CN115050361A - Live voice interaction method, device, storage medium and electronic device - Google Patents

Abstract

The present disclosure relates to a live voice interaction method, device, storage medium and electronic device. The above method includes, when the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, configuring the working state of the above-mentioned live broadcast application as a voice interaction state, and the above voice interaction state is received by parsing the voice input device. The information determines the object and the state of the liquidity information interaction for the above-mentioned object; when the above-mentioned working state is the above-mentioned voice interaction state, in response to the situation of receiving the liquidity information, based on the above-mentioned liquidity information, the interaction for the target object is generated Management information; when the working state is the voice interaction state, in response to receiving the interaction trigger information, the liquidity information interaction content of the target object is generated based on the interaction trigger information and the interaction management information. In the present disclosure, shopping can be completed in the live broadcast room through the whole process of voice.

Description

Live voice interaction method, device, storage medium and electronic device

technical field

The present disclosure relates to the field of Internet technologies, and in particular, to a method, apparatus, storage medium and electronic device for live voice interaction.

Background technique

With the development of Internet technology, live broadcast applications have played more and more roles in people's lives, and the development of e-commerce in live broadcast applications is the general trend. It is not friendly enough for some people with poor eyesight, that is to say, related technologies cannot provide interactive services for some specific groups of people, and the application scenarios of interactive services are obviously limited.

SUMMARY OF THE INVENTION

In order to solve at least one of the above technical problems, the present disclosure provides a live voice interaction method, device, storage medium and electronic equipment. The technical solutions of the present disclosure are as follows:

According to a first aspect of the embodiments of the present disclosure, there is provided a live voice interaction method, including:

When the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, configure the working state of the live broadcast application as a voice interaction state, where the voice interaction state is information received by parsing the voice input device determine the status of an object and the exchange of liquidity information for said object;

When the working state is the voice interaction state, in response to receiving the liquidity information, generating interaction management information for the target object based on the liquidity information;

When the working state is the voice interaction state, in response to receiving the interaction trigger information, the interaction content of the liquidity information of the target object is generated based on the interaction trigger information and the interaction management information.

In an exemplary embodiment, the method further includes:

When the working state is the voice interaction state, the wake-up state of the voice input device is maintained.

In an exemplary embodiment, the method further includes:

When the working state is the voice interaction state, in response to receiving the voice interaction mode closing information, configure the working state as a character interaction state, and configure the voice input device as a non-awakening state , the character interaction state is a state in which an object is determined through information received by a character input device and a liquidity information interaction for the object is performed.

In an exemplary embodiment, when the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, before configuring the working state of the live broadcast application to the voice interaction state, the method further: include:

In response to the fact that the live broadcast application is opened, trigger the voice output device to broadcast first information and wake up the voice input device, where the first information is used to ask the user whether to configure the live broadcast application to the voice interaction state;

Parsing the feedback information for the first information received by the voice input device to obtain a first parsing result;

In the case that the first analysis result indicates that the user has voice interaction willingness, it is determined that the voice interaction mode wake-up information is received.

In an exemplary embodiment, when the working state is the voice interaction state, in response to receiving the liquidity information, before the interaction management information for the target object is generated based on the liquidity information , the method also includes:

In response to a situation in which the live broadcast process reaches the liquidity information interaction period corresponding to the target object, triggering the voice output device to broadcast second information, where the second information is used to ask the user whether to associate with the target object;

Parsing the feedback information for the second information received by the voice input device to obtain a second parsing result;

The liquidity information is received when the second analysis result indicates that the user has a willingness to associate.

In an exemplary embodiment, when the working state is the voice interaction state, in response to receiving the liquidity information, before the interaction management information for the target object is generated based on the liquidity information , the method also includes:

In response to receiving the first target voice during the live broadcast, parsing the first target voice;

The liquidity information is received in response to the fact that the information corresponding to the target object exists in the parsing result.

In an exemplary embodiment, the liquidity information includes at least one item of liquidity information, and the receiving the liquidity information includes:

obtaining at least one attribute item corresponding to the target object;

For each attribute item, trigger the voice output device to broadcast third information corresponding to the attribute item, where the third information is used to request the user to select at least one attribute value corresponding to the attribute item;

Parsing the feedback information for the third information received by the voice input device to obtain the liquidity information item corresponding to the attribute item.

In an exemplary embodiment, the liquidity information includes at least one item of liquidity information, and the receiving the liquidity information includes:

receiving a second target voice, and analyzing the second target voice;

obtaining at least one attribute item corresponding to the target object;

The content corresponding to each attribute item is determined according to the analysis result, and the liquidity information item corresponding to the attribute item is obtained according to the content.

In an exemplary embodiment, when the working state is the voice interaction state, in response to receiving interaction trigger information, generating the interaction trigger information based on the interaction trigger information and the interaction management information. Before interacting with the content of the target object's liquidity information, the method further includes:

After the interaction management information is generated, the voice output device is triggered to broadcast fourth information, where the fourth information is used to request interaction trigger parameters of the user, and the interaction trigger parameters include at least one of the following: interaction trigger mode, Interactive trigger account, interactive trigger password, interactive trigger password, interactive trigger biological information;

The interaction trigger information is obtained according to the received interaction trigger parameter.

In an exemplary embodiment, the generating, based on the interaction trigger information and the interaction management information, the circulation information interaction content of the target object includes:

triggering the voice output device to broadcast fifth information, where the fifth information is used to request the address information of the user;

Parsing the received third target voice to obtain the address information;

The liquidity information interaction content is generated according to the interaction management information, the interaction trigger information and the address information.

