CN103488525A - Determination of user preference relevant to scene - Google Patents

Abstract

Embodiments of the invention provide a method, apparatus and computer program product for determining context-related user preferences. The method includes recording a context in which one or more items of the mobile device are being used. The method also includes determining one or more sub-scenario spaces based on the distribution of the scenarios. In addition, the method further includes forming a corresponding preference mode for each sub-context space, so that when it is detected that the mobile device is in a sub-context space, according to the preference mode corresponding to the one sub-context space, display the corresponding s project. According to some embodiments of the present invention, among the user preferences related to the context, items frequently used by the user in the context are sorted, so that the user can obtain the frequently used items conveniently and quickly.

Description

Determining contextually relevant user preferences

technical field

Embodiments of the invention relate to determining preferences of a user of a mobile device. More specifically, embodiments of the invention relate to methods, devices and computer program products for determining context-dependent user preferences in mobile devices.

Background technique

For users of mobile devices, it is very important to be able to quickly find their desired contacts from a phonebook in which many contacts are recorded. The currently used phone book already supports the search function. With the help of the search function, the user searches for interested contacts by performing various types of input on the mobile device. However, it is not very convenient to search and input contacts on the mobile device. Ideally, a mobile device would enable the contacts a user wishes to contact to appear directly and prominently in the contact list, eliminating the need for the user to search. Some current smart phone books can list the most frequently contacted contacts at the top of the phone book, which is more convenient than a simple alphabetical order.

It has also been noted that users of mobile devices often need to contact different people in different scenarios. Taking the location and time scenario as an example, some users may contact their friends when they are at home on weekends, and their clients and colleagues when they are working in the office. Therefore, it is very convenient for the selection of contacts to be able to automatically arrange the contacts that the user is most likely to contact in a specific situation. Further, such a context-dependently arranged phone book can have personalized customization, since different users may have different modes of contacting others.

In the prior art, some methods for sorting frequently contacted contacts of a user of a mobile device have also been disclosed. For example, in US patent application US20080161059 a method is disclosed for optimized sorting of numbers of a particular contact according to communication type (e.g. call, SMS and MMS), according to time of day and/or date (and according to communication type) A method for optimal ordering of numbers for a particular contact, and a method for determining dynamic options or softkeys for a contact number based on the most typical communications for that number. However, the implementation disclosed in this application is mainly based on simple counters depending on the type of communication and/or the date of time, which does not take full account of the context. In the United States patent application US 2011/0231407, a context-related phone book is mentioned, but it only stays at the conceptual level and lacks specific implementation means.

It can be seen that the prior art does not consider how to provide the user with a context-related phone book according to different scenarios, for example, according to different times or locations.

In addition, users of mobile devices often install many applications on the mobile devices. If the user interface of the system can list the applications that are most likely to be used in a given situation in the most prominent position on the home screen, then the user can avoid the cumbersome process of finding the desired application. Such a function is very useful for mobile phones, such as the Windows ^™ Phone platform, because its applications are organized by list, so that commonly used applications in specific scenarios will appear in a prominent position on the main screen in the form of a list, so that users can make Intuitive selection.

It can be seen that the user's personal preferences in different scenarios need to be considered, so that in a given scenario, the user preferences related to the given scenario are automatically provided to the user, thereby saving the user from tedious manual selection.

Contents of the invention

Aiming at the problems existing in the prior art, embodiments of the present invention provide a method, device and computer program product for determining context-related user preferences.

According to an exemplary embodiment of the present invention, a method is provided. The method includes recording a context in which one or more items of the mobile device are being used. The method also includes determining one or more sub-scenario spaces based on the distribution of the scenarios. In addition, the method further includes forming a corresponding preference mode for each sub-context space, so that when it is detected that the mobile device is in a sub-context space, display the corresponding s project.

In one embodiment, based on the distribution of scenarios, determining one or more sub-scenario spaces comprises: identifying one or more clusters of scenarios in the distribution of scenarios; and dividing at least one of the clusters of scenarios into a sub-scenario in space.

In another embodiment, according to the context distribution, determining one or more sub-context spaces further includes: merging sub-context spaces with similar context distributions for different items.

Further, in this embodiment, merging sub-context spaces with similar situational distributions for different items further includes: comparing the situational distributions of the two projects to determine a similarity measure between the situational distributions; and When the similarity measure is greater than a first threshold, the sub-context spaces for the two items are merged.

In another embodiment, for each sub-scenario space, forming a corresponding preference pattern further includes: dividing scenarios overlapping in multiple preference patterns into one of the preference patterns.

Further, in this embodiment, a greedy algorithm is used to divide the overlapping scenarios into one of the preference modes.

Furthermore, in this embodiment, checking the ranking changes among items in multiple preference modes when the overlapping scenarios are absorbed; and dividing the overlapping scenarios into those with small ranking changes between items preferred mode.

In another embodiment, the sub-scenario space and the corresponding preference mode are stored in the mobile device or the remote server in the form of a scenario tree.

Further, in this embodiment, the scenario tree is updated dynamically or periodically.

In yet another embodiment, for each sub-scenario space, forming a corresponding preference pattern includes: for each sub-scenario space, according to at least one property of the respective historical usage conditions of at least a part of the one or more items, for each sub-scenario space, The at least a portion of items are sorted to form corresponding preference patterns.

Further, in this embodiment, the at least one property includes at least one of historical usage times, historical usage frequency, historical usage location, historical usage time, and historical usage duration.

In yet another embodiment, the items include contacts of a phonebook of the mobile device or applications used.

