
• a user may wish to block the synchronization of sensitive or personal information to certain platforms used by the user. For example, a user may choose to keep all of their personal and other sensitive information on their handheld device and use the computing power, databases and network connections of other platforms from their handheld device.
• a vehicle operator can carry their personal databases and agents from one vehicle to another, but keep their information within the handheld computer.
• the system may format results in a manner enhancing the understandability to the user.
• the optimal formatting and presentation depends on the context of the queries, the contents of the response being presented, the history of the interaction with the user, the user's preferences and interests and the nature of the domain.
• Information presented in a rigid, highly formatted, or structured manner seems unnatural to most people.
• the system may simulate some aspects of human “personality.”
• the presentation of the response and the terms used are randomized so they do not appear rigidly formatted or mechanical.
• the use of simulated personality characteristics is also desirable. For example, a response that may be upsetting to the user is best presented in a sympathetic manner.
• information requiring immediate action or annunciating a safety problem can be delivered with a definite and authoritative personality.
• the results of queries may be long text strings, lists, tables or other lengthy sets of data. Natural presentation of this type of information presents particular challenges. Simply reading the long response is generally not preferred. Therefore the system can parse the most important sections from the response and, at least initially, only report these. Determining what parts of a long response are presented may depend on the context of the questions, the contents of the response being presented, the history of the interaction with the user, the user's preferences and interests and the nature of the domain. At the same time, the system may give the user, interactive control over what information and how much information is being presented, to stop the response all together, or to take other actions.
• the invention can be applied as a user interface to telematics systems in a wide variety of environments.
• environments can include, but are not limited to, the following: 1) personal automobiles, rented automobiles, or fleet automobiles; 2) motorcycles, scooters, and other two wheeled or open-air vehicles; 3)commercial long-haul and short haul trucks; 4) delivery service vehicles; 5)) fleet service vehicles; 6) industrial vehicles; 7) agricultural and construction machinery; 8) water-borne vehicles; 9) aircraft; and; 10) specialized military, law enforcement and emergency vehicles.
• the system can process and respond to questions, queries and commands. Keywords or context can be used to determine if the user's utterance is a command or query. Some utterances can include both aspects of a command and a query or question. For example, a user may say, “tune in my favorite radio station.” A query may be required to determine the name, and/or the channel of the use's favorite station. If the programming on that station is of a type the user generally does not listen to, the system can suggest using an alterative, such as listening to a CD more likely to please the user.
• the invention can be used for generalized local or network information query, retrieval and presentation in a mobile environment.
• the system may perform multiple steps possibly including: 1) capturing the user's question or query through accurate speech recognition operating in a variety of real-world environments; 2) parsing and interpreting the question or query; 3) determining the domain of expertise required and context, invoking the proper resources, including agents; 4) formulating one or more queries to one or more local and/or network data sources or sending appropriate commands to local or remote devices or the system itself, 5) performing required formatting, variable substitutions and transformations to modify the queries to a form most likely to yield desired results from the available sources; 6) executing the multiple queries or commands in an asynchronous manner and dealing gracefully with failures; 7) extracting or scraping the desired information from the one or more results, which may be returned in any one of a number of different formats; 8) evaluating and interpreting the results, including processing of errors, gathered and combine them into a single best
• the above steps may be performed using the context of the domain of expertise required, the context for the question or command, domain specific information, the history of the user's interaction, user preferences, information sources or commands available, and responses obtained from the sources.
• probabilistic or fuzzy set decision and matching methods can be applied to deal with inconsistent, ambiguous, conflicting and incomplete information or responses.
• asynchronous queries allowing rapid and graceful failure of some queries or commands, allows the system to robustly return results quickly, and in a manner that seems natural to the user.
• the invention may use probabilistic and fuzzy set decision and matching methods to first identify the subjective nature of the question and to evaluate a range of possible answers, selecting the one answer or few answers that best represent the type of result desired by the user.
• the invention creates, stores and uses extensive personal profile information for each user.
• Information in the profile may be added and updated automatically as the user uses the system or can be manually added or updated by the user.
• Domain specific agents collect, store and use specific profile information, as required for optimal operations. Users can create commands for regularly used reports, automatically generated alerts, and other queries and for the formatting and presentation of results.
• the system may use profile data in interpreting questions, formulating queries, interpreting results of queries and presenting answers to the user.
• Examples of information in a user profile includes, history of questions asked, session histories, formatting and presentation preferences, vehicle type, special vehicle equipment, vehicle related data, special word spelling, terms of interest, special data sources of interest, age, sex, education level, location of vehicle, planned path or route, specific addresses, commonly visited destinations, place of business, type of business, investments, hobbies, sports interests, news interests and other profile data.
• the invention can attempt to provide rapid responses without requiring any additional information.
• the invention may determine the mostly likely context or domain for a user's question or command, for example, by using a real-time scoring system or other techniques. Based on this determination the system can invoke the correct agent.
• the agent may make one or more queries and may rapidly return a formatted response.
• a user can receive a direct response to a set of questions each with a different response or context.
• the available information, including the query results may not adequately answer the question.
• the user can then be asked one or more questions to resolve the ambiguity. Additional queries may then be made before an adequate response is made.
• the system can use context information, user profile information and domain specific information to minimize the interaction with the user required to deliver a response.
• the system can ask a question of the user to verify the question or command is correctly understood.
• the question may be phrased to indicate the context of the question including all criteria or parameters. If the user confirms that the question is correct then the system may proceed to produce a response. Otherwise, either the user can rephrase the original question, perhaps adding additional information to remove ambiguity, or the system can ask one or more questions to attempt to resolve the ambiguity or other actions may taken.
• the system can support a voice query language.
• the language helps users clearly specify the keywords or contexts of the question or command along with the parameters or criteria.
• the system may provide built in training capabilities to help the user learn the best methods to formulate their questions and commands.
• the invention may employ one or more dynamically invokeable personalities.
• Personalities have specific characteristics, which simulate the behavioral characteristics of real humans. Examples of these characteristics include, sympathy, irritation, and helpfulness.
