CN115278370A - Television program recommendation method and system, smart television and medium - Google Patents

Television program recommendation method and system, smart television and medium Download PDF

Info

Publication number
CN115278370A
CN115278370A CN202210730250.5A CN202210730250A CN115278370A CN 115278370 A CN115278370 A CN 115278370A CN 202210730250 A CN202210730250 A CN 202210730250A CN 115278370 A CN115278370 A CN 115278370A
Authority
CN
China
Prior art keywords
user
target
television program
television
program
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210730250.5A
Other languages
Chinese (zh)
Inventor
李皖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Spreadtrum Semiconductor Nanjing Co Ltd
Original Assignee
Spreadtrum Semiconductor Nanjing Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Spreadtrum Semiconductor Nanjing Co Ltd filed Critical Spreadtrum Semiconductor Nanjing Co Ltd
Priority to CN202210730250.5A priority Critical patent/CN115278370A/en
Publication of CN115278370A publication Critical patent/CN115278370A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/441—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card
    • H04N21/4415—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies

Abstract

The invention discloses a recommendation method, a recommendation system, a smart television and a medium of television programs, wherein the recommendation method comprises the following steps: collecting face feature data of a target user to perform face recognition; determining viewing preference data of a target user based on a face recognition result; and screening out a target television program matched with the viewing preference data from the pre-stored television program classification information, and recommending the target television program to a target user. According to the method, the user preference and the program style type are combined, so that the corresponding television program is more accurately recommended to the user, and the real-time performance, the accuracy and the intelligence of television program recommendation are improved; the experience degree of the user is enhanced; the user's stickiness to the tv program content is increased.

Description

Television program recommendation method and system, smart television and medium
Technical Field
The invention relates to the technical field of intelligent televisions, in particular to a television program recommending method, a television program recommending system, an intelligent television and a medium.
Background
At present, with the development of internet technology and the pursuit of digital life by people, digital information such as broadcasting, television, short video, news, and the like enters the information explosion era. Live tv has also gradually developed as a multimedia carrying way for receiving external information or consuming entertainment.
However, although the existing live television program can realize a real-time interaction mode with a user, it is difficult to quickly and accurately grasp the preference and viewing characteristics of the user, so that the effect of video program recommendation is difficult to meet the actual requirements of the user.
Disclosure of Invention
The invention aims to overcome the defect that in the prior art, the effect of recommending video programs cannot meet the actual requirements of users easily because the television programs cannot fast and accurately grasp the preferences and viewing characteristics of the users, and provides a method, a system, an intelligent television and a medium for recommending the television programs.
The invention solves the technical problems through the following technical scheme:
in a first aspect, the present invention provides a recommendation method for television programs, where the recommendation method includes:
collecting face feature data of a target user to perform face recognition;
determining viewing preference data of the target user based on a face recognition result;
screening out a target television program matched with the viewing preference data from pre-stored television program classification information, and recommending the target television program to the target user; the television program classification information is generated from EPG information (electronic program guide) and Genre information (Genre/style) extracted from the transport stream media data.
Preferably, the face recognition result is a plurality of faces, and target users corresponding to the faces form a user group;
the step of determining the viewing preference data of the target user based on the face recognition result comprises the following steps:
selecting a main target user from the user group;
determining viewing preference data of the main target user;
the step of screening out the target television program matched with the viewing preference data from the pre-stored television program classification information and recommending the target television program to the target user comprises the following steps:
screening out a target television program matched with the watching preference data of the main target user from pre-stored program classification information, and recommending the target television program to the user group;
or the like, or a combination thereof,
the step of determining viewing preference data of the target user based on the face recognition result includes:
determining viewing preference data for each of the target users;
calculating preference intersection data of the user group according to the viewing preference data of each target user;
the step of screening out the target television program matched with the viewing preference data from the pre-stored program classification information and recommending the target television program to the target user comprises the following steps:
screening out a target television program matched with the preference intersection data of the user group from pre-stored television program classification information, and recommending the target television program to the user group;
or the like, or a combination thereof,
the step of determining viewing preference data of the target user based on the face recognition result includes:
determining viewing preference data of the user group;
the step of screening out the target television program matched with the viewing preference data from the pre-stored program classification information and recommending the target television program to the target user comprises the following steps:
and screening out a target television program matched with the viewing preference data of the user group from pre-stored television program classification information, and recommending the target television program to the user group.
