User preference content recommendation method, control system, television, medium and product

Abstract

The invention relates to the technical field of televisions, in particular to a user preference content recommendation method, a control system, a television, a medium and a product. The user preference content recommendation method comprises the following steps: detecting state data when a user watches a program; wherein the state data comprises external data and / or physical sign data, the external data comprises facial expression, body form and respiratory rate, and the physical sign data comprises blood pressure, pulse and heart rate; judging whether the program watched by the user is favorite content of the user or not according to the state data; and when the program is the favorite content of the user, recommending the content matched with the favorite content to the user. According to the method and the device, whether the program is the favorite program of the user is judged according to the state data when the user watches the program, and subjective random content selection of the user is replaced by an objective body reaction data (namely, state data) identification result, so that the really favorite content is recommended to the user; and therefore, the problem of poor user experience caused by subjective selection uncertainty can be avoided.

Description

Technical Field

[0001] This application relates to the field of television, and in particular to a method, control system, television, medium, and product for recommending user-preferred content. Background Technology

[0002] Currently, content recommendation functions generally rely on the analysis and identification of users' past browsing content. Taking Google Ads recommendations and video recommendations on short video platforms such as Douyin, Kuaishou, and Bilibili as examples, the implementation process is usually as follows: software crawls the content that users browse, builds a database, uses algorithms to analyze the content features, and pushes relevant content based on the algorithm's identification results when users use the platform again.

[0003] Existing recommendation algorithms have certain limitations, heavily relying on users' subjective browsing choices and exhibiting significant uncertainty. When users encounter new content, they may need to spend considerable time viewing, understanding, and judging whether it matches their preferences. During this process, the algorithm captures the browsed content and assumes it's liked by the user, subsequently making recommendations. However, if the user determines that the new content is not of interest, it means the algorithm has made an incorrect judgment, and subsequent recommendations will only provoke user resentment. Summary of the Invention

[0004] Based on this, this application provides a method, control system, television, medium, and product for recommending user-preferred content, solving the problem of poor user experience caused by relying on users' subjective browsing content to recommend preferred content in the prior art.

[0005] On the one hand, this application provides a method for recommending user-preferred content, including:

[0006] The system detects user status data while watching a program; wherein the status data includes external data and / or vital sign data, the external data includes facial expression, body shape, and respiratory rate, and the vital sign data includes blood pressure, pulse, and heart rate.

[0007] Based on the status data, determine whether the program watched by the user is content that the user prefers;

[0008] When the program is content that the user prefers, content that matches the user's preferences will be recommended to the user.

[0009] Optionally, after determining whether the program watched by the user is content that the user prefers based on the status data, the method further includes:

[0010] Establish a database of the users and their preferred content;

[0011] The next time the user watches a program, content related to their preferences will be recommended to the user based on the database.

[0012] Optionally, the step of establishing a database of users and their preferred content includes:

[0013] Collect content and viewing status data for each user during each program viewing session;

[0014] The preferred content for each user is obtained based on the status data.

[0015] The preferences of different users are stored in different target databases that match the users.

[0016] Optionally, after obtaining the preferred content for each user based on the status data, the method further includes:

[0017] The preferred content obtained from the status data when the same user watches the program multiple times is stored in the same database to form the target database that matches the user.

[0018] Optionally, the step of establishing a database of users and their preferred content further includes:

[0019] Detecting the actual users in front of the TV screen;

[0020] Determine whether the actual user is a new user;

[0021] When the actual user is a new user, a new database matching that actual user is created;

[0022] When the actual user is not a new user, the pre-established target database that matches the actual user is invoked.

[0023] Optionally, when the actual user is a new user, the step of establishing a new database matching that actual user further includes:

[0024] Determine whether the actual user has entered the search page;

[0025] When the TV enters the search page, it recommends and plays programs based on the actual user's search.

[0026] Based on the status data of the actual user while watching the program, determine whether the program is content that the actual user likes;

[0027] When the program being played matches the actual user's preferred content, the program is stored in the new database that matches the actual user.