• the personality also randomizes aspects of responses, just as a real human would do. This behavior includes randomization of terms used and the order of presentation of information. Characteristics of the personality may be invoked using probabilistic or fuzzy set decision and matching methods, and using criteria including the context for the question, the history of the user's interaction, user preferences, information sources available, responses obtained from the sources.
• the invention may use special procedures to present information that is in the form of long text strings, tables, lists or other long response sets. Simply presenting a long set of information in an ordered manner may not be natural nor what most users have in mind.
• the system using probabilistic or fuzzy set matching methods, may extract the most relevant information to the user and presents these subsets first. Further the system can provide commands allowing the user to skip through the list, find keywords or key information in the list or stop processing the list altogether.
• the system may recognizes a user either by name or voice. Once the user is recognized, the system may invoke the correct profile. If multiple users are addressing the system in overlapping or interleaved sessions, the system can determine which user is stating each question or command and apply the correct profile and context. For applications requiring security, the user is verified, typically by using voiceprint matching or requesting a password or pass-phrase from the user.
• the system may gracefully resolve conflicts using a probabilistic or fuzzy set decision method. This process simulates the manner in which a human would address multiple questions. For example, the system may answer short questions first at times, while answering questions in the order received at other times.
• the system can use either one-dimensional or two-dimensional array microphones (or other devices) to receive human speech.
• the array microphones can be fixed or employ dynamic beam forming techniques. The array pattern may be adjusted to maximize gain in the direction of the user and to null point noise sources.
• microphones can be placed at particular locations within a vehicle near where occupants are likely to use the system. These microphones can be single microphones, directional microphones or an array of microphones. Speech received at the microphones may then be processed with analog or digital filters to optimize the bandwidth, cancel echoes, and notch-out narrow band noise sources. Following filtering, the system may use variable rate sampling to maximize the fidelity of the encoded speech, while minimizing required bandwidth. This procedure can be particularly useful in cases where the encoded speech is transmitted over a wireless network or link.
• the invention can be applied to a wide range of telematics applications.
• General applications areas can include, but are not limited to remote or local vehicle control, information query, retrieval and presentation from local or network sources, safety applications, and security applications.
• the system can provide local or remote control functions for the system or for other devices on the vehicle or off the vehicle. Users can initiate commands locally or remotely. Typically, remote operation may be through a telephone or other audio connection. Alternately, the user can address spoken commands to a handheld device or desktop unit, which may send the commands to controllers on the vehicle over wireless links. Other remote command techniques may be used.
• the system may process commands in a nearly identical manner to a query. One difference being that the result of the command is generally an action rather than a response. In many cases, the system may give the user a cue or response to indicate that the command has been successfully executed or has failed. In cases of failure, an interactive session may be started to allow the user to resolve the difficulty or formulate a command more likely to succeed.
• the system may execute a number of steps possibly including: 1) capture the user's command through accurate speech recognition operating in a variety of real-world environments; 2) parse and interpret the command; 3) determine the domain for the command and context, invoking the proper resources, including agents as required; 4) gather required data including, device settings, and measurement data; 5)) formulate device specific commands for the system or external devices; 6) route command to system, or external devices, including external devices connected to data networks; 7) receive and process results of command, including errors; and, 8) optionally, provide response to user indicating the success or failure of the command, and possibly including state information.
• the invention can provide to users, including vehicle operators, the capability to control most any vehicle system function using interactive speech. Generally, all controls of a critical nature or with safety implications may employ fail-safe checks, verify that a command will not create a hazardous condition before it is executed and have manual overrides.
• the invention can provide built in help and user guidance for the devices under control. This guidance can include step-by-step training for operators learning to use the features of the vehicle.
• the system can provide extensive interactive guidance when commands cannot be executed or fail. This advice can include, suggestions to reformulate the command so it can succeed, suggestions to work around a failure, and suggestions for alternative commands that may achieve a similar function. Examples of control functions, which can be performed from local or remote locations by the invention include:
• the invention can provide users or operators of a vehicle with specialized safety functions through the interactive speech interface.
• the invention uses a dynamically evocable personality capability to create announcements that are appropriate for the severity of the situation.
• the announcements and personalities can be under user control and configuration.
• the invention can offer vehicle operators and occupants a variety of services, useful while in the vehicle or arriving at a destination.
• the user can employ the interactive speech interface of the invention.
• users can employ the interactive natural language speech interface to customize these services to suite each individual.
• Some examples of services that can be supported by the natural-language interactive speech interface of the invention include:
• Vehicle operators and other occupants can use the interactive natural language interactive speech interface of the invention to perform many types of information query, retrieval and presentation operations.
• users can modify the parameters of queries or specify the presentation formats for results.
• Data used to create a response can be from any combination of local and remote data sources.
• User specific data can be synchronized between systems fixed to one or more vehicles, handheld systems and desktop systems.
• FIG. 1 is an overall block diagram of the system according to ant embodiment of the invention
• FIG. 2 is an overall block diagram of the system according to an embodiment of the invention.
• FIG. 3 is an overall block diagram of a handheld computer according to an embodiment of the invention.
• FIG. 4 is an overall block diagram of a fixed computer according to an embodiment of the invention.
• FIG. 5 is an overall diagrammatic view of the; interactive natural language speech processing system according to an embodiment of the invention.
• FIG. 6 is a schematic block diagram showing the agent architecture according to an embodiment of the invention.
• the Telematics natural language speech interface of the invention may be applicable to most any vehicle environment and telematic application.
• the same system or portions thereof can be used in a vehicle, while on foot through a handheld device or, at a fixed location such as an office or home using a desktop or handheld device, or through other devices.
• An overall block diagram of one embodiment of the invention is shown in FIG. 1 .
• a speech unit 128 can be permanently attached to the vehicle 10 or can be part of a handheld device 36 or a fixed home or office computer system 44 .
• the speech unit 128 may be interfaced to a Telematics Control Unit (TCU) 28 through one or more data interfaces 26 .
• TCU Telematics Control Unit
• the main speech-processing unit 98 may be embedded in one or more TCU 28 .
• the components of the speech unit 128 can also be distributed between one or more TCUs.