Preferably, the recommendation method further comprises:
receiving a mode selection instruction;
acquiring a current watching mode of the smart television according to the mode selection instruction; the current watching mode is one of a master user watching mode, a user set watching mode and a user group watching mode;
the step of determining viewing preference data of the target user based on the face recognition result includes:
and determining the viewing preference data of the user group based on a face recognition result according to the current viewing mode.
Preferably, the recommendation method further comprises:
inputting the face feature data of a plurality of users into a database in a face recognition mode;
and acquiring the program watching record of each user in the database, and generating viewing preference data corresponding to different users.
Preferably, the recommendation method further comprises:
and updating the viewing preference data corresponding to the user according to the program viewing record of the user.
Preferably, the television program classification information includes television program genre data and television program genre data.
Preferably, the target television program includes a television program in a current time period and/or a television program in a future preset time period.
Preferably, the recommendation method further comprises:
receiving a user selection instruction;
and displaying a user list according to the user selection instruction so that the target user can inquire the television programs to be recommended corresponding to other users according to the user list.
Preferably, the recommendation method further comprises:
and when the starting time of the television program to be played in the target television program is monitored, switching to playing the television program to be played.
In a second aspect, the present invention provides a recommendation system for television programs, the recommendation system comprising:
the acquisition module is used for acquiring the face characteristic data of a target user to perform face recognition;
the determining module is used for determining viewing preference data of the target user based on a face recognition result;
the recommending module is used for screening out a target television program matched with the viewing preference data from pre-stored television program classification information and recommending the target television program to the target user; the television program classification information is generated from EPG information (electronic program guide) and Genre information (Genre/style) extracted from the transport stream media data.
Preferably, the face recognition result is a plurality of faces, and target users corresponding to the faces form a user group;
the determining module is specifically configured to:
selecting a main target user from the user group;
determining viewing preference data of the main target user;
the recommendation module is specifically configured to:
screening out a target television program matched with the watching preference data of the main target user from pre-stored program classification information, and recommending the target television program to the user group;
or the like, or, alternatively,
the determining module is specifically configured to:
determining viewing preference data for each of the target users;
calculating preference intersection data of the user group according to the viewing preference data of each target user;
the recommendation module is specifically configured to:
screening out a target television program matched with the preference intersection data of the user group from pre-stored television program classification information, and recommending the target television program to the user group;
or the like, or, alternatively,
the determining module is specifically configured to:
determining viewing preference data of the user group;
the recommendation module is specifically configured to:
and screening out a target television program matched with the viewing preference data of the user group from pre-stored television program classification information, and recommending the target television program to the user group.
Preferably, the recommendation system further comprises:
the first receiving module is used for receiving a mode selection instruction;
the acquisition module is used for acquiring the current watching mode of the intelligent television according to the mode selection instruction; the current watching mode is one of a master user watching mode, a user set watching mode and a user group watching mode;
the determining module is specifically configured to:
and determining the viewing preference data of the user group based on a face recognition result according to the current viewing mode.
Preferably, the recommendation system further comprises:
the first input module is used for inputting the face feature data of a plurality of users into a database in a face recognition mode;
the second entry module is used for entering the program watching record corresponding to each user into the database;
and the generating module is used for generating viewing preference data corresponding to different users according to the program viewing records.
Preferably, the recommendation system further comprises:
and the updating module is used for updating the film watching preference data corresponding to the user according to the program watching record of the user.
Preferably, the television program classification information includes television program genre data and television program genre data.
Preferably, the target television program includes a television program in a current time period and/or a television program in a future preset time period.
Preferably, the recommendation system further comprises:
the second receiving module is used for receiving a user selection instruction;
and the display module is used for displaying a user list according to the user selection instruction so that the target user can inquire the television programs to be recommended corresponding to other users according to the user list.