[0028] Optionally, after determining whether the actual user is a new user, the method further includes:

[0029] When the actual user is not a new user, determine whether the TV enters the search page;

[0030] When the TV enters the search page, it recommends preferred content based on the target database that matches the actual user;

[0031] When the TV is not accessing the search page, recommended content is made based on the type of program the user last viewed.

[0032] Optionally, after detecting the actual user in front of the TV screen when the TV is turned on, the process may also include:

[0033] Determine whether there are multiple actual users;

[0034] When there are multiple actual users, determine whether each actual user is a new user.

[0035] When all of the actual users are not new users, the target database matched for each actual user is invoked, and programs with similar preferences are retrieved from the multiple target databases for recommendation.

[0036] When some of the actual users are new users and some of the actual users are not new users, programs are recommended based on the content retrieved by the actual users and the preferences in the target database corresponding to the non-new users.

[0037] When all the actual users are new users, programs are recommended based on the content retrieved by the actual users and according to the built-in popularity ranking of the TV.

[0038] Optionally, the steps for detecting user status data include:

[0039] When the user is watching the program, the camera is activated, and the camera is used to detect the user's external data.

[0040] Optionally, the step of detecting user status data further includes:

[0041] When the user is watching the program, determine whether the user is connected to the television.

[0042] Once the user is connected to the television, the user's vital signs data are detected.

[0043] The user connects to the television by wearing a wristband or holding a remote control.

[0044] On the other hand, this application also provides a user preference content recommendation control system, including a memory, a processor, and a program for a user preference content recommendation method stored in the memory and executable on the processor. When the program for the user preference content recommendation method is executed by the processor, it implements the steps of the user preference content recommendation method described above.

[0045] On the other hand, this application also provides a television, including the above-mentioned user preference content recommendation control system, for controlling the television to display or play content recommended by the user preference content recommendation method.

[0046] On the other hand, this application also provides a computer-readable storage medium storing a program for a method of recommending user-preferred content, wherein when the program for recommending user-preferred content is executed by a processor, it implements the steps of the method for recommending user-preferred content described above.

[0047] On the other hand, this application also provides a computer program product, which includes a program for a method of recommending user-preferred content, wherein when the program for recommending user-preferred content is executed by a processor, it implements the steps of the user-preferred content recommendation method described above.

[0048] This application uses user status data while watching programs to determine whether a program is one that the user likes. This status data can include facial expressions, body shape, breathing rate, blood pressure, pulse, heart rate, etc. By using objective physical response data (i.e., status data) to identify results, the application replaces the user's subjective and random content selection, thereby recommending content that the user truly likes and avoiding the problem of poor user experience caused by the uncertainty of subjective selection. Attached Figure Description

[0049] Figure 1 This is an illustrative flowchart illustrating a method for recommending user-preferred content according to an embodiment of this application.

[0050] Figure 2 This is a schematic flowchart illustrating the steps for detecting user status data according to one embodiment of this application.

[0051] Figure 3 A schematic flowchart illustrating the steps for detecting user status data provided in another embodiment of this application.

[0052] Figure 4 A schematic flowchart illustrating a method for recommending user-preferred content as another embodiment of this application.

[0053] Figure 5This is an illustrative flowchart illustrating the steps of establishing a database of user and preferred content according to one embodiment of this application.

[0054] Figure 6 A schematic flowchart illustrating the steps of establishing a database of user and preference content, provided for another embodiment of this application.

[0055] Figure 7 This is an illustrative flowchart illustrating the steps of establishing a database of user and preferred content, provided as another embodiment of this application.

[0056] Figure 8 This is an illustrative flowchart illustrating the steps of establishing a database of user and preferred content when the actual user is a new user, as provided in one embodiment of this application.

[0057] Figure 9 This is an illustrative flowchart illustrating the steps of establishing a database of users and their preferred content, and recommending preferred content, as provided in another embodiment of this application.