In yet another embodiment, recording the scenarios when one or more items of the mobile device are used includes: recording activities of the user of the mobile device at different times and locations.

According to another exemplary embodiment of the present invention, a method is provided. The method includes detecting one or more items and corresponding contexts being used in the mobile device. The method also includes determining that the context is within a predetermined subcontext space. In addition, the method further includes displaying corresponding items according to a preference mode corresponding to the predetermined sub-context space.

In one embodiment, the predetermined sub-context space and the corresponding preference mode are stored in the mobile device or a remote server in the form of a situation tree.

Further, in this embodiment, according to the preference mode corresponding to the predetermined sub-scenario space, displaying corresponding items includes: mapping the scenario to the sub-scenario space in the scenario tree; The preference mode corresponding to the sub-scenario space determines the preference mode related to the scenario to display corresponding items.

Furthermore, in this embodiment, the scenario tree is dynamically or periodically updated according to the usage of the one or more items.

In another embodiment, the items include contacts of a phonebook of the mobile device or applications used.

In yet another embodiment, detecting the one or more items being used in the mobile device and the corresponding context includes: detecting the one or more items being used in the mobile device and the corresponding time and place.

According to yet another exemplary embodiment of the present invention, an apparatus is provided. The apparatus includes at least one processor and at least one memory containing computer program code. The processor and the memory are configured to use the processor to make the device at least perform recording and acquisition of scenarios when one or more items of the mobile device are used, and determine one or more according to the distribution of the scenarios. Multiple subcontext spaces. The processor and the memory are also configured to use the processor to make the device at least perform, for each sub-context space, form a corresponding preference mode, so that when it is detected that the mobile device is in a sub-context space , according to the preference mode corresponding to the one sub-scenario space, the corresponding item is displayed.

According to yet another exemplary embodiment of the present invention, an apparatus is provided. The apparatus includes at least one processor and at least one memory containing computer program code. The processor and the memory are configured to use the processor so that the device at least performs detection of one or more items being used in the mobile device and a corresponding context, and determining that the context is within a predetermined sub-level. in situational space. The processor and the memory are further configured to use the processor to enable the device to at least display corresponding items according to a preference mode corresponding to the predetermined sub-context space.

According to yet another exemplary embodiment of the present invention, an apparatus is provided. The device comprises recording means for recording scenarios in which one or more items of the mobile device are used, and first determining means for determining one or more sub-context spaces according to the distribution of the scenarios. The device also includes forming means for forming a corresponding preference mode for each sub-context space, so that when it is detected that the mobile device is in a sub-context space, according to the preference mode corresponding to the one sub-context space , to display the corresponding item.

According to yet another exemplary embodiment of the present invention, an apparatus is provided. The device includes detecting means for detecting one or more items being used in the mobile device and the corresponding context, and second determining means for determining that the context is in a predetermined sub-context space. The device further includes display means for displaying corresponding items according to a preference mode corresponding to the predetermined sub-context space.

According to yet another exemplary embodiment of the present invention there is provided a computer program product comprising at least one computer readable storage medium having stored therein computer readable program code portions for A method for determining context-related user preferences according to an embodiment of the present invention is performed.

According to yet another exemplary embodiment of the present invention there is provided a computer program product comprising at least one computer readable storage medium having stored therein computer readable program code portions for A method for utilizing context-dependent user preferences according to another embodiment of the present invention is performed.

According to some embodiments of the present invention, a context tree is constructed by detecting context-related preference patterns, and user preferences relevant to a given context are determined from the context tree. In the context-related user preferences, the items frequently used by the user in the context are sorted, so that the user can obtain frequently used items conveniently and quickly.

Description of drawings

Other characteristics, objects and advantages of various embodiments of the present invention will become more apparent through the detailed description of non-limiting embodiments made with reference to the following drawings:

Fig. 1 schematically shows a flowchart of a method 100 for determining context-related user preferences according to an embodiment of the present invention.

Fig. 2 schematically shows an example of context distribution for a contact in a two-dimensional context space according to an embodiment of the present invention.

Fig. 3 schematically shows a flowchart of a method 300 for determining context-related user preferences according to another embodiment of the present invention.

FIG. 4 schematically shows a flowchart of a method 400 for utilizing context-related user preferences according to an embodiment of the present invention.

Fig. 5 schematically shows an example of preference patterns of different items with similar context distributions according to an embodiment of the present invention.

Fig. 6 schematically shows an example of a scenario tree according to an embodiment of the present invention.

Fig. 7 schematically shows a block diagram of an apparatus 700 for determining context-related user preferences according to an embodiment of the present invention.

Fig. 8 schematically shows a block diagram of an apparatus 800 for utilizing context-related user preferences according to an embodiment of the present invention.

Fig. 9 schematically shows a block diagram of an apparatus 900 for determining context-related user preferences according to another embodiment of the present invention.

Fig. 10 schematically shows a block diagram of an apparatus 1000 for utilizing context-related user preferences according to another embodiment of the present invention.

Detailed ways

Embodiments of the present invention will be explained and described in more detail below in conjunction with the accompanying drawings. It should be understood that the drawings and embodiments of the present invention are for exemplary purposes only, and are not intended to limit the protection scope of the present invention.

In the method, device, and computer program product for determining context-related user preferences according to the embodiments of the present invention described below, user preferences are determined by modeling context-related user preferences, thereby displaying the Download frequently used items.

In an embodiment of the present invention, the mobile device may include various types of mobile terminals, such as mobile phones, personal digital assistants (PDAs), tablet computers, and portable computers.