Preferably, the recommendation system further comprises:
and the switching module is used for monitoring and switching to play the television program to be played when the playing start time of the television program to be played in the target television program is reached.
In a third aspect, the present invention provides an intelligent television, which includes a processor, a memory, and a computer program stored on the memory and operable on the processor, and when executed by the processor, the computer program implements the method for recommending a television program according to any one of the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the method for recommending television programs according to any one of the first aspect.
The positive progress effects of the invention are as follows: the invention provides a recommendation method, a recommendation system, an intelligent television and a medium of television programs. According to the method, the user preference and the program style type are combined, so that the corresponding television program is more accurately recommended to the user, and the real-time performance, the accuracy and the intelligence of television program recommendation are improved; the experience degree of the user is enhanced; the user's stickiness to the content of the television program is increased.
Drawings
Fig. 1 is a first flowchart of a television program recommendation method according to embodiment 1 of the present invention.
Fig. 2 is a second flowchart of a recommendation method of a television program according to embodiment 1 of the present invention.
Fig. 3 is a first flowchart of a method for recommending a television program according to embodiment 2 of the present invention.
Fig. 4 is a second flowchart of a method for recommending a television program according to embodiment 2 of the present invention.
Fig. 5 is a third flowchart of a television program recommending method according to embodiment 2 of the present invention
Fig. 6 is a fourth flowchart of a television program recommendation method according to embodiment 2 of the present invention.
Fig. 7 is a schematic block diagram of a television program recommendation system according to embodiment 3 of the present invention.
Fig. 8 is a schematic block diagram of a television program recommendation system according to embodiment 4 of the present invention.
Fig. 9 is a schematic diagram of a hardware structure of an electronic device according to embodiment 5 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
As shown in fig. 1, the recommendation method for television programs of this embodiment includes:
and S11, collecting face feature data of the target user to perform face recognition.
And S12, determining viewing preference data of the target user based on the face recognition result.
S13, screening out a target television program matched with the viewing preference data from the pre-stored television program classification information, and recommending the target television program to a target user; the television program classification information is generated based on EPG information and Genre information extracted from the transport stream media data.
The television program classification information comprises television program type data and television program style genre data; the target television programs include television programs in the current time period and/or television programs in a future preset time period.
And S14, receiving a user selection instruction.
And S15, displaying the user list according to the user selection instruction so that the target user can inquire the television programs to be recommended corresponding to other users according to the user list.
And S16, switching to playing the television program to be played when the playing start time of the television program to be played in the target television program is monitored.
In this embodiment, the recommendation method may be implemented by a smart television, or by a smart terminal (e.g., a mobile phone installed with a corresponding application) in communication connection with the smart television, or may be applied to other smart viewing devices, or may be executed in a computer terminal, a network device, a chip, or a chip module. For example, the device such as a tablet computer, a smart phone, and an intelligent outdoor large screen is not limited herein to a specific apparatus for implementing the recommendation method.
For the above step S11, the facial feature data of the target user is collected by a facial information collection device, which includes a depth camera different from a conventional two-dimensional camera. The depth camera can be integrated inside the intelligent television terminal, can be hung outside the intelligent television terminal and can be integrated inside the mobile terminal. The operation of acquiring the face feature data of the target user by using the face acquisition device can be triggered by starting the intelligent television terminal by the target user or triggered at a preset interval time after the intelligent television terminal is started. In the process of face recognition, data which can reflect the facial structure characteristics of a target user, such as eyes, a nose or a mouth of the target user, can be extracted from the face feature data.
For step S12, viewing preference data corresponding to the target user may be obtained from a viewing preference model trained in advance based on a deep learning algorithm, or may be obtained from a pre-established database.
In the embodiment, the sample sets of the historical film watching records of a plurality of historical users can be obtained in advance, the sources and the number of the sample sets are not limited, and the larger the number of the sample sets is, the more accurate the output result of the film watching preference model is. Specifically, the face recognition result of the historical user and the historical viewing record are used as the input of the viewing preference model, the viewing preference data is used as the output of the viewing preference model, and the viewing preference model is generated.