• a speech-processing unit built into a handheld device 36 may be connected with the data interfaces 26 though a wireless or wired handheld interface 20 .
• Other user interface peripherals can be connected to the TCU through the data interfaces and can include, displays 18 including touch screen displays for text, graphics and video, keypads 14 for data input, video cameras 16 for multimedia communications or conferences, and a pointing device or stylus (not shown).
• Other devices connected to the TCU though the data interfaces can include wide-area RF transceivers 24 , and navigation system components 22 .
• the navigation system components can include a number of items, such as, a Global Positioning System (GPS) receiver or other radiolocation system receiver, gyroscope and other inertial measurement equipment, and distance measurement sensors such, as odometers.
• GPS Global Positioning System
• Radiolocation equipment receives coded signals from one or more satellite or terrestrial sources 40 .
• the one or more location service servers 48 may assist the navigation system.
• Other systems that can connect to the TCU through the data interfaces can include automotive control computers, digital control interfaces for devices such as media players or other electronic systems, measurement sensors, and specialized electronic equipment.
• the control and device interfaces 30 may connect the TCU 28 to various devices on the vehicle 32 .
• the control and device interfaces may be used to execute local or remote commands from users of the natural language speech interface.
• the control and device interfaces 30 may include specialized hardware required for interaction with each type of device.
• the hardware interfaces may include analog or digital signal interfaces for device control along with analog or digital interfaces for measurements required to control the device.
• These interfaces may also include specialized software encapsulating or abstracting specific behavior of each device.
• the interface software may include one or more drivers, specific to the hardware interface, and one or more agents.
• the domain agents may include the specialized software behavior and data required for controlling a particular device or class of devices. New or updated behavior can be added to the system by updating the agents for a specific device or class of devices.
• control and device interface may incorporate fail-safe systems, which, for example, may verify operating limits before changing settings, ensuring that commands do not conflict with settings from manual controls, and will not in some combination with other commands or device settings create an unsafe situation.
• the software behavior and data that may be required to ensure safe operations may be included within the domain agent specific to the device or class of devices. Examples of devices and system that can be controlled through the control and device interfaces include, power management systems, measurement sensors, door locks, window controls, interior temperature controls, shifting of the transmission, turn signals, lights, safety equipment, engine ignition, cruise control, fuel tank switches, seat adjustments, specialize equipment such as winches, lifting systems or loading system, and other systems.
• the wide-area RF transceiver 24 may communicate with one or more wide-area wireless networks 38 , which are connected to data networks 42 , including the Internet, and the Public Switched Telephone Network (PSTN) 42 .
• the wide-area wireless networks can be of any suitable terrestrial or satellite based type.
• Handheld systems 36 can communicate with one or more local or wide-area wireless networks.
• Home or office systems 44 equipped with wired or wireless network interfaces communicate through the data networks or PSTN.
• synchronization In cases where a user uses one or more main speech-processing units 98 attached to vehicles 10 , handheld systems 36 or fixed systems 44 , data and agents stored in these systems can be synchronized.
• the synchronization between these different systems can occur on the wide area wireless network 38 , the data network 42 , through the handheld interface 20 , or other local data connections.
• the synchronization can be performed automatically when any two or more of the computers are connected to these networks. Alternatively the synchronization can be performed on demand under control of the user.
• the synchronization process attempts determine which version of a data element or an agent are the newest or most up to date and will propagate that element.
• synchronization is an incremental change processes. In some cases, a complete replacement of a database or portion of a database or of one or more agents may be performed rather that a series of incremental updates.
• the wide-area wireless networks 38 may connect the invention 98 , 128 on vehicles 10 , in handheld devices 36 and fixed computers 44 to one or more servers, which provide one of more services.
• the invention may provide an interactive natural language speech user interface to the services offered.
• a standardized data transfer format is, typically used, including for example, Hypertext Markup Language over Hypertext Transfer Protocol (HTTP), Extensible Markup Language (XML), possibly employing a variety of data formats or schemas, over HTTP or other transfer protocol, Electronic Data Interchange formats over a variety of transport protocols, etc. Examples of services being offered have already been discussed.
• the exact configuration of the servers may be determined by many considerations including, the exact combinations of services being offered, the service providers providing the services, the contractual relationships between the service provider, and other factors, and that the invention can support most any suitable configuration. In each case these servers may themselves be distributed over one or more public or private networks. Some examples the servers, which may be used to deliver these services, are given below:
• the main speech processing unit 98 and the speech unit 128 can be distributed in a vehicle in a number of ways.
• these units can be attached to the vehicle as independent components or as a single integrated component.
• some or all of the main speech processing unit 98 and speech unit 128 can be embedded in one or more of the TCUs 28 , handheld computers 36 and fixed computer systems 44 .
• FIG. 2 A block diagram of a second possible embodiment of the invention is shown FIG. 2 .
• the main speech processing unit 98 and speech unit 128 are external to the TCU 28 .
• These components can be housed in one or more packages or included in a single integrated package.
• the second embodiment is identical to the first embodiment. It will be understood that the exact distribution and packaging of the main speech processing unit 98 and speech unit 128 , can be determined by the details of the deployment situation and will not change the functionality, capabilities or spirit of the invention in any way.
• a handheld computer 36 can be used as a component of the invention.
• a block diagram of one possible embodiment of the handheld computer is shown in FIG. 3 .
• the main speech processing unit 98 and speech unit 128 may be embedded into the handheld computer 36 .
• the main speech processing unit interfaces to the handheld computer's one or more processing units 70 .
• the processing units may include one or more central processing units, one or more data and address busses, data interfaces and volatile memory.
• the processing unit 70 uses one of more types of nonvolatile memory 80 for software and data storage. Suitable types of nonvolatile memory 80 include flash memory and hard disk drives.
• the main speech processing unit 98 can be integrated with the one or more processing units 70 .
• users interact with the handheld computer 36 through the speech unit 128 , the keypad 74 or keyboard, and a display 72 for text, graphics and video.
• the display is of a touch screen type.
• An optional pointing device (not shown) may be used as well.
• the handheld computer 36 can connect to one or more wired or wireless wide-area or local-area networks through one or more interfaces.
• a wide-area network transceiver 78 can connect to the wide-area wireless network 38 or the data network 42 , using a wireless or wired connection, including a dial PSTN network connection.
• the local-area network transceiver 76 connects to wired or wireless local area networks. These networks can include the handheld interface 20 or connections to fixed computer systems 44 .
• FIG. 4 A block diagram of one possible embodiment of the fixed computer is shown in FIG. 4 .