In another embodiment of the present invention, the item may be content displayed or recommended to the user through the mobile device. For example, the item may be contacts in a phone book of the mobile device or various specific applications used by the user of the mobile device. These applications include, for example, telephony, Short Message Service (SMS), Multimedia Message Service (MMS) or browser applications (eg IE). In addition, the item may also include a corresponding link in the favorites of the browser.

In yet another embodiment of the present invention, in different scenarios, the user can search for various items of interest through the mobile device. Scenarios can be composed of several factors. In one example, the scenario includes the activities of the user of the mobile device at different times and locations, for example, in this scenario, the user may need to look up related contacts (ie, items) in the phonebook. In another example, the scenario includes the time, place, vehicle or specific working status of the user's location. In yet another example, the scenario includes the duration of each call of the user. In yet another example, the scenario includes the user's social activities, such as attending various meetings. In addition, the scenario may also include the current geographical location of the mobile device (for example, obtained through Beidou satellite navigation, Galileo navigation or GPS measurement) or historical state information about the mobile device's networking and record information of access history.

It should be pointed out that the items and scenarios in the embodiments of the present invention are not limited to the above-mentioned content, in which the user may use the mobile device to inquire or search for the application of interest or can be collected to recommend items to the user. Both type data can be considered contexts of embodiments of the present invention.

According to an embodiment of the present invention, the above scenarios constitute a scenario space, and the scenario space may include one or more sub-scenario spaces. The sub-scenario space may be two-dimensional or multi-dimensional. In the sub-context space, the user may perform multiple operations on the item. For example, in a two-dimensional situational space composed of time and geographical regions, when users contact relevant contacts in a specific time period and corresponding geographical regions relatively intensively, the time period and corresponding geographical regions The formed two-dimensional space constitutes a sub-scenario space.

It should be explained that, in the embodiment of the present invention, when modeling user preferences, it is extremely challenging to determine the context granularity for modeling context-related preferences. Specifically, if the granularity is too large, then the model cannot accurately capture and fully utilize situational information. If the scenario model is too complex, it is not easy to implement in mobile devices.

For example, in the case of considering only two types of context information, ie, time and location, then one way of setting context granularity may be <time of day, zone>. In this case, if the user stays in "Queens" (ie "district") for the entire morning (ie "time of day"), then the contextual phonebook will only be able to give the same A hierarchical list of contacts. Clearly, the context granularity of this context model is too large, because the contacts the user frequents between 9:00 am and 10:00 am may be different from the contacts the user frequents between 10:30 am and 12:00 am.

However, choosing a small scene granularity may not necessarily lead to better accuracy. For example, for the above example, if the time granularity is set to minutes, and the location granularity is set to location, then the scenario model will be very complex, because it will contain 3600*N pending scenarios, where N indicates that the user has The number of frequently visited places, and this number is usually greater than thousands.

If the above model takes into account more contextual information, such as battery level, activated mode (general, silent, pager, etc.), inactive time, weather, user behavior recognized by 3D accelerometer, then the situation to be handled will become It is more difficult and complex, because a mobile device with limited storage capacity and computing power will have difficulty storing millions of context-related preferences.

On the other hand, too small scenario granularity may also cause the problem of data sparseness. For example, if <minute, location> is set to the scenario granularity, then there may be too little data for each scenario, so it will not be possible to establish a preference pattern in each scenario, because too little data is not useful for statistical modeling. practical significance. Assuming that the given scenario is <PM12:05-12:06, (latitude=115.2347, longitude=38.4517)>, because the time interval is too short, it is very likely to find that in the past month, the user only made two calls in in this scenario. Obviously, such a scenario does not provide enough sample data to build a useful contact list based on such a scenario.

Therefore, it is necessary to choose an appropriate context granularity to model user preferences in order to accurately reflect user preferences in specific contexts.

Fig. 1 schematically shows a flowchart of a method 100 for determining context-related user preferences according to an embodiment of the present invention. It should be understood that the steps of method 100 shown in FIG. 1 are for illustration purposes only and that additional and/or alternative steps may be included.

The method 100 starts at step S101, and then proceeds to step S102. In step S102, the scene when one or more items of the mobile device are used is recorded.

Although not specifically shown in step S102, in one embodiment of the present invention, the method 100 may record items frequently used by the user and corresponding scene distributions according to historical device logs of the mobile device. In another embodiment of the present invention, the method 100 may record the frequently contacted contacts of the user and the corresponding context distribution according to the contact groups of the phonebook. In yet another embodiment of the present invention, the method 100 may record the applications frequently used by the user and the corresponding scene distribution according to the popularity of the applications, for example, the number of webpages searched by a search engine.

Next, in step S103, one or more sub-scenario spaces are determined according to the distribution of the scenarios.

Table 1 schematically shows the context information of the device log:

Table 1

time Place action Friday 6:10pm (115.2347, 38.4517) SMS Jimmy Friday 7:00pm (115.2347, 38.5067) Call Rebecca ... ... ... Saturday 11:05am (115.4590, 38.3422) SMS Lily

According to the context information of the device log shown in Table 1, context distribution for contacts can be obtained. In one example, record the call records of the user at different times and different places with the contact person, obtain the distribution of the user's call in the two-dimensional space composed of time and place, and obtain the call history of the user and the contact person. Scenario distribution. Furthermore, one or more sub-context spaces may be determined from the context distribution.