[0058] Figure 10 This is an illustrative flowchart illustrating the steps of establishing a database of users and their preferred content, and recommending preferred content, as provided in another embodiment of this application. Detailed Implementation

[0059] To make the technical solution and beneficial effects of this application more apparent and understandable, a detailed description is provided below by listing specific embodiments. The accompanying drawings are not necessarily drawn to scale, and local features may be enlarged or reduced to more clearly show the details of the local features; unless otherwise defined, the technical and scientific terms used herein have the same meanings as those in the technical field to which this application pertains.

[0060] As a specific embodiment of this application, such as Figure 1 As shown, this embodiment provides a method for recommending user-preferred content, which may include:

[0061] Step S100: Detect the user's status data while watching the program; wherein, the status data includes external data and / or vital sign data, external data includes facial expression, body shape, and respiratory rate, and vital sign data includes blood pressure, pulse, and heart rate;

[0062] Step S200: Determine whether the program the user is watching is content the user prefers based on the status data; if yes, proceed to step S300; otherwise, end the process.

[0063] Step S300: Recommend content that matches the user's preferences to the user.

[0064] Specifically, in this embodiment, the system determines whether a program is one that the user likes by analyzing the user's state data while watching the program. This state data can include facial expressions, body shape, breathing rate, blood pressure, pulse, heart rate, and other data. The objective physical response data (i.e., state data) is used to identify the results instead of the user's subjective and random content selection, thereby recommending content that the user truly likes and avoiding the problem of poor user experience caused by the uncertainty of subjective selection.

[0065] Generally, when users watch content they like, their facial expressions unconsciously show smiles, excitement, etc. Their bodies, due to focused attention, may involuntarily lean forward, stiffen, and experience increased breathing rate, blood pressure, pulse, and heart rate. Different users exhibit different behaviors, but the presence of one or more of these symptoms can confirm a user's preference for the content. The more symptoms a user displays, the stronger their liking. Specifically, relevant algorithms can be pre-stored within the TV software. These algorithms can calculate whether content is a user's favorite and further determine the degree of liking.

[0066] As a specific embodiment of this application, such as Figure 2 As shown, step S100 of this embodiment, which involves detecting user status data, may include:

[0067] Step S110: When the user is watching a program, activate the camera;

[0068] Step S120: Use the camera to detect the user's external data.

[0069] Specifically, generally speaking, a camera can be installed on the TV or an external camera, and the camera's data is then transmitted to the TV. When the user watches a program, the camera activates, detects the user's external data, and transmits that data to the computing software.

[0070] As another specific embodiment of this application, such as Figure 3 As shown, step S100 of this embodiment, which involves detecting user status data, may further include:

[0071] Step S130: When the user is watching a program, determine whether the user is connected to the TV; if yes, proceed to step S140; otherwise, exit.

[0072] Step S140: Detect the user's vital signs data;

[0073] Users connect to the TV by wearing a wristband or holding a remote control.

[0074] Specifically, when a user is watching a TV program, if they wear a wristband or hold a remote control, they can connect to the TV, and the user's vital signs data can be detected.

[0075] In one embodiment, if the user is neither wearing a wristband nor holding a remote control, the system determines whether the program being watched is a favorite program solely by detecting external data received from the camera. In another embodiment, if the user is wearing a wristband or holding a remote control, the system can determine whether the program is a favorite program using either the user's biometric data alone, the user's external data received from the camera alone, or a combination of both.

[0076] As a specific embodiment of this application, such as Figure 4 As shown, in this embodiment, after step S200, which determines whether the program being watched by the user is content that the user prefers based on the status data, the following steps are also included:

[0077] Step S400: Establish a database of users and their preferred content;

[0078] Step S500: When the user watches the program again, recommend content related to the user's preferences based on the database.

[0079] Specifically, once the user's favorite content is obtained based on the status data, the user and the favorite content are stored to form a database. In this way, when the user watches a program again (after restarting the device or searching for the program again), recommendations can be made to the user based on the content of the database, thereby improving the user experience.