In an exemplary embodiment, the analyzing the received third target voice to obtain the address information includes:

Get address template information;

Matching the parsing result for the third target speech with the address template information to obtain the address information.

In an exemplary embodiment, before generating the interaction management information for the target object based on the liquidity information in response to receiving the liquidity information, the method further includes: triggering the voice output device to broadcast the information. each item of liquidity information in the liquidity information;

The generating the interaction management information for the target object based on the circulation information in response to the situation of receiving the circulation information includes: receiving a confirmation instruction for each of the circulation information items in the circulation information In the case of , the interaction management information for the target object is generated based on the liquidity information.

In an exemplary embodiment, before generating the interaction management information for the target object based on the liquidity information in response to receiving the liquidity information, the method further includes:

In response to receiving the fourth target voice, parsing the fourth target voice;

The target content related to the target object is determined according to the analysis result of the fourth target voice, and the voice output device is triggered to broadcast the associated information corresponding to the target content, where the associated information is used to perform an analysis on the target content. explain or give advice.

According to a second aspect of the embodiments of the present disclosure, a live voice interaction device is provided, including:

The switching module is configured to perform, in the case that the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, configure the working state of the live broadcast application as a voice interaction state, and the voice interaction state is through parsing The information received by the voice input device determines the object and the state of the exchange of liquidity information for the object;

a voice processing module configured to perform, in response to receiving the liquidity information, generating interaction management information for the target object based on the liquidity information when the working state is the voice interaction state; and, When the working state is the voice interaction state, in response to receiving the interaction trigger information, the interaction content of the liquidity information of the target object is generated based on the interaction trigger information and the interaction management information.

In an exemplary embodiment, the voice processing module is configured to maintain the wake-up state of the voice input device when the working state is the voice interaction state.

In an exemplary embodiment, the switching module is configured to perform, in the case that the working state is the voice interaction state, in response to receiving the voice interaction mode closing information, configure the working state. is a character interaction state, and the voice input device is configured to be in a non-awakening state, where the character interaction state is a state in which an object is determined through information received by the character input device and a liquidity information interaction for the object is performed.

In an exemplary embodiment, the switching module is configured to perform:

In response to the fact that the live broadcast application is opened, trigger the voice output device to broadcast first information and wake up the voice input device, where the first information is used to ask the user whether to configure the live broadcast application to the voice interaction state;

Parsing the feedback information for the first information received by the voice input device to obtain a first parsing result;

In the case that the first analysis result indicates that the user has voice interaction willingness, it is determined that the voice interaction mode wake-up information is received.

In an exemplary embodiment, the speech processing module is configured to perform:

In response to a situation in which the live broadcast process reaches the liquidity information interaction period corresponding to the target object, triggering the voice output device to broadcast second information, where the second information is used to ask the user whether to associate with the target object;

Parsing the feedback information for the second information received by the voice input device to obtain a second parsing result;

The liquidity information is received when the second analysis result indicates that the user has a willingness to associate.

In an exemplary embodiment, the speech processing module is configured to perform:

In response to receiving the first target voice during the live broadcast, parsing the first target voice;

The liquidity information is received in response to the fact that the information corresponding to the target object exists in the parsing result.

In an exemplary embodiment, the speech processing module is configured to perform:

obtaining at least one attribute item corresponding to the target object;

For each attribute item, trigger the voice output device to broadcast third information corresponding to the attribute item, where the third information is used to request the user to select at least one attribute value corresponding to the attribute item;

Parsing the feedback information for the third information received by the voice input device to obtain the liquidity information item corresponding to the attribute item.

In an exemplary embodiment, the speech processing module is configured to perform:

receiving a second target voice, and analyzing the second target voice;

obtaining at least one attribute item corresponding to the target object;

The content corresponding to each attribute item is determined according to the analysis result, and the liquidity information item corresponding to the attribute item is obtained according to the content.

In an exemplary embodiment, the speech processing module is configured to perform:

After the interaction management information is generated, the voice output device is triggered to broadcast fourth information, where the fourth information is used to request interaction trigger parameters of the user, and the interaction trigger parameters include at least one of the following: interaction trigger mode, Interactive trigger account, interactive trigger password, interactive trigger password, interactive trigger biological information;

The interaction trigger information is obtained according to the received interaction trigger parameter.

In an exemplary embodiment, the speech processing module is configured to perform:

triggering the voice output device to broadcast fifth information, where the fifth information is used to request the address information of the user;

Parsing the received third target voice to obtain the address information;

The liquidity information interaction content is generated according to the interaction management information, the interaction trigger information and the address information.

In an exemplary embodiment, the speech processing module is configured to perform:

Get address template information;

Matching the parsing result for the third target speech with the address template information to obtain the address information.

In an exemplary embodiment, the speech processing module is configured to perform:

triggering the voice output device to broadcast each item of liquidity information in the liquidity information;

In the case of receiving a confirmation instruction for each of the liquidity information items in the liquidity information, the interaction management information for the target object is generated based on the liquidity information.

In an exemplary embodiment, the speech processing module is configured to perform:

In response to receiving the fourth target voice, parsing the fourth target voice;

The target content related to the target object is determined according to the analysis result of the fourth target voice, and the voice output device is triggered to broadcast the associated information corresponding to the target content, where the associated information is used to perform an analysis on the target content. explain or give advice.

According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the first aspect as described above any of the methods.

According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the first aspect of the embodiments of the present disclosure any of the methods.