It should be noted that only the items frequently used by users are statistically significant for identifying context-related preference patterns. Items that are used infrequently may not be considered when determining the preferred mode. For example, in some embodiments of the present invention, only items that are used or accessed more than a predetermined number of times within a certain period of time, such as used or accessed more than 4 times in a month, are considered. For these frequently used items, one or more sub-scenario spaces may be determined according to the distribution of the scenarios in which these items are used.

Returning to FIG. 1, in step S104, for each sub-context space, a corresponding preference mode is formed, so that when it is detected that the mobile device is in a sub-context space, according to the preference mode corresponding to the one sub-context space, The corresponding item is displayed.

Finally, the method 100 ends in step S105.

According to some embodiments of the present invention, in the context-related user preferences, items frequently used by the user in the context are sorted, so that the user can obtain these frequently used items conveniently and quickly. For example, use the preference mode related to the situation to sort the contacts or applications in the phone book frequently used by the user of the mobile device, and display the most likely contacts or the most likely N applications in the prominent position of the mobile device In this way, retrieval efficiency for preferred contacts or applications can be improved.

Fig. 2 schematically shows an example of context distribution for a contact in a two-dimensional context space according to an embodiment of the present invention. In the example shown in Figure 2, the scene is two-dimensional, that is, time (vertical) and location (horizontal) are the dimensions, and the black dots in it represent a time point indicated by a certain vertical time and a horizontal location. At a certain location indicated, the user has a call record with a contact, the distribution of these black dots reflects the context distribution for the contact, and the context distribution constitutes two context clusters.

In such an example, on the location dimension, different locations may be mapped to integer IDs (eg, location 1 or location 2, as shown in FIG. 6 ) in order to simplify the example display.

It should be noted that, in the context-related preference pattern according to an embodiment of the present invention, the context cluster indicates a group of contexts that the user has obvious preference, which should be considered when determining the context-related preference pattern of the user.

In one embodiment of the present invention, the corresponding sub-scenario space is determined through the frequently used call records and the corresponding scene distribution, so as to form a preference pattern related to the scene. For example, in the example shown in FIG. 2 , the scenario distribution shown has two clusters of scenarios A and B, which respectively show that calls with the contact are generally concentrated at A and B for a specific period of time and a specific geographic location indicated area. That is to say, two sub-scenario spaces can be determined according to the scenario clusters A and B, and these two sub-scenario spaces reflect the user's preferred mode of talking with the contact.

However, if the call records with the contact are evenly distributed in the two-dimensional space, it means that the call with the contact is anytime and anywhere, rather than at a specific time and a specific place, so that a sub-scenario space cannot be formed. This situation can be ignored when modeling the scenario distribution.

Fig. 3 schematically shows a flowchart of a method 300 for determining context-related user preferences according to another embodiment of the present invention. It should be understood that the steps of method 300 shown in FIG. 3 are for illustration purposes only. Method 300 may include additional and/or alternative steps.

The method 300 starts at step S301, and then proceeds to step S302. In step S302, the scene when one or more items of the mobile device are used is recorded. Here, the execution of step S302 is the same as step S102 of the method 100 described above in conjunction with FIG. 1 , so the detailed description about step S102 is also applicable to step S302.

Subsequently, in step S303, one or more sub-scenario spaces are determined according to the distribution of the scenarios.

In one embodiment of the present invention, by identifying one or more scenario clusters in the scenario distribution when a certain item is used, and dividing at least one of the scenario clusters into a sub-scenario space, it is determined that the The sub-context space corresponding to the item.

Further, in another embodiment of the present invention, the specific implementation manner of determining whether the scenario distribution of a certain item forms some scenario clusters is to perform a density-based clustering algorithm (for example, DBSCAN) on it. DBSCAN is a typical density-based clustering algorithm. It defines clusters as the largest collection of density-connected points, can divide areas with sufficiently high density into clusters, and can find clusters of arbitrary shapes in spatial databases. The clusters generated according to the clustering algorithm can meet certain density requirements.

Among the clustering results generated by the density-based clustering algorithm, only scenario clusters containing more than β different scenarios than a predetermined second threshold are considered meaningful and will be used as scenario-related preferences model.

Subsequently, the method 300 proceeds to step S304. In step S304, the method 300 merges sub-context spaces with similar context distributions for different items.

In one embodiment of the present invention, sub-context spaces with similar situation distributions for different items are merged to make the situation space more compact, thereby reducing the complexity of the preference model. After merging, each context-related preference pattern will correspond to a sub-situation space.

Further, in this embodiment, in order to combine the preference patterns, some similarity measurement criteria may be defined first, and then the situational distributions for the two items are compared to obtain the similarity measurement between the situational distributions. When the similarity measure is greater than a predetermined first threshold, the sub-context spaces for the two items are merged into one sub-context space.

Subsequently, in step S305, the method 300 forms a corresponding preference mode for each sub-context space, so that when it is detected that the mobile device is in a sub-context space, according to the preference mode corresponding to the one sub-context space, display corresponding item.

In one embodiment of the present invention, for each sub-scenario space, according to at least one property of the respective historical usage of at least a part of the one or more items, the at least a part of the items are sorted to form a corresponding preferred mode.

Further, in this embodiment, the at least one property includes at least one of historical usage times, historical usage frequency, historical usage location, historical usage time, and historical usage duration.

Subsequently, in step S306, the method 300 divides the overlapping scenarios in multiple preferred modes into one of the preferred modes.