In step S13, EPG information and Genre information are extracted from the digital television TS (Transport Stream, transport Stream of media files). The EPG information indicates television program information of the last several days of each channel, and the Genre information indicates Genre or Genre information of each television program. The target television programs screened from the pre-stored television program classification information can comprise a plurality of programs to be recommended, and the programs to be recommended are sorted according to the preference degree of the user to be recommended, so that the recommended target television programs are as much as possible in accordance with the preference of the user, the recommended programs are sorted according to the preference degree of the user, the ordering and the focusing are strong, and the experience degree of the user is improved.
It is understood that the genre data includes at least one of a director genre, an actor genre, a drama genre, a title genre, a language genre, and a channel genre. The style genre data includes at least one of an education style genre, an entertainment style genre, a movie style genre, a news style genre, a sports style genre, a children style genre, a drama style genre, a music style genre, a comedy style genre, a game style genre, a scientific style genre, and a shopping style genre.
The target tv programs include tv programs of all channels available in the current time period (e.g., 3-4 hours) or the current time period, and the target tv programs may also include tv programs of all channels available in a future time period (e.g., 2-3 days). That is, the target user can view the television program being played in the current time period, and simultaneously can acquire the advance television program which will be played on a certain channel in the future and is interested by the target user, and can reserve the television program which is interested in the future time period, thereby enhancing the viscosity of the target user to the live television program.
For the above step S14, a user selection instruction generated by the target user through a physical key on the remote controller, or a user selection instruction generated by text input, or a user selection instruction generated by voice input is received.
In step S15, the smart television displays the user list, prompts the target user to select one or more users to be viewed from the user list established and stored by a plurality of different other users, and queries the television program to be recommended corresponding to the one or more users to be viewed. The target user can check the television programs to be recommended of other users through inquiring, for example, the target user can check the television programs to be recommended of other people in the family members and adjust the television programs to be played in the target television programs at any time, so that the television program list is more flexible, the watching selection range of the target user is expanded, and the experience of the target user on the smart television is enhanced.
In step S16, after the target user selects to receive the target television program recommended by the smart television, the target user may receive a user detection instruction, and then start monitoring the target television program. Monitoring of the target television program may also be automatically initiated. And when the playing start time of the television program to be played is reached, switching to the channel of the television program to be played. The problem that in traditional program recommendation, the recommended television program content cannot be automatically switched on the same intelligent television device according to the user's disuse in watching is solved. The television programs to be played are automatically and intelligently switched, so that the time that a target user misses watching favorite live television programs is reduced, and the user experience of the intelligent television is enhanced.
In a possible implementation scheme, as shown in fig. 2, the recommendation method further includes:
s101, inputting the face feature data of a plurality of users into a database in a face recognition mode.
And S102, recording the program watching record corresponding to each user into a database.
And S103, generating viewing preference data corresponding to different users according to the program viewing records.
And S104, updating the viewing preference data corresponding to the user according to the program viewing record of the user.
Aiming at the steps S101-S102, a database is established in advance and stored in the intelligent television in advance. The method includes the steps of collecting face feature data of a plurality of different users, for example, collecting face feature data of a plurality of users in family members, inputting the face feature data into a database after face recognition is carried out on the face feature data, obtaining a program watching record of each user, and inputting the program watching record into the database which stores the face feature data. In addition, a plurality of different users can also obtain the face feature data of the users through the smart television in a recognizable range of the smart television and store the face feature data in the database. The database is used for comparing the face feature data of the user to determine the identity information of the user.
In step S103, program viewing records of each user in the past days, months, or other historical time periods pre-stored in the database are obtained, and what type of tv programs the user is interested in is determined from the program viewing records according to the length of the viewing time of the programs, and the tv programs are arranged in the order of increasing interest degree to decreasing interest degree, so as to generate viewing preference data corresponding to different users.
For the above step S104, every time the user finishes watching a television program, the program watching records of the same user in the database are updated in real time, so as to adjust the watching preference data corresponding to the user.