According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, the computer program product includes a computer program, the computer program is stored in a readable storage medium, and at least one processor of the computer device reads and executes the computer program from the readable storage medium A computer program that causes a computer device to perform the method of any one of the first aspects of the embodiments of the present disclosure.

The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:

The embodiment of the present disclosure completes the acquisition of liquidity information, the generation of interactive management information, the interactive triggering, and the generation of the interactive content of liquidity information through the whole process of voice, which does not require eyesight, and significantly expands application scenarios. Taking the e-commerce scenario as an example, without the need for users to manually input any information, shopping can be completed in the live broadcast room only by means of voice interaction. This technical solution does not require users to use their eyes, but can complete shopping in the live broadcast room only by hearing and issuing voice commands, which is very suitable for users who need to rest their eyes or have poor eyesight. Currently, the number of people who are blind or visually impaired is increasing, and there are some elderly people with poor eyesight. Because of their inconvenience, these users may have a stronger demand for online shopping. The embodiment of the present disclosure supports shopping by voice during live shopping. It can well meet the specific needs of such users.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the principles of the present disclosure and do not unduly limit the present disclosure.

FIG. 1 is a schematic diagram of an implementation environment of a live voice interaction method according to an exemplary embodiment.

FIG. 2 is a flowchart of a method for live voice interaction according to an exemplary embodiment;

3 is a schematic diagram of a scenario of a live voice interaction method according to an exemplary embodiment;

FIG. 4 is a schematic diagram showing a scenario of request confirmation of the liquidity information of the interaction management information obtained according to the example of FIG. 2 according to an exemplary embodiment;

5 is a schematic diagram of another scenario of a live voice interaction method according to an exemplary embodiment;

6 is a schematic diagram of an address information adaptation manner according to an exemplary embodiment;

FIG. 7 shows a flow chart of a specific voice interaction scenario according to an exemplary embodiment;

Fig. 8 shows a block diagram of a live voice interaction apparatus according to an exemplary embodiment;

Fig. 9 is a block diagram of an electronic device according to an exemplary embodiment.

Detailed ways

In order to make those skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first", "second" and the like in the description and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar first objects, and are not necessarily used to describe a specific order or sequence. order. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as recited in the appended claims.

All kinds of information involved in this disclosure are information authorized by the user or fully authorized by all parties.

FIG. 1 is a schematic diagram of an implementation environment of a live voice interaction method according to an exemplary embodiment. Taking the electronic device provided as a terminal as an example, referring to FIG. 1 , the implementation environment specifically includes: a terminal 101 and a server 102 .

The terminal 101 may be at least one of devices such as a smart phone, a smart watch, a desktop computer, a laptop computer, and a laptop portable computer. The terminal 101 can install and run an application program that provides a live broadcast service, and the user can log in to the application program through the terminal 101 to obtain the live broadcast service provided by the application program, and participate in e-commerce shopping in the process of using the live broadcast service. The terminal 101 may generally refer to one of multiple terminals, and this embodiment only takes the terminal 101 as an example for illustration. Those skilled in the art may know that the number of the above-mentioned terminals may be more or less. For example, the above-mentioned terminals may be only a few, or the above-mentioned terminals may be dozens or hundreds, or more, and the embodiments of the present disclosure do not limit the number of terminals and device types.

The server 102 may be at least one of a server, multiple servers, a cloud computing platform, and a virtualization center. The server 102 can be connected to the terminal 101 and other terminals through a wireless network or a wired network. The server 102 can receive voice information sent by the terminal 101 and provide the terminal 101 with live broadcast and e-commerce shopping services according to the received voice information. Of course, the server 102 may also include other functional servers in order to provide more comprehensive and diversified services. Fig. 2 is a flowchart showing a method for live voice interaction according to an exemplary embodiment. As shown in Fig. 2 , the above method includes at least the following steps S10-S30.

In step S10, when the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, the working state of the live broadcast application is configured as a voice interaction state, and the voice interaction state is received by parsing the voice input device. The received information determines the object and the status of the exchange of liquidity information for the above object.

The embodiments of the present disclosure do not limit the interaction of objects and liquidity information, which may have corresponding meanings according to different scenarios. For example, in an e-commerce scenario, an object may refer to an item traded by e-commerce, and an exchange of liquidity information may refer to an object transaction for this item.

The present disclosure does not limit the live broadcast application, and the voice interaction mode wake-up information can be received when the live broadcast application is opened, so that the user can conduct e-commerce shopping based on voice when accessing any live broadcast room. It is also possible to receive the voice interaction mode wake-up information when the live application is opened and the user enters a specific live room. After receiving the voice interaction mode wake-up information, the voice interaction state can be entered. In this state, the voice input device As the only device for receiving the information input by the user, the live application determines the object by parsing the information received by the voice input device and performs the exchange of liquidity information for the above object. In the embodiment of the present disclosure, by setting the voice interaction state, the user can be provided with a whole-process voice-based interactive live broadcast e-commerce service in this state. The embodiments of the present disclosure do not limit the specific type of the voice input device, which may be various microphones or other devices capable of inputting voice.

In the embodiment of the present disclosure, when the working state is the voice interaction state, the wake-up state of the voice input device is maintained. That is to say, when the working state of the live broadcast application is configured as the voice interaction state, the voice input device is in the wake-up state, and the user can participate in the e-commerce activities in the live broadcast room through voice. order, select objects, trigger liquidity information interaction, etc.