In one embodiment of the invention, scenarios that occur in more than one sub-context space such that these scenarios belong to multiple preference patterns are considered overlapping scenarios. For example, in the two-dimensional space composed of time and place, in the sub-scenario space 1, its time period is 5:00pm-7:00pm, and the geographical area is the "unit". In sub-context space 2, its time period is 7:00pm-9:00pm, and the geographical area is "home". When the user discusses a certain work with a colleague at home at 7:01pm via a mobile device, the call will be divided into the sub-context space 2 . In fact, according to the content of the call and the contacts, the call is divided into the sub-context space 1 to reflect the user's preference more accurately. In this case, a Greedy algorithm can be used to divide the overlapping scenarios into appropriate preference patterns.

Specifically, for each overlapping scenario, it is checked which scenario cluster's preference pattern is least affected when that scenario is absorbed, and the scenario is assigned to that scenario cluster. The greedy algorithm is used repeatedly until all overlapping scenarios are assigned to corresponding scenario clusters.

For example, when a certain situation belongs to two sub-scenario spaces at the same time, it is firstly removed from the two sub-scenario spaces, and the two sub-scenario spaces after removing the situation constitute two different preference modes C and D respectively. Then, the scenario is added to the two sub-scenario spaces respectively, and the two sub-scenario spaces containing the scenario constitute two different preference modes C' and D' respectively. Finally, compare the change in ordering between items in subcontext spaces C and C', and D and D'. This addition is considered to have a small effect on the preference pattern C if the change in the ordering of items between subcontext space C and subcontext space C' is smaller than the change in ordering of items between subcontext space D and subcontext space D', The scenario can be divided into preference mode C which has less influence.

Alternatively or alternatively, an average of the change in position of each item in subcontext spaces C and C' may be calculated, and an average of change in position of each item in subcontext spaces D and D' may be calculated. This addition can be considered to have a small effect on the preference pattern C if the mean value of the change in position in the subcontext space C' is smaller than the mean value of the change in position in the subcontext space D'.

Finally, the method 300 ends in step S307.

In one embodiment of the present invention, the sub-scenario space and the corresponding preference mode are stored in the mobile device or the remote server in the form of a scenario tree.

In another embodiment of the present invention, the scenario tree is updated dynamically or periodically.

In yet another embodiment of the present invention, the modeling process of the context-dependent preference model is performed periodically so as to realize incremental training of the context distribution to update the context-dependent preference pattern.

FIG. 4 schematically shows a flowchart of a method 400 for utilizing context-related user preferences according to an embodiment of the present invention. It should be understood that the steps of method 400 shown in FIG. 4 are for illustration purposes only. Method 400 may include additional and/or alternative steps.

The method 400 starts in step S401, and then proceeds to step S402. In step S402, items being used in the mobile device and corresponding scenarios are detected. As described above, one or more sub-scenario spaces may be determined according to the distribution of scenarios, such that each scenario is associated with one or more sub-scenario spaces.

Subsequently, in step S403, it is determined that the scene is in a predetermined sub-scenario space. Specifically, since each scenario is associated with one or more sub-scenario spaces, it can be determined whether the scenario is in the in the predetermined sub-scenario space.

When the scenario is in the predetermined sub-scenario space, the method 400 proceeds to step S404.

In step S404, according to the preference mode corresponding to the predetermined sub-scenario space, corresponding items are displayed. As mentioned above, for each sub-context space, there is a corresponding one or more preference patterns. Among these preference patterns are included items that correspond to a given context, such as contacts to talk to at a particular place at a particular time.

In one embodiment of the invention, the method 400 maps a given context to a subcontext space in the context tree, and utilizes the preference patterns (e.g., contact preferences, application usage, etc.) corresponding to the subcontext spaces. preference) to determine a preference mode related to the scenario to display the corresponding item.

In another embodiment of the present invention, the predetermined sub-scenario space and the corresponding preference mode are stored in the mobile device or a remote server in the form of a scenario tree.

In yet another embodiment of the present invention, the scenario tree is dynamically or periodically updated according to the usage of the one or more items.

Finally, the method 400 ends in step S405.

In some embodiments of the present invention, the method 400 indexes the sub-scenario space through the scenario tree, so that the user can quickly find the sub-scenario space that matches a given specific scenario, and display corresponding items.

Fig. 5 schematically shows an example of preference patterns of different items with similar context distributions according to an embodiment of the present invention. A sub-context space for one contact is shown at the top 5A of FIG. 5 and a sub-context space for another contact is shown at the bottom 5B. As shown in FIG. 5 , since these two contacts have similar attributes for the user (for example, relatives, friends or colleagues who belong to the user), they have similar sub-context spaces, and can be identified according to the method 300. Step S304 is performed to merge the two sub-scenario spaces.

Fig. 6 schematically shows an example of a scenario tree according to an embodiment of the present invention. As shown in Figure 6, Scenario 1 {(Week 1) 6:00am-6:01am), (Position 1)}, Scenario 2 {(Tuesday), (6:00am-6:01am), (Position 2)} And scenario 3 {(Tuesday), (6:02am-6:03am), (Location 1)} can be mapped to the same sub-scenario space associated with a preference pattern, as shown in the lower part of Figure 6 Each element in the table of , which indicates a preference mode for a subcontext space.

In the example shown in FIG. 6, the scenario tree is a scenario space with a three-dimensional structure, and the three latitudes include week, time and location. In another example of the present invention, the scenario tree may also include more dimensions, such as vehicle, call duration, working status or social activity dimensions.

It needs to be explained that when a certain scenario cannot be found in the scenario tree, it means that the scenario does not belong to any sub-scenario space and may not have a significant impact on the user's preference. In this case, for this context, a context-independent preference pattern may be used, eg purely based on frequency of use or a traditional alphabetical pattern.