[0080] As a specific example, such as Figure 5 As shown, step S400 of this embodiment, which involves establishing a database of users and their preferred content, includes:

[0081] Step S410: Collect content and viewing status data for each user during each program viewing session;

[0082] Step S420: Obtain the preferred content for each user based on the status data;

[0083] Step S430: Store the preferred content of different users into different target databases that match the users.

[0084] Specifically, this embodiment analyzes the status data of each user watching the program, and can also distinguish different users by detecting the user's facial data. Different databases will be established for each different user, so that when each user watches a program, the program can be recommended according to the corresponding database.

[0085] Specifically, such as Figure 6 As shown, after step S420 of obtaining the preferred content of each user based on the state data, this embodiment may further include:

[0086] Step S440: Store the preferred content obtained from the status data when the same user watches the program multiple times into the same database to form a target database that matches the user.

[0087] Each time a user watches a program, the content they prefer based on their viewing status is stored in the same database. Through repeated storage, the database grows continuously, increasing the accuracy and ranking of the user's preferred content, thus facilitating subsequent recommendations based on that user's preferences.

[0088] As a specific embodiment of this application, such as Figure 7 As shown, step S400 of this embodiment, the step of establishing a database of users and their preferred content, further includes:

[0089] Step S450: Detect the actual user in front of the TV screen;

[0090] Step S460: Determine whether the actual user is a new user; if yes, proceed to step S470; otherwise, proceed to step S480.

[0091] Step S470: Establish a new database that matches the actual user;

[0092] Step S480: Invoke the pre-established target database that matches the actual user.

[0093] Specifically, in this embodiment, each time the battery is powered on, the user watching the program is detected, and it is determined whether the user is a new user. If the user is a new user, a new database is created. If the user is not a new user, a pre-created or stored target database is accessed. This ensures that the data in the target database is continuously increased, and programs can be recommended based on the target database, while ensuring that new users are not missed.

[0094] Furthermore, the database can be further subdivided into program types, such as variety shows, TV dramas, movies, documentaries, news, science and education programs, sports events, commercials, and animation. When a user does not search, recommendations are made based on the user's favorite categories; when a user searches for a specific program type, recommendations are made based on the ranking of programs within that category.

[0095] As a specific embodiment of this application, such as Figure 8 As shown, step S470 of this embodiment, when the actual user is a new user, includes the step of establishing a new database matching the actual user:

[0096] Step S471: Determine whether the actual user has entered the search page; if yes, proceed to step S472; otherwise, end.

[0097] Step S472: Recommend and play programs based on the actual user search results;

[0098] Step S473: Determine whether the program is content that the actual user prefers based on the status data of the actual user when watching the program; if yes, proceed to step S474; otherwise, end.

[0099] Step S474: Store the program in a new database that matches the actual user.

[0100] Specifically, in this embodiment, if a user is identified as a new user while watching a program, the system directly recommends and plays programs based on the user's search queries. Furthermore, when the system uses status data to determine the new user's preferred content while watching a program, it stores this information in a new database. This information can then be used as a basis for subsequent searches or recommendations during the next television viewing.

[0101] Specifically, such as Figure 9 As shown, after step S460 of determining whether the actual user is a new user, this embodiment further includes:

[0102] Step S481: When the actual user is not a new user, determine whether the TV has entered the search page; if yes, proceed to step S482; otherwise, proceed to step S483.

[0103] Step S482: Recommend preferred content based on the target database that matches the actual user;

[0104] Step S483: Recommend preferred content based on the type of program the actual user last viewed.

[0105] Specifically, in this embodiment, when the user is not a new user, it means that the TV already stores a target database. When a new user performs a search, the TV can recommend content that the user prefers based on the target database. If the user does not enter the search page, the TV can directly recommend programs similar to those the user previously viewed. In this way, as long as a returning user is watching TV, the recommended programs are content that the user prefers, thereby enhancing the user experience.

[0106] As a specific embodiment of this application, step S450 of this embodiment, after the step of detecting the actual user in front of the TV screen, further includes:

[0107] Step S451: Determine if there are multiple actual users; if yes, proceed to step S452; otherwise, proceed to step S460.