In step S20, when the working state is the voice interaction state, in response to receiving the liquidity information, the interaction management information for the target object is generated based on the liquidity information.

The embodiments of the present disclosure do not limit the liquidity information, and in an e-commerce scenario, it may refer to order information for items. The embodiment of the present disclosure does not limit its specific content, which may include various information of the target object to be exchanged with liquidity information, such as the type, size, color, price, quantity, transportation method, etc. of the target object. The target object can be understood as any object listed in the live broadcast room. The user's voice can be acquired through the voice input device, and the liquidity information can be obtained according to the received voice.

The embodiment of the present disclosure does not limit the interaction management information, which may refer to an item order in an e-commerce scenario. Specifically, the interaction management information refers to an information collection formed by acquired information related to the target The interactive management information, combined with the user's address information and liquidity information, can be used for the exchange of liquidity information to obtain the content of the exchange of liquidity information. The interactive content of liquidity information can also implement operations required by other e-commerce links such as receipt operations, refund operations, rights protection operations, and logistics inquiries.

In step S30, when the working state is the voice interaction state, in response to receiving the interaction trigger information, the liquidity information interaction content of the target object is generated based on the interaction trigger information and the interaction management information.

The embodiment of the present disclosure does not limit the specific meaning of the interaction trigger information. Taking an e-commerce scenario as an example, it can refer to payment information generated for purchasing an e-commerce item. Specifically, the interaction trigger information can be understood as the user is the The information required by the target object in the interaction management information to trigger interaction. Of course, the embodiment of the present disclosure does not limit the specific meaning of the interactive content of liquidity information. In an e-commerce scenario, it may represent a transaction order generated for a target object.

After the interaction triggering information is obtained, the interaction triggering operation can be performed on the above interaction management information, and after the interaction triggering is successful, the circulation information interaction content is generated, and the circulation information interaction content is the certificate obtained by the circulation information interaction. So far, the acquisition of liquidity information, the generation of interactive management information, the interaction trigger, and the generation of liquidity information interactive content have been completed through the whole process of voice. Taking the e-commerce scenario as an example, without the need for users to manually input any information, Shopping in the live broadcast room can be completed by voice interaction alone. This technical solution does not require users to use their eyes, but can complete shopping in the live broadcast room only by hearing and issuing voice commands, which is very suitable for users who need to rest their eyes or have poor eyesight. Currently, the number of people who are blind or visually impaired is increasing, and there are some elderly people with poor eyesight. Because of their inconvenience, these users may have a stronger demand for online shopping. The embodiment of the present disclosure supports shopping by voice during live shopping. , which can well meet the specific needs of such users.

In an exemplary embodiment, when the working state is the voice interaction state, in response to receiving the voice interaction mode closing information, the working state is configured as a character interaction state, and the voice input device is configured as a character interaction state. It is configured in a non-awakening state, and the above character interaction state is a state in which an object is determined through information received by a character input device and a liquidity information interaction for the above object is performed.

That is to say, when the above working state is the above voice interaction state, the user can switch the working state to the character interaction state by sending out the voice interaction mode closing message, and the character interaction state can be understood as the shopping frequently used by ordinary users. In this state, information can be input through character input devices such as keyboard, mouse, touch screen, etc., so as to complete the selection of objects and the exchange of information on the circulation of objects. That is to say, the embodiment of the present disclosure provides an e-commerce shopping solution in voice mode, and also provides a common e-commerce shopping solution, which fully meets different shopping needs of different types of users by being compatible with the two shopping solutions and allowing users to switch at will.

In an exemplary embodiment, when the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, before configuring the working state of the live broadcast application to the voice interaction state, the method further includes: In response to the above-mentioned live application being opened, trigger the voice output device to broadcast the first information and wake up the above-mentioned voice input device, and the above-mentioned first information is used to ask the user whether to configure the above-mentioned live application to the above-mentioned voice interaction state; Parse the above-mentioned voice input device A first analysis result is obtained from the received feedback information for the above-mentioned first information; if the above-mentioned first analysis result indicates that the user has a voice interaction willingness, it is determined that the above-mentioned voice interaction mode wake-up information is received.

The present disclosure does not limit the voice output device, for example, it may be a peripheral device such as a speaker and a sound box. When the live broadcast application is opened, the voice output device may be triggered to play a piece of voice (first information), so that the user can choose whether to set the live broadcast application to a voice interaction state. For example, the first information can be "whether to enter the voice live broadcast room" or "please select the interactive mode, if you want to enter the voice live broadcast state, please issue the 'voice live broadcast' password, otherwise, please issue the 'normal live broadcast' password". After hearing the first information, the user may give feedback in the form of voice, for example, the feedback voice may be "yes" or "voice live broadcast".

When the first information is "whether to enter the voice live broadcast room" and the voice feedback from the user is "Yes", or when the first information is "Please select the interactive mode, if you want to enter the voice live broadcast state, please issue the 'voice live broadcast' password , otherwise, please issue the 'normal live broadcast' password" and the voice feedback from the user is "voice live broadcast", it can be determined that the user has the voice interaction willingness, therefore, it can be considered that the above voice interaction mode wake-up information is received, and then the user can automatically enter the Voice interaction status, support the whole voice-based way to provide users with an e-commerce shopping experience. In this implementation manner, the user can be provided with an entrance to trigger the live application to enter the voice interaction state in time, and the voice interaction state can be quickly entered, thereby providing a better experience for users with poor eyesight.