Fig. 7 shows a block diagram schematically illustrating an apparatus 700 for determining context-related user preferences according to an embodiment of the present invention. As shown in FIG. 7 , the device 700 includes a recording device 701 , a first determining device 702 and a forming device 703 . The recording means 701 is used for recording the scene when one or more items of the mobile device are used. The first determining means 702 is configured to determine one or more sub-scenario spaces according to the distribution of the scenarios. The forming unit 703 is used for forming a corresponding preference mode for each sub-scenario space, so that when it is detected that the mobile device is in a sub-scenario space, corresponding items are displayed according to the preference mode corresponding to the one sub-scenario space .

In an embodiment of the present invention, the first determining means 702 is further configured to identify one or more scenario clusters in the scenario distribution, and divide at least one scenario cluster into a sub-scenario space.

In another embodiment of the present invention, the first determining means 702 is further configured to merge sub-context spaces with similar situation distributions for different items.

Further, in this embodiment, the first determining means 702 is also used to compare the situational distributions of the two items to determine a similarity measure between the situational distributions; and in the similarity measure When greater than the first threshold, merge the sub-scenario spaces for the two items.

In yet another embodiment of the present invention, the forming means 703 is further configured to divide overlapping scenarios in multiple preference modes into one of the preference modes.

Further, in this embodiment, a greedy algorithm is used to divide the overlapping scenarios into one of the preference modes.

Furthermore, in this embodiment, the forming means 703 is also used to check the order changes among items in multiple preference modes when the overlapping scenarios are absorbed, and divide the overlapping scenarios into A preference pattern with small ordering variations between items.

In yet another embodiment of the present invention, the sub-context space and the corresponding preference patterns are stored in the mobile device or a remote server in the form of a situation tree.

In yet another embodiment of the present invention, the scenario tree is updated dynamically or periodically.

In yet another embodiment of the present invention, the forming means 703 is configured to, for each sub-scenario space, according to at least one property of the respective historical usage conditions of at least a part of the one or more items, to the at least A subset of items is ranked to form a corresponding preference pattern.

Further, in this embodiment, the at least one property includes at least one of historical usage times, historical usage frequency, historical usage location, historical usage time, and historical usage duration.

Fig. 8 shows a block diagram schematically illustrating an apparatus 800 for utilizing context-related user preferences according to an embodiment of the present invention. As shown in FIG. 8 , the device 800 includes a detection device 801 , a second determination device 802 and a display device 803 . The detecting means 801 is used for detecting one or more items being used in the mobile device and corresponding scenarios. The second determining means 802 is used for determining that the scene is in a predetermined sub-scenario space. The display device 803 is configured to display corresponding items according to the preference mode corresponding to the predetermined sub-scenario space.

In an embodiment of the present invention, the predetermined sub-scenario space and the corresponding preference mode are stored in the mobile device or a remote server in the form of a scenario tree.

Further, in this embodiment, the display device 803 is configured to map the scenario to a sub-scenario space in the scenario tree, and use the preference mode corresponding to the sub-scenario space to determine the Context-sensitive preference modes to display corresponding items.

In another embodiment of the present invention, the scenario tree is dynamically or periodically updated according to the usage of the one or more items.

Fig. 9 schematically shows a block diagram of an apparatus for determining context-related user preferences according to another embodiment of the present invention. As shown in FIG. 9 , the device 900 includes a data processor (DP) 901 and a memory (MEM) 903 coupled with the data processor 901 . The memory 903 stores a program (PROG) 902 .

The embodiments of the present invention may be implemented by software executed by the data processor 901, or by hardware, or by a combination of software and hardware.

Memory 903 may be of any suitable type suitable for the local technical environment and may be implemented using any suitable data storage technology, including but not limited to semiconductor-based storage devices, magnetic storage devices and systems, optical storage devices and systems. Although only one memory unit is shown in FIG. 9 , there may be multiple physically distinct memory units in device 900 . DP 901 may be of any suitable type suitable for the local technical environment, and may include, but is not limited to, one of a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), and a processor-based multi-core processor architecture or multiple multiples. Device 900 may include multiple processors.

As shown in FIG. 9 , the data processor 901 and the memory 903 are configured to use the data processor 901 so that the device 900 at least executes recording the scenario when one or more items of the mobile device are used; according to the distribution of the scenario , determine one or more sub-context spaces; and for each sub-context space, form a corresponding preference pattern, so that when it is detected that the mobile device is in a sub-context space, according to the preference pattern corresponding to the one sub-context space , to display the corresponding item.

In one embodiment of the present invention, the data processor 901 and the memory 903 are configured to utilize the data processor 901, so that the device 900 at least performs identifying one or more scenario clusters in the distribution of scenarios, and at least One of the scenario clusters is divided into a sub-scenario space.

In another embodiment of the present invention, the data processor 901 and the memory 903 are configured to utilize the data processor 901 so that the device 900 at least performs merging of sub-context spaces with similar context distributions for different items.

Further, in this embodiment, the data processor 901 and the memory 903 are configured to use the data processor 901 so that the device 900 at least performs a comparison of the situational distributions of two items to determine the difference between the situational distributions. , and when the similarity measure is greater than a first threshold, merging the sub-context spaces for the two items.

In yet another embodiment of the present invention, the data processor 901 and the memory 903 are configured to utilize the data processor 901, so that the device 900 at least executes dividing scenarios overlapping in multiple preference modes into one of the preference modes .

Further, in this embodiment, a greedy algorithm is used to divide the overlapping scenarios into one of the preference modes.