• the main speech processing unit 98 and speech unit 128 may be embedded into the fixed computer 44 .
• the main speech processing unit may interface to the fixed computer's one or more processing units 84 .
• the processing units may include one or more central processing units, one or more data and address busses, data interfaces and volatile memory.
• the processing unit may use one of more types of nonvolatile memory 94 for software and data storage. Suitable types of nonvolatile memory include, for example, flash memory and hard disk drives.
• the main speech processing unit 98 can be integrated with the one or more processing units 84 .
• users may interact with the fixed computer 44 through the speech unit 128 , the keyboard 88 or keypad, and a display 86 for text, graphics and video.
• the display is of a touch screen type.
• An optional pointing device (not shown) may be used as well.
• the fixed computer 44 can connect to one or more wired or wireless wide-area or local-area networks through one or more interfaces.
• a wide-area transceiver 92 can connect to the wide-area wireless network 38 or the data network 42 , using a wireless or wired connection, including a dial PSTN network connection.
• the local-area network transceiver 90 connects to wired or wireless local area networks. These networks can include connections to the handheld computer 36 .
• the natural language interactive speech processing system may make maximum use of context, prior information, location information, domain information and user specific profile data to achieve a natural environment for one or more users making queries or stating commands across multiple domains.
• the telematic natural language speech interface can be deployed as part of or a peripheral to a TCU or other vehicle computer, as part of a handheld computer interfaced to vehicle computers and other system through wired, wireless, optical, or other types of connections or fixed computers interfaced to the vehicle computers or other systems through a combination of wired, wireless, optical and/or other types of connections.
• the components of the interactive natural language telematic speech interface can be distributed in any suitable manner between these multiple computing platforms. Regardless of the method of deployment the invention provides the required functionality.
• FIG. 5 shows an overall diagrammatic view of the interactive natural language speech processing system according to one embodiment of the invention.
• the event manager 100 may mediate interactions between other components of the invention.
• the event manager can provide a multi-threaded environment allowing the system to operate on multiple commands or questions from multiple user sessions without conflict and in an efficient manner, maintaining real-time response capabilities.
• Agents 106 may include packages of both generic and domain specific behavior for the system. Agents may use the nonvolatile storage for data, parameters, history information, and locally stored content provided in the system databases 102 or other local sources. User specific data, parameters, session information, location data and history information determining the behavior of agents are stored in one or more user profiles 110 . Agents for commands typically include domain knowledge specific to the device or devices under control. Data determining system personality characteristics for agents are stored in the one or more personalities 108 . The update manager 104 manages the automatic and manual loading and updating of agents and their associated data from the Internet 42 or other network through the network interface 116 .
• the main user interface for the invention is through one or more speech units 128 .
• the speech unit 128 includes one or more microphones, for example array microphone 134 , to receive the utterances of the user. Alternatively, one or more external microphones can be used.
• the speech received at the microphone 134 may be processed by filters 132 and passed to the speech coder 138 for encoding and compression.
• a transceiver module 130 transmits the coded speech to the main unit 98 . Coded speech received from the main unit is detected by the transceiver 130 , then decoded and decompressed by the speech coder 138 and annunciated by the speaker 136 .
• the speech units can be attached to a vehicle 98 , 128 , in a handheld device 36 , or embedded in or attached to a fixed system 44 .
• the one or more speech units 128 and the main unit 98 may communicate over a communication link.
• the communication link can include a wired or wireless link.
• the communication link having an RF link.
• the transceiver 130 on the speech unit communicates coded speech data bi-directionally over the communication link with the transceiver 126 on the main unit 98 .
• the RF link can use any standard local area wireless data protocols including the IEEE 802.11, Bluetooth or other standards.
• an infrared data link conforming to any suitable standard such as IrDA or other infrared standards can be used.
• wires, optical fibers or other connection techniques may connect the speech unit and the main unit, eliminating the need for a speech coder 138 .
• the main speech processing unit 128 can be attached to a vehicle, embedded in one or more TUCs 28 , in a handheld computer 36 , attached as a peripheral to a fixed computer 44 or embedded in a fixed computer 44 .
• the speech unit can be integrated with the main unit or can be configured as a separate attachment.
• Coded speech received at the transceiver 126 on the main unit 98 may be passed to the speech coder 122 for decoding and decompression.
• the decoded speech can be processed by the speech recognition engine 120 using data in the dictionary and phrases module 112 and received from the agents 106 .
• the recognized words and phrases may be processed by the parser 118 , which transforms them into complete commands and questions using data supplied by the agents.
• the agents can then process the commands or questions.
• the agents create queries to local databases 102 or though the network interface 116 to data sources on the Internet 42 or other networks. Commands typically result in actions taken by the system itself (i.e., pause or stop), or to a remote device or data source (i.e., download data or program, or control a local or remote device), through the network interface to the Internet or other data interface.
• the agents 106 may return results of questions as responses to users.
• the response can be created using the results of information queries, the system personality 108 and the user preferences or other data in the user profile 110 .
• the agents generally present these results using the speech unit 128 .
• the agent may create a response string, which may be sent to the text to speech engine 124 .
• the text to speech engine creates the required utterances, which may be encoded and compressed by the speech coder 122 . Once coded, the utterances may be transmitted from the main unit 98 by the transceiver 126 to the transceiver 130 on the speech unit 128 . The utterance may then be decoded and decompressed by the speech coder 138 and output by the speaker 136 .
• the graphical user interface 114 can be used as a substitute or complement to the speech interface.
• the graphical user interface can be used to view and interact with graphical or tabular information in a manner more easily digested by the user.
• the graphical user interface can include a display 18 , keypad 14 , and pointing device (not shown).
• the graphical user interface can be implemented using the capabilities of a handheld computer 36 or fixed computer 44 .
• the graphical user interface can show system state and history in a more concise manner than the speech interface. Users can use the graphical user interface to create or extend agents 106 . These operations can include scripting of agents, adding data to the agent or databases 102 used by the agent, adding links to information sources;
• agent provides default functionality and basic services.
• the domain specific agents may provide complete, convenient and re-distributable packages or modules for each application area.
• an agent may include everything needed to extend or modify the functionality of the system in a current or new domain.
• agents and their associated data can be updated remotely over a network as new behavior is added or new information becomes available.
• Agents may access a plurality of sources that may provide various services. Agents can use the services of other, typically more specialized, agents and the system agent. Agents are distributed and redistributed in a number of ways including on removable storage media, transfer over networks or attached to emails and other messages.