[0108] Step S452: Determine whether each actual user is a new user;

[0109] Step S453: When multiple actual users are not new users, call the target database matched by each actual user, and call programs with similar preferences from multiple target databases for recommendation;

[0110] Step S454: When some actual users are new users and some actual users are not new users, recommend programs based on the content retrieved by the actual users and the preferred content in the target database corresponding to the non-new users.

[0111] Step S455: When all actual users are new users, recommend programs based on the content searched by the actual users and according to the built-in popularity ranking of the TV.

[0112] In this embodiment, the system detects whether there are multiple users watching the program. If all users are not new users, the system retrieves programs from each user's target database that reflect similar user preferences, ensuring that everyone can find programs they like. If some users are new and some are not, the system recommends programs based on a combination of the search results and the preferences found in the target databases of the non-new users, ensuring that the recommended programs satisfy at least some of the users' preferences. If all users are new, the system recommends programs based on popularity rankings, allowing users to choose their preferred content based on these rankings. This design ensures that multiple users can enjoy programs that cater to their preferences as much as possible while considering TV popularity rankings, thereby improving the user experience.

[0113] The following is a detailed description using specific examples.

[0114] When the TV is turned on, the system first checks if there is only one user. If there is only one user, it checks if the user is new. If so, the TV will recommend programs based on popularity rankings, regardless of whether the user enters the search page. If the user is not new, before entering the search page, programs related to the programs the user previously watched will be recommended. When the user enters the search page, the system retrieves the user's preferred content from the database based on the search results and recommends programs accordingly. If there are multiple users, the system checks if all users are new. If all users are new, programs will be recommended based on popularity rankings. If the multiple users include both new and existing users, the system combines the preferred programs from the database of existing users with the TV's own popularity rankings for a comprehensive recommendation. If all users are existing users, programs will be recommended based on similar programs from each user's database, ensuring that each user can see programs they like.

[0115] When a user is watching a program, the system detects their external data via a camera and their vital signs via a wristband and / or remote control. This data is then transmitted to the TV software for calculation to determine if the program is a favorite. If it is a favorite, the user and their favorite program are stored in the corresponding database (a new database is created for new users, while existing users are stored in the existing target database).

[0116] As a specific embodiment of this application, this embodiment also provides a user preference content recommendation control system, characterized in that it includes a memory, a processor, and a program for a user preference content recommendation method stored in the memory and executable on the processor. When the program for the user preference content recommendation method is executed by the processor, it implements the steps of the user preference content recommendation method described above.

[0117] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. General-purpose can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0118] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0119] In some embodiments, the memory can be an internal storage unit of the television, such as the television's hard drive or RAM. In other embodiments, the memory can be an external storage device of the television, such as a plug-in hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory can include both internal and external storage units of the television. The memory is used to store application software and various types of data installed on the television, such as the program code for installing the television. The memory can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory stores a program for a method of recommending user-preferred content, which can be executed by a processor to implement the user-preferred content recommendation method of this application.

[0120] As a specific embodiment of this application, this embodiment provides a television that includes the above-mentioned user-preferred content recommendation control system, used to control the display or playback of content recommended by the television based on the user-preferred content recommendation method.

[0121] As a specific embodiment of this application, this embodiment provides a computer-readable storage medium storing a program for a method of recommending user-preferred content. When the program for recommending user-preferred content is executed by a processor, it implements the steps of the method for recommending user-preferred content described above.

[0122] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0123] As a specific embodiment of this application, this embodiment also provides a computer program product, which includes a program for a method of recommending user-preferred content. When the program for recommending user-preferred content is executed by a processor, it implements the steps of the above-described method for recommending user-preferred content.

[0124] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0125] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0126] It should be understood that the above embodiments are exemplary and are not intended to encompass all possible implementations included in the claims. Various modifications and changes can be made to the above embodiments without departing from the scope of this disclosure. Similarly, the various technical features of the above embodiments can be arbitrarily combined to form other embodiments of this application that may not be explicitly described. Therefore, the above embodiments only illustrate several implementations of this application and do not limit the scope of protection of this patent application.