Furthermore, in this embodiment, the data processor 901 and the memory 903 are configured to utilize the data processor 901 so that the device 900 at least executes checking items in multiple preference modes when absorbing the overlapping scenarios The ranking variation among items, and the preference pattern for dividing the overlapping scenarios into items with little ranking variation between them.

In yet another embodiment of the present invention, the sub-context space and the corresponding preference patterns are stored in the mobile device or a remote server in the form of a situation tree.

In one embodiment of the present invention, the scenario tree is updated dynamically or periodically.

In yet another embodiment of the present invention, the data processor 901 and the memory 903 are configured to use the data processor 901 so that the device 900 at least executes, for each sub-scenario space, according to at least one of the one or more items According to at least one property of the respective historical usage conditions of a part of items, the at least a part of items are sorted to form a corresponding preference pattern.

Further, in this embodiment, the at least one property includes at least one of historical usage times, historical usage frequency, historical usage location, historical usage time, and historical usage duration.

Fig. 10 schematically shows a block diagram of an apparatus 1000 for utilizing context-related user preferences according to another embodiment of the present invention. As shown in FIG. 10 , the device 1000 includes a data processor (DP) 1001 and a memory (MEM) 1003 coupled with the data processor 1001 . The memory 1003 stores a program (PROG) 1002 .

As shown in FIG. 10, the data processor 1001 and the memory 1003 are configured to use the data processor 1001, so that the device 1000 at least performs detection of one or more items being used in the mobile device and the corresponding context; determining the context in a predetermined subcontext space. Moreover, the data processor 1001 and the memory 1003 are configured to use the data processor 1001 to enable the device 1000 to at least display corresponding items according to a preference mode corresponding to the predetermined sub-scenario space.

In an embodiment of the present invention, the predetermined sub-scenario space and the corresponding preference mode are stored in the mobile device or a remote server in the form of a scenario tree.

Further, in this embodiment, the data processor 1001 and the memory 1003 are configured to use the data processor 1001, so that the device 1000 at least performs mapping the scenario to the sub-scenario space in the scenario tree, and using A preference mode corresponding to the sub-scenario space, determining a preference mode related to the scenario to display corresponding items.

In another embodiment of the present invention, the scenario tree is dynamically or periodically updated according to the usage of the one or more items.

Exemplary embodiments of the present invention are described above with reference to flowcharts and block diagrams shown in the accompanying drawings. It should be noted that embodiments of the invention may also take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system. For purposes of description, a computer-usable or computer-readable mechanism may be any tangible means that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

It should be noted that in order to make the embodiments of the present invention easier to understand, the above description omits some more specific technical details that are known to those skilled in the art and may be necessary for the implementation of the embodiments of the present invention. . The description of the present invention has been presented for purposes of illustration and description, not exhaustive or limited to the invention in the form disclosed. Many modifications and changes are possible to those of ordinary skill in the art.

Therefore, the embodiment is selected and described in order to better explain the principle of the present invention and its practical application, and to make those of ordinary skill in the art understand that all modifications and variations fall within the scope of the patent rights without departing from the essence of the present invention. within the scope of protection of the present invention as defined by the requirements.

Claims (42)