• the invention may provide license management capability allowing the sale of agents by third parties to one or more users on a one time or subscription basis.
• users with particular expertise can create agents, update existing agents by adding new behaviors and information and making these agents to other users;
• a block diagram of the agent architecture according to an embodiment of the invention is shown in FIG. 6 .
• Agents 106 may receive and return events to the event manager 100 . Both system agents 150 and domain agents 156 receive questions and commands from the parser 118 . Based on the keywords and command structure, the parser may invoke the required agent. Agents may use the nonvolatile storage for data, parameters, history information and local content provided in the system databases 102 . When the system starts-up or boots-up, the agent manager 154 may load and initialize the system agent 150 and the one or more domain agents 156 . At shutdown the agent manager may unload the agents. The agent manager may also performs license management functions for the domain agents and content in the databases 102 .
• the system agent 150 may manage the criteria handlers 152 , which may handle specific parameters or values (criteria) used to determine context for questions and commands. Both the system agent 150 and the domain agents 156 can use the criteria handlers 152 .
• the various domain agents 156 can use the services of the system agent 150 and of other, typically more specialized, domain agents 156 .
• the system agent 150 and the domain agents 156 can use the services of the agent library 158 , which may include utilities for commonly used functions.
• the library 158 may include utilities for text and string handling, network communications, database lookup and management, fuzzy and probabilistic evaluation, text to speech formats, and other utilities.
• Domain agents 156 can be data-driven, scripted or created with compiled code. A base of generic agent is used as the starting point for data-driven or scripted agents. Agents created with compiled code are typically built into dynamically linkable or loadable libraries. Developers of agents 106 can add new functionality to the agent library 158 as required. Details of agent distribution and update, and agent creation or modification are discussed in sections below.
• the invention provides capabilities to distribute and update system agents 150 , domain agents 156 , agent library components 158 , databases 102 , and dictionary and phrase entries 112 over wireless or wired networks 42 , including dial-up networks using the update manager 104 .
• the network interface 116 may provide connections to one or more networks.
• the update manager 104 may also manage the downloading and installation of core system updates.
• the agent manager 154 may perform license management functions for the domain agents and the databases.
• the update manager 104 and agent manager 154 may perform these functions for all agents and database content including, agents and content available to all users or agents and content only available to certain users.
• agent and database components added or updated on a periodic basis include: 1) agents for new domains; 2) agents for new commands; 3) agents for new devices added to the vehicle or remote devices; 4) agents for new or updated behavior for existing devices on the vehicle or remote devices; 5) additional domain knowledge for agents; 6) new keywords for a domain, which can include names of politicians, athletes, entertainers, names of new movies or songs, new command words, and or other names and words; 7) links to a preferred set of information sources for the domains covered including links for, entertainment, news, sports, weather, and other topical sites; 8) updates to domain information based on, for example, changes to tax laws, company mergers, changing political boundaries, new safety rules; 9) updates to content, including dictionaries, encyclopedias and almanacs; and 10) other content and database components.
• the update manager 104 may connect to the source on the network 42 though the network interface 116 , and may download and install the agent and/or data. To save system resources and to comply with any license conditions, the update manger 104 may uninstall agents 106 that are no longer in use. In some embodiments, the update manager may periodically queries the one or more sources of the licensed agents and database components to locate and down load updates to agent executables, scripts or data as they become available. In other embodiments, the agent sources may initiate the downloading of agent updates of the registered or licensed agents to the update manager 104 as they become available.
• the agent manager 154 may provide a license management client capable of executing most any license terms and conditions.
• the agent manger may verify that the use of the agent or data element is within the allowed terms and conditions, and if so, invokes the agent or allows access to the data element.
• License management schemes that can be implemented through the agent manager 154 includes out right purchase, subscription for updates, one time or limited time use. Use of shared agents and data elements (such as those down-loaded from web sites maintained by groups of domain experts) may also be managed by the agent manager.
• the agent manager 154 can search the network 42 through the network interface 116 to find a source for a suitable agent. This process can be triggered, for example, when a query is made in a domain for which an agent is not available, or when a new device is added to a vehicle or the behavior of a device is updated. Once located, the agent can be loaded under control of the update manager 104 , within the terms and conditions of the license agreement as enforced by the agent manger.
• New commands, keywords, information, or information sources can be added to any domain agent 156 by changing agent data or scripting.
• These configuration capabilities allow users and content developers to extend and modify the behavior of existing agents or to create new agents from a generic agent without the need to create new compiled code.
• the modification of the agents can range from minor data-driven updates by even the most casual users, such as specifying the spelling of words, to development of complex behavior using the scripting language as would typically be done by a domain expert.
• the user can create and manage modifications to agents through speech interface commands or using a graphical user interface 114 . User-specific modifications of agents are stored in conjunction with the users profile and accessed by the agent at run-time.
• the data used to configure data driven agents 156 may be structured in a manner to facilitate efficient evaluation and to help developers with organization. These data can be used not only by the agent, but also in the speech recognition engine 120 , the text to speech engine 124 , and the parser 118 . Examples of some major categories of data include:
• Commands and questions are interpreted, queries formulated, responses created and results presented can be based on the user's personal or user profile 110 values.
• Personal profiles may include information specific to the individual, their interests, their special use of terminology, the history of their interactions with the system, and domains of interest.
• the personal profile data can be used by the agents 106 , the speech recognition engine 120 , the text to speech engine 124 , and the parser 118 . Preferences can include, special (modified) commands, past behavior or history, questions, information sources, formats, reports, and alerts.
• User profile data can be manually entered by the user and/or can be learned by the system based on user behavior.
• User profile values can include: 1) spelling preferences; 2) date of birth for user, family and friends; 3) income level; 4) gender; 5) occupation; 6)location information such as, home address, neighborhood, and business address, paths traveled, locations visited; 7) vehicle type or types; 8) vehicle operator certifications, permits or special certificates; 9) history of commands and queries; 10) telecommunications and other service providers and services; 11) financial and investment information; 12) synonyms (i.e., nick name for someone, different terms for the same item); 13) special spelling; 14) keywords; 15) transformation or substitution variables; 16) domains of interest; and, 17) other values.
• End users can use the data driven agent 156 extension and modification facilities and values stored in user profiles 110 to create special reports, packages of queries, alerts and output formats.