Claims

1. A method of recommending user preference content, characterized by, The method comprises: detecting state data of a user when watching a program; wherein the state data comprises external data and / or physical data, the external data comprises facial expression, body shape, breathing rate, and the physical data comprises blood pressure, pulse, heart rate; judging whether the program watched by the user is the user's favorite content according to the state data; when the program is the user's favorite content, recommending content matching the favorite content to the user.

2. The method of claim 1, wherein after the step of judging whether the program watched by the user is the user's favorite content according to the state data, the method further comprises: establishing a database of the user and the favorite content; when the user watches a program next time, recommending content related to the favorite content to the user according to the database.

3. The method of claim 2, wherein the step of establishing a database of the user and the favorite content comprises: collecting content and state data when watching a program of each user each time; obtaining the favorite content of each user according to the state data; storing the favorite content of different users into different target databases matching the users.

4. The method of claim 3, wherein after the step of obtaining the favorite content of each user according to the state data, the method further comprises: storing the favorite content obtained according to the state data when watching a program of the same user multiple times into the same database to form the target database matching the user.

5. The method of claim 3, wherein the step of establishing a database of the user and the favorite content further comprises: detecting an actual user in front of a TV screen; judging whether the actual user is a new user; when the actual user is a new user, establishing a new database matching the actual user; when the actual user is not a new user, calling the target database matching the actual user established in advance.

6. The method of claim 5, wherein when the actual user is a new user, the step of establishing a new database matching the actual user further comprises: judging whether the actual user enters a search page; when the TV enters the search page, recommending and playing according to the program searched by the actual user; judging whether the program is the favorite content of the actual user according to the state data of the actual user when watching the program; when it is obtained that the played program is the favorite content of the actual user, storing the program into the new database matching the actual user.

7. The method of claim 5, wherein after the step of judging whether the actual user is a new user, the method further comprises: when the actual user is not a new user, judging whether the TV enters a search page; ​ ​ ​ ​ ​ ​ When the television enters the search page, the favorite content is recommended according to the target database matched with the actual user; When the television does not enter the search page, the favorite content is recommended according to the type of the program last browsed by the actual user.

8. The method of claim 5, wherein, the step of detecting the actual user in front of the television screen further comprises: determining whether the actual user is multiple; when the actual user is multiple, determining whether each of the actual user is a new user; when the actual user is not a new user, calling the target database matched with each of the actual user, and recommending the similar favorite program from the target database; when some of the actual user is a new user and some of the actual user is not a new user, recommending the program according to the content searched by the actual user and the favorite content in the target database corresponding to the non-new user; when all of the actual user is a new user, recommending the program according to the content searched by the actual user and the hot ranking built-in the television.

9. The method of any one of claims 1-8, wherein, the step of detecting the state data of the user comprises: when the user is watching the program, starting the camera, and detecting the external data of the user by using the camera.

10. The method of any one of claims 1-8, wherein, the step of detecting the state data of the user further comprises: when the user is watching the program, determining whether the user is linked with the television; when the user is linked with the television, detecting the state data of the user; wherein the user is linked with the television by wearing a bracelet or holding a remote controller.

11. A system for controlling the recommendation of user preference content, characterized by A computer readable storage medium storing a program of the method of recommending favorite content of a user, the program of the method of recommending favorite content of a user being executed by a processor to implement the steps of the method of recommending favorite content of a user according to any one of claims 1-10.

12. A television characterized by A computer program product comprising the control system of recommending favorite content of a user according to claim 11, for controlling the television to display or play the content recommended by the method of recommending favorite content of a user.

13. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a program of the method of recommending favorite content of a user, the program of the method of recommending favorite content of a user being executed by a processor to implement the steps of the method of recommending favorite content of a user according to any one of claims 1-10.

14. A computer program product, characterised in that, The computer program product comprises a program of the method of recommending favorite content of a user, the program of the method of recommending favorite content of a user being executed by a processor to implement the steps of the method of recommending favorite content of a user according to any one of claims 1-10.

Images