In an exemplary embodiment, when the working state is the voice interaction state, in response to receiving the liquidity information, before the interaction management information for the target object is generated based on the liquidity information, the above method is performed. It also includes: triggering the voice output device to broadcast second information in response to the live broadcast process reaching the liquidity information interaction period corresponding to the target object, and the second information is used to inquire whether the user is associated with the target object; parsing the voice input The device receives the feedback information for the second information, and obtains a second analysis result; and in the case that the second analysis result represents the user's willingness to associate, the device receives the liquidity information. Specifically, in an e-commerce scenario, a user is associated with a target object, which means that the user purchases the target object.

As the live broadcast progresses, the host may list many objects in turn. When each object is listed, a period of time can be set aside for the user to place an order for the object. The live broadcast application can trigger the above-mentioned voice output device to broadcast a piece of content during this time period. two information) to ask the user whether to place an order to associate the object. For example, the anchor has put an electric toothbrush on the shelf and prompted the audience to place an order. In this case, the second message "The current anchor has an electric toothbrush on the shelf, may I ask if it is related?", if the user feedback voice information is "Yes", " Contents such as "I buy" or "I want" can determine the user's willingness to associate, and in this case, you can continue to conduct voice interaction with the user to obtain subsequent liquidity information. This solution can accompany the live broadcast process, and actively ask the user whether there is a related demand for each listed object, providing users with an opportunity to place an order in a timely manner, to ensure that users will not miss because of invisible, unclear or inconvenient to use the mouse and keyboard. A single opportunity to enhance the user's shopping experience.

In another exemplary embodiment, when the working state is the voice interaction state, in response to receiving the liquidity information, before the interaction management information for the target object is generated based on the liquidity information, the above The method further includes: in response to receiving the first target voice during the live broadcast, parsing the first target voice; in response to the analysis result having information corresponding to the target object, receiving the liquidity information.

Of course, at any point in the live broadcast process, the user can trigger the ordering process for the objects listed in the live broadcast process, that is to say, the user can output the voice for placing the order (the first target voice) at any time. , for example, the current live broadcast room has a total of four types of objects: "windbreaker", "lipstick", "fan" and "drink". At any time during the live broadcast, users can place an order for the above four objects. For example, you can output "I Want to buy a windbreaker”, “I want a fan”, etc. can trigger the live broadcast application to interact with the user by voice, and then obtain specific liquidity information.

The embodiment of the present disclosure does not limit the specific content of the first target voice. For example, if it is determined that there are objects listed in the live broadcast room and words expressing the user's associated wishes in the received voice, it can be determined that the first target voice is received. Or if the received voice contains preset command words, such as "place an order", you can trigger the voice output device to play the corresponding response "please place an order", and after the response is played, it will be received again through the voice input device. The voice can be regarded as the first target voice. This solution allows users to place an order for shopping at any time during the live broadcast, further enhancing the shopping experience.

In an exemplary embodiment, the liquidity information includes at least one liquidity information item, and the receiving the liquidity information includes: acquiring at least one attribute item corresponding to the target object; for each attribute item, triggering the voice The output device broadcasts the third information corresponding to the above-mentioned attribute item, and the above-mentioned third information is used to request the user to select at least one attribute value corresponding to the above-mentioned attribute item; parses the feedback information for the above-mentioned third information received by the above-mentioned voice input device, Obtain the liquidity information item corresponding to the above attribute item.

For example, if the user associates a windbreaker, the windbreaker object includes at least four attribute items, namely size, color, quantity and version. Correspondingly, the liquidity information items that need to be filled in include at least windbreaker size, windbreaker color, windbreaker Quantity, windbreaker version. The user can be guided to select the specific attribute values of the above-mentioned four attributes in a way of item-by-item interaction, and the corresponding liquidity information items can be obtained according to the selection results, and then the total liquidity information can be obtained.

As shown in Figure 3, the voice output device can broadcast "Please select the size of the windbreaker, S, M, L" and wait for the user's input. After the voice input device receives the voice "M", the specific attribute value of "size" Determined to be "M". Then, the voice output device can broadcast "Please select the color of the windbreaker, black, gray, white" and wait for the user's input. After the voice input device receives the voice "black", the specific attribute value of "color" is determined as "black" ". Then, the voice output device can broadcast "Please determine the number of windbreakers" and wait for the user's input. After the voice input device receives the voice "2", the specific attribute value of "quantity" is determined as "2". Then, the voice output device can broadcast "Please select the style of the windbreaker, loose, slim fit" and wait for the user's input. After the voice "Slim fit" received by the voice input device, the specific attribute value of the "fit" is determined as "Slim fit" ".

Please refer to FIG. 4 , which shows a schematic diagram of a scenario of request confirmation of the liquidity information of the interaction management information obtained according to the example of FIG. 3 . In the example of Figure 3, the liquidity information corresponding to the target object can be obtained:

Target object: windbreaker;

Windbreaker size: M;

Windbreaker color: black;

Number of windbreakers: 2;

Windbreaker Fit: Slim fit.

Confirmation can be requested by broadcasting the circulation information, and after confirmation by the user, interactive management information for the target object—the windbreaker can be generated according to the circulation information. In this embodiment, the user's determination result of the attribute value of each attribute item is determined in a way of item-by-item guidance, and the content of important attribute items is not omitted, so as to obtain interactive management information that fully meets the user's wishes and ensure that the ordering process does not fail. Errors occur to improve the user's shopping experience.

In another embodiment, the liquidity information includes at least one item of liquidity information, and the receiving the liquidity information includes: receiving a second target voice, and analyzing the second target voice; acquiring at least one item corresponding to the target object An attribute item; the content corresponding to each of the above attribute items is determined according to the analysis result, and the liquidity information item corresponding to the above attribute item is obtained according to the above content.