• a single alert or report can be configured to use multiple data sources and other variables (i.e., time, location, measured value) value to condition to determine when alerts should be sent. For example, an alert can be generated by sampling a stock price every 15 min and sending an alert if the price drops below some value.
• a user can create an alert when a particular condition or combination of conditions occurs on the vehicles. Alerts and reports can be directed to a local or remote output.
• a report can have variable parameters. For example, a user may create a company stock report, and execute the report by stating its name and the company name, which gives the user selected information and in a specified format for that company. In another example, a user can create a “morning” report, which presents selected multimedia information from different sources (news, sports, traffic, weather) in the order and formats desired. In yet another example, the user can create a report on the status of one or more vehicle systems. Alerts and reports can be created using only voice commands and responses, commands and responses through the graphical user interface 114 , or a combination of the two.
• Reports can be run locally or remotely with respect to the vehicle.
• the user performs a number of steps including: 1) specify the command to run a report or alert; 2): specify the question or questions, including keywords, used for a query; 3) set the criteria for running the report such as on command or when a particular condition is met; 4) define preferred information sources; 5)define preferences for order of result evaluation by source, value, and other parameters; 6) specify the presentation medium for a report or alert, such as an email, the text to speech engine, a message to a pager, or a text and graphics display; and, 7) specify the preferred format for the report, such as information to be presented, order of information to be presented, preferred abbreviations or other variable substitutions.
• Filtering and noise elimination may be a key aspect of the invention allowing it to operate in noisy vehicle environments.
• the accurate recognition and parsing of the user's speech requires the best possible signal to noise ratio at the input to the speech recognition engine 120 .
• an array microphone 134 and a filter 132 may be employed.
• the microphone array, filters and speech coder 138 are physically separated from the main unit 98 into a speech unit 128 , and connected using a wireless link. Since bandwidth on a wireless connection is at a premium the speech coder dynamically adapts the digitization rate and compression of the captured speech.
• Some embodiments of the invention may use one or more arrays of microphones 134 to provide better directional signal capture and noise elimination than can be achieved with a single microphone.
• the microphone array can be one-dimensional (a linear array) or two-dimensional (a circle, square, triangle or other suitable shape).
• the beam pattern of the array can be fixed or made adaptive though use of analog or digital phase shifting circuitry.
• the pattern of the active array is steered to point in the direction of the one or more users speaking. At the same time nulls can be added to the pattern to notch out point or limited area noise sources.
• the use of the array microphone also helps reduce the cross talk between output from the text to speech engine 124 through the speaker 136 or from another user talking and detection of the user's speech.
• the invention may use an analog or digital fitter 132 between the array microphone or conventional microphone 134 and the speech coder 138 .
• the pass band of the filter can be set to optimize the signal to noise ratio at the input to the speech recognition engine 120 .
• the filter is adaptive, using band shaping combined with notch filtering to reject narrow-band noise.
• One embodiment employs adaptive echo cancellation in the filter. The echo cancellation helps prevent cross talk between output from the text to speech engine and detection of the user's speech as well as suppression of environmentally caused echoes. Algorithms comparing the background noise to the signal received from the users speech may be used to optimize the band-shaping parameters of the adaptive filter.
• the speech received by the array microphone 134 and passed through the filter 132 may be sent to the speech digitizer or coder 138 .
• the speech coder may use adaptive lossy audio compression to optimize bandwidth requirements for the transmission of the coded speech to the speech recognition engine 120 over a wireless link.
• the lossy coding is optimized to preserve only the components of the speech signal required for optimal recognition. Further, the lossy compression algorithms used are designed to prevent even momentary gaps in the signal stream, which can cause severe errors in the speech recognition engine.
• the digitized speech is buffered in the coder and the coder adapts the output data rate to optimize the use of the available bandwidth.
• the use of the adaptive speech coder is particularly advantageous when a band-limited wireless link is used between the coder and the speech recognition engine.
• the microphone can be complemented with an analog or digital (i.e., Voice over IP) speech interface.
• This interface allows a remote user to connect to the system and interact with it in the same manner possible if they were physically present.
• the array microphone can be replaced by a set of physically distributed microphones or headsets worn by the users.
• the distributed microphones can be placed in different parts of a vehicle or room or in different rooms of a building.
• the distributed microphones can create a three-dimensional array to improve signal to noise ration.
• the headset can use a wireless or wired connection.
• the system can support a voice query language.
• the language may be structured to allow a variety of queries and commands with minimal ambiguity.
• the voice query language helps users clearly specify the keywords or contexts of the question or command along with the parameters or criteria.
• the language can provide a grammar to clearly specify the keyword used to determine the context and present a set of one or criteria or parameters. A user asking a question or stating a command in the voice query language may nearly always be guaranteed to receive a response.
• the voice query language can be sensitive to the contents of the context stack.
• a following-on question or command can be asked using an abbreviated grammar, since key words and criteria can be inherited from the stack. For example, the user can simply asked about another keyword if the criteria of the question remain constant.
• the system may provide built in training capabilities to help the user learn the best methods to formulate their questions and commands.
• the interactive training allows the user to audibly or visibly see the machine interpretation of their queries and provides suggestions on how to better structure a query.
• Using the interactive training a user can quickly become comfortable with the voice query language and at the same time learn how to optimize the amount of information required with each step of a dialog.
• the output of the speech coder 122 may be fed to the speech recognition engine 120 .
• the speech recognition engine 120 may recognize words and phrases, using for example, information in the dictionary and phrase tables 112 , and pass these to the parser 118 for interpretation.
• the speech recognition engine 120 may determine the user's identity by voice and name for each utterance. Recognized words and phrases are tagged with this identity in all further processing. Thus, as multiple users engage in overlapping sessions, the tags, added by the speech recognition engine 120 to each utterance, may allow other components of the system to tie that utterance to the correct user and dialog.
• the user recognition capability can also be used as a security measure for applications, such as auctions or online shopping, where this is required. Voice characteristics of each user may be included in the user profile 110 .
• a dialog with the system may begin when a user first addresses it. This can be done by speaking a generic word (“computer”) and/or addressing a specific name (“Fred”), which is generally tied to a system personality 108 . Once the user starts the dialog, they may be recognized by the speech recognition engine 120 , using unique characteristics of their speech. At the end of a dialog or to interrupt a dialog, the user may speak a dismissal word (“good by”).