1. A method comprising: record the circumstances in which one or more items of the mobile device are used; Determining one or more sub-scenario spaces based on the distribution of the scenarios; and For each sub-context space, a corresponding preference mode is formed, so that when it is detected that the mobile device is in a sub-context space, corresponding items are displayed according to the preference mode corresponding to the one sub-context space. 2. The method of claim 1, wherein based on the distribution of scenarios, determining one or more sub-scenario spaces comprises: identifying one or more clusters of scenarios in the distribution of scenarios; and Dividing at least one scenario cluster into a sub-scenario space. 3. The method of claim 1, wherein determining one or more sub-scenario spaces based on the distribution of the scenarios further comprises: Merge sub-context spaces with similar situation distributions for different projects. 4. The method of claim 3, wherein merging sub-context spaces with similar context distributions for different projects further comprises: comparing the scenario distributions for the two projects to determine a measure of similarity between the scenario distributions; and When the similarity measure is greater than a first threshold, the subcontext spaces for the two items are merged. 5. The method according to claim 1, wherein for each sub-scenario space, forming a corresponding preference pattern further comprises: Partition scenarios that overlap in multiple preference patterns into one of the preference patterns. 6. The method of claim 5, wherein the overlapping scenarios are divided into one of the preference patterns using a greedy algorithm. 7. The method of claim 6, further comprising: checking for ranking changes between items in a plurality of preference patterns when said overlapping context is absorbed; and The overlapping scenarios are grouped into preference patterns where the ranking variation between items is small. 8. The method according to claim 1, wherein the sub-context space and the corresponding preference mode are stored in the mobile device or the remote server in the form of a situation tree. 9. The method of claim 8, further comprising: The scenario tree is updated dynamically or periodically. 10. The method of claim 1, wherein for each sub-context space, forming a corresponding preference pattern comprises: For each sub-context space, according to at least one property of the respective historical usage of at least a part of the one or more items, the at least a part of the items are sorted to form a corresponding preference pattern. 11. The method according to claim 10, wherein the at least one property includes at least one of historical usage times, historical usage frequency, historical usage location, historical usage time, and historical usage duration. 12. The method of any one of claims 1-11, wherein the items include contacts of a phonebook of the mobile device or applications used. 13. The method according to any one of claims 1-11, wherein recording the context in which one or more items of the mobile device are used comprises: Record the activities of users of mobile devices at different times and locations. 14. A method comprising: Detect one or more items being used in the mobile device and the corresponding context; determining that the context is within a predetermined subcontext space; and According to the preference mode corresponding to the predetermined sub-context space, corresponding items are displayed. 15. The method according to claim 14, wherein said predetermined sub-context space and corresponding preference patterns are stored in said mobile device or a remote server in the form of a situation tree. 16. The method according to claim 15, wherein according to a preference mode corresponding to the predetermined sub-context space, displaying corresponding items comprises: mapping the scenarios to sub-scenario spaces in the scenario tree; and Using the preference mode corresponding to the sub-scenario space, a preference mode related to the context is determined to display corresponding items. 17. The method of claim 15, further comprising: The context tree is dynamically or periodically updated based on usage of the one or more items. 18. A method according to any of claims 14-17, wherein said items include contacts of a phonebook of a mobile device or applications used. 19. The method according to any one of claims 14-17, wherein detecting one or more items and corresponding contexts being used in the mobile device comprises: One or more items and corresponding times and locations being used by a user of the mobile device are detected. 20. An apparatus comprising: at least one processor and at least one memory containing computer program code; The processor and the memory are configured to, with the processor, cause the device to at least perform: recording and obtaining a context in which one or more items of the mobile device are used; Determining one or more sub-scenario spaces based on the distribution of the scenarios; and For each sub-context space, a corresponding preference mode is formed, so that when it is detected that the mobile device is in a sub-context space, corresponding items are displayed according to the preference mode corresponding to the one sub-context space. 21. The device of claim 20, wherein the processor and the memory are configured to utilize the processor such that the device at least performs: identifying one or more clusters of scenarios in the distribution of scenarios , and dividing at least one scenario cluster into a sub-scenario space. 22. The device of claim 20, wherein the processor and the memory are configured to, with the processor, cause the device to at least perform: merging sub-context spaces with similar distribution of situations for different projects. 23. The device of claim 22 , wherein the processor and the memory are configured to utilize the processor such that the device at least performs: comparing scenario distributions for two items to determine the A similarity measure between the context distributions, and when the similarity measure is greater than a first threshold, merge the sub-context spaces for the two items. 24. The device of claim 20 , wherein the processor and the memory are configured to utilize the processor such that the device at least performs: partitioning scenarios that overlap in a plurality of preference modes into one of them in preference mode. 25. The apparatus of claim 24, wherein the overlapping scenarios are partitioned into one of the preference patterns using a greedy algorithm. 26. The device of claim 25 , wherein the processor and the memory are configured to utilize the processor such that the device at least performs: checking for a plurality of preference modes when absorbing the overlapping scenarios The ranking variation among items in , and the preference pattern for partitioning the overlapping scenarios into small ranking variation among items. 27. The device of claim 20, wherein sub-context spaces and corresponding preference patterns are stored in the mobile device or a remote server in the form of a context tree. 28. The apparatus of claim 27, wherein the context tree is updated dynamically or periodically. 29. The device according to claim 20, wherein the processor and the memory are configured to utilize the processor such that the device at least performs: for each subcontext space, according to the one or more items At least one property of the respective historical usage conditions of at least a part of the items, sorting the at least a part of the items to form a corresponding preference pattern. 30. The device according to claim 29, wherein the at least one property includes at least one of historical usage times, historical usage frequency, historical usage location, historical usage time, and historical usage duration. 31. A device according to any one of claims 20-29, wherein said items include contacts of a phonebook of a mobile device or applications used. 32. The device according to any one of claims 20-29, wherein the context comprises activities of a user of the mobile device at different times and places. 33. A device comprising: at least one processor and at least one memory containing computer program code; The processor and the memory are configured to, with the processor, cause the device to at least perform: detecting one or more items being used in the mobile device and a corresponding context; determining that the context is within a predetermined subcontext space; and According to the preference mode corresponding to the predetermined sub-context space, corresponding items are displayed. 34. The device according to claim 33, wherein said predetermined subcontext space and corresponding preference patterns are stored in said mobile device or a remote server in the form of a situation tree. 35. The device of claim 34, wherein the processor and the memory are configured to utilize the processor such that the device at least performs: Mapping the context to a sub-context space in the context tree, and using the preference mode corresponding to the sub-context space, determining a preference mode related to the context to display corresponding items. 36. The apparatus of claim 34, wherein the context tree is updated dynamically or periodically based on usage of the one or more items. 37. A device according to any of claims 33-36, wherein the items include contacts of a phonebook of the mobile device or applications used. 38. The device according to any one of claims 33-36, wherein the context comprises activities of a user of the mobile device at different times and places. 39. A device comprising: recording means for recording the circumstances in which one or more items of mobile equipment are used; The first determining means is used to determine one or more sub-scenario spaces according to the distribution of the scenarios; and forming means for forming a corresponding preference mode for each sub-scenario space, so that when it is detected that the mobile device is in a sub-scenario space, corresponding items are displayed according to the preference mode corresponding to the one sub-scenario space . 40. A device comprising: A detecting device, configured to detect one or more items being used in the mobile device and corresponding scenarios; The second determining means is used to determine that the scenario is in a predetermined sub-scenario space; and The display device is configured to display corresponding items according to the preference mode corresponding to the predetermined sub-scenario space. 41. A computer program product comprising at least one computer-readable storage medium having computer-readable program code portions stored therein for performing any one of claims 1-13 the method described. 42. A computer program product comprising at least one computer-readable storage medium having computer-readable program code portions stored therein for performing any one of claims 14-19 the method described.

Images