In this embodiment, after entering the ordering state, the user can send out a piece of voice (the second target voice), and the ordering state can be entered by means of the first target voice sent out above. The second target voice may include content related to one or more attribute items of the target object, and by analyzing the second target voice, content corresponding to the relevant attribute items may be obtained. Please refer to Figure 5, after entering the order state, the user outputs a voice (second target voice), the second target voice can be "I want to buy a black slim fit windbreaker", then it can be determined that the next target voice in the liquidity information three things:

Target object: windbreaker;

Windbreaker color: black;

Windbreaker Fit: Slim fit.

Combining the above, it can be seen that the content of the circulation information is not enough. In this case, a voice prompt can be given to the user to guide the user to make a new second target voice again, such as triggering the voice output device to play "Please continue to say the number and size of the windbreaker". , the user continues to issue a new second target voice "I want to buy two windbreakers of size M", in this case, the following two contents in the order can be determined:

Windbreaker size: M;

Number of trench coats: 2.

At this point, the liquidity information is complete. In this embodiment, the entire content of the liquidity information can be quickly determined through one or a limited number of voice interactions, the interaction efficiency is high, the ordering speed is fast, and information loss or error will not occur.

At least two ways to obtain liquidity information are given in the preceding paragraph. In the process of obtaining the liquidity information items in the liquidity information, the voice output device can also request the user to confirm each determined liquidity information item. After obtaining complete liquidity information, the voice output device can be triggered to broadcast the specific content of the liquidity information "Please confirm the following: target object: windbreaker; windbreaker size: M; windbreaker color: black; windbreaker quantity: 2; windbreaker version : Self-cultivation." If the user feedback "all correct", interactive management information can be generated. If the user feedbacks that there is an incorrect item of liquidity information, the user can continue to perform voice interaction until the liquidity information is all correct. That is, in the embodiment of the present disclosure, when a confirmation instruction for each of the above-mentioned liquidity information items in the above-mentioned liquidity information is received, the interaction management information for the target object is generated based on the above-mentioned liquidity information. By confirming the contents of the liquidity information with the user, it ensures that the generated interactive management information meets the user's expectations, reduces the probability of mistakenly placing an order, and improves the user experience.

In one embodiment, when the working state is the voice interaction state, in response to receiving the interaction trigger information, the interaction content of the liquidity information of the target object is generated based on the interaction trigger information and the interaction management information. Before, the method further includes: after generating the interaction management information, triggering the voice output device to broadcast fourth information, where the fourth information is used to request interaction trigger parameters of the user, and the interaction trigger parameters include at least one of the following: Trigger method, interaction trigger account, interaction trigger password, interaction trigger password, interaction trigger biological information; the interaction trigger information is obtained according to the received interaction trigger parameters.

The embodiment of the present disclosure does not limit the interactive triggering method. For example, it can support the interactive triggering of multiple authentication methods such as fingerprint, password, password, iris, face, etc., and also does not limit the interactive triggering channel. For example, the live broadcast application can provide interactive triggering. The trigger channel can also be connected to the interaction trigger channel of any third party. The information related to the interaction trigger is encapsulated as the interaction trigger parameter, and the user is triggered to give the interaction trigger parameter by means of voice interaction with the user, thereby generating the interaction trigger information.

In one embodiment, after acquiring the interaction management information and interaction trigger information, it is also necessary to acquire the delivery address of the target object. In this case, the above-mentioned circulation of the target object is generated based on the interaction trigger information and the interaction management information. Sexual information interaction content, including: triggering the voice output device to broadcast fifth information, where the fifth information is used to request the address information of the user; parsing the received third target voice to obtain the address information; according to the interaction management information , the above interaction trigger information and the above address information to generate the above liquidity information interaction content. The embodiment of the present disclosure does not limit the address information, which may include the user's name, phone number, address, zip code, etc., and may also include optional delivery information, for example, select weekday delivery or rest day delivery, morning delivery or Afternoon delivery, whether to pay on delivery, whether to associate delivery insurance, etc. The embodiments of the present disclosure support fully automatic voice acquisition of target object information, fully automatic voice acquisition of interactive trigger information, and fully automatic voice acquisition of address information, thereby realizing voice-based live shopping throughout the entire process and improving user experience.

The embodiment of the present disclosure does not limit the address information parsing method. As shown in FIG. 6 , address template information can be obtained; the parsing result for the third target voice is matched with the address template information to obtain the address information. That is to say, the embodiments of the present disclosure can generate address information according to an address template in an intelligent matching manner. For example, according to the specific address in the parsing result, the province, city, district, house number, floor, building in the address template can be automatically generated. Items such as brand names are adapted to the corresponding content, thereby improving the standardization of address information and reducing the probability of wrong delivery of target objects. Of course, address information can also be confirmed to users by voice broadcast.

In one embodiment, before generating the interaction management information for the target object based on the liquidity information in response to receiving the liquidity information, the method further includes: in response to receiving the fourth target voice, performing The fourth target voice is analyzed; the target content related to the above-mentioned target object is determined according to the analysis result of the above-mentioned fourth target voice, and the above-mentioned voice output device is triggered to broadcast the associated information corresponding to the above-mentioned target content, and the above-mentioned associated information is used for the above-mentioned target content. Explain or give advice.