• Some embodiments may employ a speech recognition engine 124 seeding for improved word recognition accuracy using, for example, data from the dictionary and phrase tables 112 , user profiles 110 , and the agents 106 .
• the fuzzy set possibilities or prior probabilities for the words in the dictionary and phrase tables may be dynamically updated to maximize the probability of correct recognition at each stage of the dialog.
• the probabilities or possibilities can be dynamically updated based on a number of criteria including the application domain, the questions or commands, contexts, the user profile and preferences, user dialog history, the recognizer dictionary and phrase tables, and word spellings.
• the user may be given the option to spell the words.
• the spelling can be done by saying the names or the letters or using a phonetic alphabet.
• the phonetic alphabet can be a default one or one of the user's choosing.
• a user when a user speaks a word that is not recognized correctly or not recognized at all by the speech recognition engine 120 , then they may be asked to spell the word.
• the speech engine may determine this condition based on confidence level for the scoring process.
• the word may be looked up in the dictionary 112 and the pronunciation for the word may be added to either the dictionary, the agent 106 , or the user's profile 110 .
• the word pronunciation can then be associated with the domain, the question, the context and the user. Though this process the speech recognition engine learns with time and improves accuracy.
• an individualized phonetic alphabet can be used. Each user can modify the standard phonetic alphabets with words, which they can remember more easily.
• the tokens and user identification may be passed to the parser 118 .
• the parser examines the tokens for the questions or commands, context and criteria.
• the parser may determine a context for an utterance by applying prior probabilities or fuzzy possibilities to keyword matching, user profile 110 , dialog history, and context stack contents.
• the context of a question or command may determine the domain and thereby, the domain agent 156 , if any, to be invoked. For example, a question with the keywords “temperature” implies a context value of weather for the question. Within a different dialog, the keyword “temperature” can imply a context for a measurement.
• the parser dynamically receives keyword and associated prior probability or fuzzy possibility updates from the system agent 150 or an already active domain agent 156 . Based on these probabilities or possibilities the possible contexts are scored and the top one or few are used for further processing.
• the parser 118 may use a scoring system to determine the mostly likely context or domain for a user's question or command.
• the score can be determined from weighting a number of factors including, the user profile 110 , the domain agent's 156 knowledge and previous context. Based on this scoring, the system may invoke the correct agent. If the confidence level of the score is not high enough to ensure a reliable response, the system can ask a question of the user to verify the question or command is correctly understood.
• the question may be phrased to indicate the context of the question including all criteria or parameters. For example, the question can be in the form of: “Did I understand that you want such-and-such.” If the user confirms that the question is correct, the system may proceed to produce a response. Otherwise, either the user can rephrase the original question, perhaps adding additional information to remove ambiguity, or the system can ask one or more questions to attempt to resolve the ambiguity.
• the parser 118 can invoke the correct agent 156 , 150 .
• the parser will preferably determine required and optional values for the criteria or parameters. These criteria may have been explicitly supplied by the user or may need to be inferred.
• the parser may make use of the criteria handlers 152 supplied by the system agent.
• the criteria handlers can provide context sensitive procedures for extracting the criteria or parameters from the user's question or command. Some criteria may be determined by executing algorithms in the agent, while others may be determined by applying probabilistic or fuzzy reasoning to tables of possible values.
• Prior probabilities or fuzzy possibilities and associated values may be received from a number of sources including, for example, the history of the dialog, the user profile 110 , and the agent. Based on user responses, the prior probabilities or fuzzy possibilities may be updated as the system learns the desired behavior.
• criteria include, location, date and time.
• Other criteria can include command criteria (i.e., yes/no, on/off, pause, stop), and spelling.
• Special criteria handlers are available from the system agent for processing lists, tables, barge-in commands, long strings of text and system commands.
• the criteria handlers 152 can operate iteratively or recursively on the criteria extracted to eliminate ambiguity. This processing may help reduce the ambiguity in the user's question or command. For example, if the user has a place name (or other proper noun) in their utterance the parser 118 can use services of the domain agent 156 to look up tables in the databases 102 for place names or can attempt to determine which word is the proper noun from the syntax of the utterance. In another example, the user asks, “what about flight one hundred and twenty too?” The parser and domain agent use flight information in the database and network information along with context to determine the most plausible interpretation among; flight 100 and flight 20 also, flight 100 and flight 22 , flight 122 , etc.
• the parser 118 may form the question or command in a standard format or hierarchical data structure used for processing by the agents 150 , 156 .
• the parser 118 may fill in all required and some optional tokens for the grammar of the context. Often the tokens must be transformed to values and forms acceptable to the agents.
• the parser obtains the required transformations from the agents, dialog history or user profile 110 . Examples of transformations or substitutions performed by the parser on tokens include: 1) substituting a stock symbol for a company name or abbreviation; 2) substituting a numerical value for a word or words; 3) adding a zip code to an address; and, 4) changing a place or other name to a commonly used standard abbreviation.
• the agents 150 , 156 may receive a command or question once the parser 118 has placed it in the required standard format. Based on the context, the parser can evoke the correct agent to process the question or command.
• Commands can be directed to the system or to an external entity.
• System commands are generally directed to the system agent 150 .
• Commands for external entities are generally processed by a domain agent 156 , which includes the command context and behavior for the external entity.
• Specific questions may be generally directed to one of the domain agents 156 .
• the real-time selection of the correct agent allows the invention to dynamically switch contexts.
• the domain agent may create one or more queries to one or more local or external information sources. Questions can be objective or subjective in nature. Results for objective questions can often be obtained by structured queries to one or more local or network information sources. Even for objective questions, the system may need to apply probabilistic or fuzzy set analysis to deal with cases of conflicting information or incomplete information. Information to answer subjective questions is generally obtained by one or more ad-hoc queries to local or network data sources, followed by probabilistic or fuzzy set evaluation of the one results to determine a best answer.
• the domain agent 156 may be sent to local and/or network information sources.
• the queries may be performed in an asynchronous manner to account for the fact that sources respond at different speeds or may fail to respond at all.
• Duplicate queries can be sent to different information sources to ensure that at least one source responds with a useful result in a timely manner. Further, if multiple results are received in a timely manner, they can be scored by the system to determine which data is most reliable or appropriate. Examples of data sources accommodated include, HTTP data sources, sources with meta-data in various formats including XML, measurement data from sensors using various formats, device 32 setting parameters, entertainment audio, video and game files including MP3, databases using query languages and structured responses such as SQL, and other data sources.
• the local information sources can be stored in one or more system databases 102 or can be on any local data storage such as a set of CDs or DVDs in a player or other local data storage. In other cases, local information can be obtained from vehicle system settings or measurement devices.
• Network information sources can be connected to, the control and device interfaces 30 , the data interfaces 26 , the Internet 42 or other network and accessed through a series of plug-ins or adaptors, known a pluggable sources, in the network interface 116 .
• the pluggable sources are capable of executing the protocols and interpreting the data formats for the data sources of interest.
• the pluggable source provides information scrapping forms and procedures for each source to the domain agents 156 . If a new type of data source is to be used a new plug-in or adaptor can be added to the appropriate interface.
• the domain agent 156 can evaluate the results of the one or more queries as they arrive.
• the domain agent may score the relevance of the results based on results already received, the context, the criteria, the history of the dialog, the user profile 110 and domain specific information using probabilistic or fuzzy scoring techniques.
• Part of the dialog history is maintained in a context stack.
• the weight of each context for the scoring may be based on the relevance of one context to another and the age of the contexts. Other scoring variables can be associated through the context stack.
• Contexts can also be exclusive, so that previous contexts have no weight in the scoring.
• the domain agent 156 may determine if a single best answer can be extracted.
• the desired result may include a set of tokens that may be found to formulate an answer. Once a value has been found for each of these tokens, the results are ready for presentation to the user.
• the tokens can include the date, day of week, predicted high temperature, predicted low temperature, chance of precipitation, expected cloud cover, expected type of precipitation and other tokens.
• Results processed in this manner may include error messages. For subjective questions, this determination is made by determining a most likely answer or answers, extracted by matching of the results received. If no satisfactory answer can be inferred from the results of the query, the agent can do one of the following:
• the domain agent 156 may apply conditional scraping operations to each query response as it is received.
• the conditional scraping actions may depend on the context, the criteria, user profile 110 , and domain agent coding and data.
• a scraping criteria 152 can be created using the services of the system agent 150 .
• the scraping criteria may use format specific scraping methods including, tables, lists, text, and other methods.
• One or more scraping criteria can be applied to a page or results set. Once additional results are received, the domain agent can create new scraping criteria to apply to results already acquired.
• the conditional scarping process removes extraneous information, such as graphics, which need not be further processed or stored, improving system performance.
• Specific commands are generally directed to one of the domain agents 156 .
• the real-time selection of the correct agent allows the invention to dynamically switch contexts.
• Command oriented domain agents 156 evaluate the command and the state of vehicle systems, system capabilities, and measurements to determine if the command can be executed at all or if doing so will exceed operating or safety limits. If the command is ambiguous or cannot be executed for some other reason, the system may ask the user for more information or may suggest what the problem is and a likely approach to the solution.
• the domain agent may format the command for the specific device 32 and control and device interface 30 . This formatting may involve variable substitution, inference of missing values and other formatting. Variable substitution and inference depends on the command context, the user profile 110 , command history, state of vehicle systems and measured values, and other factors.
• a complex command can result in more atomic commands being sent to multiple devices, perhaps in a sequence.
• the sequence and nature of subsequent commands may depend on the previous commands, results of pervious commands, device settings and other measurements.
• measurements are made and results collected to determine if the execution was correct and the desired state or states were reached.
• the agent may format that response for presentation.
• the domain agent can format the response into the markup format used by the text to speech engine 124 .
• the domain agent may format the result presentation using available format templates and based on the context, the criteria, and the user profile 110 .
• the domain agent may perform variable substitutions and transformations to produce a response best understood and most natural to the user.
• the domain agent may vary the order of presentation of tokens and the exact terminology used to create a more natural response to the user.
• the domain agent may also select the presentation personality 108 to be used.
• the domain agent 156 may select the presentation template, determine order of presentation for tokens and determine variable substitutions and transformations using probabilistic or fuzzy set decision methods.
• the template used to form the presentation can be from the domain agent itself or from the user profile 110 .
• the user profile can completely specify the presentation format or can be used to select and then modify an existing presentation format. Selection and formatting of presentation template can also depend on the presentation personality 108 .
• the characteristics of the personality used for the response are dynamically determined using probabilities or fuzzy possibilities derived from the context, the criteria, the domain agent itself and the user profile 110 .
• the domain agent 156 may apply a number of transformations to the tokens before presentation to the user. These variable substitutions and transformations may be derived from a number of sources including, domain information carried by the agent, the context, the token values, the criteria, the personality 108 to be used, and the user profile 110 . Examples of variable substitutions and transformations include: 1) substitution of words for numbers; 2) substitution of names for acronyms or symbols (i.e., trading symbols); 3) use of formatting information derived from the information sources (i.e., HTML tags); 4) nature of the response including, text, long text, list, table; 5) possible missing information or errors; 6) units for measurement (i.e., English or metric); and, 7) preferred terminology from the user profile or presentation personality 108 .
• the invention may provide special purpose presentation capabilities for long text strings, tables, lists and other large results sets.
• Domain agents 156 may use special formatting templates for such results.
• the system agent 150 can provide special criteria handlers 152 for presentation and user commands for large results sets.
• the presentation templates used by the domain agents for large results sets typically include methods for summarizing the results and then allowing the user to query the result in more detail. For example, initially only short summaries, such as headlines or key numbers, are presented. The user can then query the results set further.
• the criteria handlers provide users with the capability to browse large results sets. Commands provided by the criteria handlers for large results sets include, stop, pause, skip, rewind, start, and forward.
• the domain agents 156 apply suitable presentation templates in these cases and present the information through the graphical user interface 114 .
• the system agent 150 provides special criteria handlers 152 for presentation and user commands for display presentations and control.

Landscapes

• Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Mathematical Physics (AREA)
• Theoretical Computer Science (AREA)
• Artificial Intelligence (AREA)
• Human Computer Interaction (AREA)
• Computational Linguistics (AREA)
• Data Mining & Analysis (AREA)
• Databases & Information Systems (AREA)
• General Engineering & Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Navigation (AREA)

Abstract

Description

Claims (55)

Priority Applications (2)

Applications Claiming Priority (2)

Related Child Applications (1)

Publications (2)

Family

ID=32993835

Family Applications (2)

Family Applications After (1)

Country Status (1)

Cited By (413)