The embodiment of the present disclosure does not limit the specific content and the opportunity of issuing the fourth target voice. For example, the user can send out the fourth target voice at any time point in the live broadcast process, and the fourth target voice can request to explain the relevant content of the target object. Or give suggestions. For example, there are four objects "towel", "soap", "electric toothbrush", and "wool coat" on the live platform, and the user can make the following voice "I want to know that the electric toothbrush can be used on a single charge. For how long", information about the power consumption of electric compression can be automatically broadcast to the user. For another example, the user can also issue "how to wash the woolen coat", and then the precautions for cleaning the woolen coat can be automatically broadcast to the user. The embodiments of the present disclosure can automatically answer questions and give relevant suggestions in the process of watching the live broadcast by the user by means of voice interaction, so as to further improve the live broadcast experience.

Please refer to FIG. 7 , which shows a flowchart of a specific voice interaction scenario in an embodiment of the present disclosure. The voice interaction process includes at least the following steps:

First, after the user enters the live room, the user is asked about the interaction mode of the live room. If the user selects the voice interaction mode, a corresponding voice live broadcast room is provided for the user. In the voice live broadcast room, the microphone (voice input device) is always awake. If the microphone receives the first target voice sent by the user, the order placement process can be entered. During the ordering process, the order information is obtained by interacting with the user through voice, and the item order is generated according to the order information. Then continue to obtain payment information through voice interaction with the user, complete payment and generate transaction orders according to the payment information, thus successfully completing a full-course voice e-commerce shopping.

Fig. 8 is a block diagram of a live voice interaction apparatus according to an exemplary embodiment. Referring to Figure 8, the device includes:

The switching module 10 is configured to perform, in the case that the live broadcast application is opened, in response to the situation of receiving the voice interaction mode wake-up information, configure the working state of the above-mentioned live broadcast application as a voice interaction state, and the above-mentioned voice interaction state is to analyze the voice The information received by the input device determines the object and the status of the exchange of liquidity information for the above object;

The voice processing module 20 is configured to perform, in response to receiving the liquidity information, in the case that the above-mentioned working state is the above-mentioned voice interaction state, based on the above-mentioned liquidity information, the interaction management information for the target object is generated; When the working state is the voice interaction state, in response to receiving the interaction trigger information, the liquidity information interaction content of the target object is generated based on the interaction trigger information and the interaction management information.

In an exemplary embodiment, the voice processing module is configured to maintain the wake-up state of the voice input device when the working state is the voice interaction state.

In an exemplary embodiment, the above-mentioned switching module is configured to perform, in the case that the above-mentioned working state is the above-mentioned voice interactive state, in response to receiving the voice interactive mode closing information, configure the above-mentioned working state as a character interactive state. , and configure the above voice input device to be in a non-awakening state, and the above character interaction state is a state in which an object is determined by the information received by the character input device and the liquidity information exchange for the above object is performed.

In an exemplary embodiment, the above-mentioned switching module is configured to perform:

In response to the above-mentioned live application being opened, trigger the voice output device to broadcast the first information and wake up the above-mentioned voice input device, and the above-mentioned first information is used to ask the user whether to configure the above-mentioned live application to the above-mentioned voice interaction state;

Parsing the feedback information for the first information received by the voice input device to obtain a first parsing result;

In the case that the above-mentioned first analysis result indicates that the above-mentioned user has a voice interaction willingness, it is determined that the above-mentioned voice interaction mode wake-up information is received.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

In response to the situation in which the live broadcast process reaches the liquidity information interaction period corresponding to the above-mentioned target object, trigger the above-mentioned voice output device to broadcast the second information, and the above-mentioned second information is used to ask the user whether to associate the above-mentioned target object;

Parsing the feedback information for the second information received by the voice input device to obtain a second parsing result;

In the case that the above-mentioned second analysis result indicates that the above-mentioned user has a willingness to associate, the above-mentioned liquidity information is received.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

In response to receiving the first target voice during the live broadcast, parse the above-mentioned first target voice;

In response to the fact that the information corresponding to the above-mentioned target object exists in the analysis result, the above-mentioned liquidity information is received.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

Obtain at least one attribute item corresponding to the above target object;

For each attribute item, trigger the above-mentioned voice output device to broadcast the third information corresponding to the above-mentioned attribute item, and the above-mentioned third information is used to request the user to select at least one attribute value corresponding to the above-mentioned attribute item;

Parse the feedback information for the third information received by the voice input device to obtain the liquidity information item corresponding to the attribute item.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

receiving the second target voice, and analyzing the above-mentioned second target voice;

Obtain at least one attribute item corresponding to the above target object;

The content corresponding to each attribute item is determined according to the analysis result, and the liquidity information item corresponding to the attribute item is obtained according to the content.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

After the interaction management information is generated, the voice output device is triggered to broadcast fourth information, where the fourth information is used to request interaction trigger parameters of the user, and the interaction trigger parameters include at least one of the following: an interaction trigger mode, an interaction trigger account, Interactive trigger password, interactive trigger password, interactive trigger biological information;

The interaction trigger information is obtained according to the received interaction trigger parameters.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

Trigger the above-mentioned voice output device to broadcast fifth information, and the above-mentioned fifth information is used to request the address information of the user;

Parsing the received third target voice to obtain the above address information;

According to the above-mentioned interaction management information, the above-mentioned interaction trigger information and the above-mentioned address information, the above-mentioned liquidity information interaction content is generated.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

Get address template information;

The above-mentioned address information is obtained by matching the analysis result for the above-mentioned third target speech with the above-mentioned address template information.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

Trigger the above-mentioned voice output device to broadcast each liquidity information item in the above-mentioned liquidity information;

In the case of receiving a confirmation instruction for each of the above-mentioned liquidity information items in the above-mentioned liquidity information, the interaction management information for the target object is generated based on the above-mentioned liquidity information.

In an exemplary embodiment, the above-mentioned speech processing module is configured to perform:

In response to receiving the fourth target voice, parse the above-mentioned fourth target voice;

The target content related to the target object is determined according to the analysis result of the fourth target voice, and the voice output device is triggered to broadcast associated information corresponding to the target content, where the associated information is used to explain or provide suggestions for the target content.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

FIG. 9 is a block diagram of an electronic device 600 for live-streaming voice interaction according to an exemplary embodiment.

The electronic device may be a server or a terminal device, and its internal structure diagram may be as shown in FIG. 9 . The electronic device includes a processor, memory, and a network interface connected by a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. The computer program implements a live voice interaction method when executed by the processor.

Those skilled in the art can understand that the structure shown in FIG. 9 is only a block diagram of a partial structure related to the solution of the present disclosure, and does not constitute a limitation on the electronic device to which the solution of the present disclosure is applied. The specific electronic device may be Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In an exemplary embodiment, there is also provided an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the present disclosure The live voice interaction method in the example.

In an exemplary embodiment, a computer-readable storage medium is also provided, when the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the live voice in the embodiment of the present disclosure interactive method.

In an exemplary embodiment, a computer program product is also provided, the computer program product includes a computer program, the computer program is stored in a readable storage medium, and at least one processor of the computer device reads from the readable storage medium and executes the computer The program enables the computer device to execute the live voice interaction method of the embodiment of the present disclosure.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium , when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Other embodiments of the present disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or techniques in the technical field not disclosed by the present disclosure . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise structures described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (10)

1. a kind of live voice interaction method, is characterized in that, comprises: When the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, configure the working state of the live broadcast application as a voice interaction state, where the voice interaction state is information received by parsing the voice input device determine the status of an object and the exchange of liquidity information for said object; When the working state is the voice interaction state, in response to receiving the liquidity information, generating interaction management information for the target object based on the liquidity information; When the working state is the voice interaction state, in response to receiving the interaction trigger information, the interaction content of the liquidity information of the target object is generated based on the interaction trigger information and the interaction management information. 2. The live voice interaction method according to claim 1, wherein the method further comprises: When the working state is the voice interaction state, the wake-up state of the voice input device is maintained. 3. The live voice interaction method according to claim 1, wherein the method further comprises: When the working state is the voice interaction state, in response to receiving the voice interaction mode closing information, configure the working state as a character interaction state, and configure the voice input device as a non-awakening state , the character interaction state is a state in which an object is determined through information received by a character input device and a liquidity information interaction for the object is performed. 4. The live voice interaction method according to any one of claims 1 to 3, wherein, when the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, the described Before the working state of the live broadcast application is configured as the voice interaction state, the method further includes: In response to the fact that the live broadcast application is opened, trigger the voice output device to broadcast first information and wake up the voice input device, where the first information is used to ask the user whether to configure the live broadcast application to the voice interaction state; Parsing the feedback information for the first information received by the voice input device to obtain a first parsing result; In the case that the first analysis result indicates that the user has voice interaction willingness, it is determined that the voice interaction mode wake-up information is received. 5. The live voice interaction method according to claim 4, wherein, in the case that the working state is the voice interaction state, in response to the situation of receiving liquidity information, based on the liquidity Before generating the interactive management information for the target object, the method further includes: In response to a situation in which the live broadcast process reaches the liquidity information interaction period corresponding to the target object, triggering the voice output device to broadcast second information, where the second information is used to ask the user whether to associate with the target object; Parsing the feedback information for the second information received by the voice input device to obtain a second parsing result; The liquidity information is received when the second analysis result indicates that the user has a willingness to associate. 6. The live voice interaction method according to claim 4, wherein, in the case that the working state is the voice interaction state, in response to the situation of receiving liquidity information, based on the liquidity Before generating the interactive management information for the target object, the method further includes: In response to receiving the first target voice during the live broadcast, parsing the first target voice; The liquidity information is received in response to the fact that the information corresponding to the target object exists in the parsing result. 7. A live voice interaction device, characterized in that, comprising: The switching module is configured to perform, in the case that the live broadcast application is opened, in response to receiving the voice interaction mode wake-up information, configure the working state of the live broadcast application as a voice interaction state, and the voice interaction state is through parsing The information received by the voice input device determines the object and the state of the exchange of liquidity information for the object; a voice processing module configured to perform, in response to receiving the liquidity information, generating interaction management information for the target object based on the liquidity information when the working state is the voice interaction state; and, When the working state is the voice interaction state, in response to receiving the interaction trigger information, the interaction content of the liquidity information of the target object is generated based on the interaction trigger information and the interaction management information. 8. An electronic device, characterized in that, comprising: processor; a memory for storing the processor-executable instructions; Wherein, the processor is configured to execute the instructions to implement the live voice interaction method according to any one of claims 1 to 6. 9. A computer-readable storage medium, characterized in that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any one of claims 1 to 6 The live voice interaction method described in item. 10. A computer program product, characterized in that the computer program product comprises a computer program, and the computer program is stored in a readable storage medium, and at least one processor of a computer device reads from the readable storage medium and stores it. Executing the computer program causes the computer device to execute the live voice interaction method according to any one of claims 1 to 6.

Images