In this embodiment, a recommendation method for television programs is provided, where viewing preference data of a target user is determined according to a face recognition result, and a target television program matched with the viewing preference data is screened from pre-stored television program classification information. According to the method, the user preference and the program style type are combined, so that the corresponding television program is more accurately recommended to the user, and the real-time performance, the accuracy and the intelligence of television program recommendation are improved; the experience degree of the user is enhanced; the user's stickiness to the tv program content is increased.
Example 2
On the basis of embodiment 1, in the recommendation method of a television program according to this embodiment, the face recognition result is a plurality of faces, and target users corresponding to the plurality of faces form a user group.
In a possible implementation scheme, as shown in fig. 3, the recommendation method further includes:
and S111, receiving a mode selection command.
S112, acquiring the current watching mode of the smart television according to the mode selection instruction; the current viewing mode is one of a master user viewing mode, a user set viewing mode, and a user group viewing mode.
Step S12 includes:
and S120, determining the viewing preference data of the user group based on the face recognition result according to the current viewing mode.
Specifically, the multi-user viewing scene may be divided into a master user scene, a user group scene and a user group scene, where the master user scene corresponds to a master user viewing mode, the user group scene corresponds to a user group viewing mode, and the user group scene corresponds to a user group viewing mode. In this embodiment, the current viewing mode of the smart television is determined by analyzing the mode selection instruction, and television program recommendation is performed for the user group in different television program recommendation modes in different current viewing modes.
In one possible implementation, as shown in fig. 4, step S12 includes:
s121, selecting a main target user from the user group.
And S122, determining the viewing preference data of the main target user.
Step S13 includes:
s131, screening out target television programs matched with the viewing preference data of the main target users from the pre-stored program classification information, and recommending the target television programs to the user group.
In the foregoing steps S121 to S122, in a scene in which a plurality of users view images simultaneously, the face recognition result is a plurality of faces. For example, two parents watch the film at the same time, two parents and children watch the film at the same time, and three parents and children watch the film at the same time, and users participating in the film watching at the same time are taken as a user group. One user is selected from the user group as a main target user, for example, the user a may be selected as the main target user from the users a, B, and C who participate in the viewing at the same time. And after the face characteristic data of the user A is subjected to face recognition, inquiring the film watching preference data of the user A from a preset database according to a face recognition result.
In step S131, the viewing preference data of the user a is used as an inquiry criterion, a target tv program is screened from the pre-stored program classification information, and the target tv program is automatically recommended to the user a, the user B, and the user C who participate in viewing the video at the same time. That is, when multiple users watch videos simultaneously, a certain user is selected as a main target user, and a target television program recommended for a user group is screened out from the pre-stored program classification information according to the main target user.
In one possible implementation, as shown in fig. 5, step S12 includes:
and S123, determining the viewing preference data of each target user.
And S124, calculating preference intersection data of the user group according to the viewing preference data of each target user.
Step S13 includes:
s132, screening out a target television program matched with the preference intersection data of the user group from the pre-stored television program classification information, and recommending the target television program to the user group.
And aiming at the steps S123-S124, acquiring the A film watching preference data corresponding to the A user, the B film watching preference data corresponding to the B user and the C film watching preference data corresponding to the C user which simultaneously participate in film watching. In this embodiment, the D-preference intersection data of the user group constituted by A, B and the C user is calculated by using a set mathematical calculation formula according to the a viewing preference data, the B viewing preference data, and the C viewing preference data. For example, if a user prefers a tv program of the DEF genre type, a user B prefers a tv program of the EFG genre type, and a user C prefers a tv program of the EFH genre type, the preference intersection data of the user group formed by the user a, the user B, and the user C is a tv program of the EF genre type.
In step S132, the D-preference intersection data is used as a query criterion, a target tv program is screened from the pre-stored program classification information, and the target tv program is automatically recommended to the user a, the user B, and the user C who participate in viewing at the same time. That is, when multiple persons watch videos simultaneously, after the preference intersection data of the user group watching videos simultaneously is calculated, the target television program recommended for the user group is screened out from the pre-stored program classification information based on the preference intersection data of the user group.
In one possible implementation, as shown in fig. 6, step S12 includes:
and S125, determining the viewing preference data of the user group.
Step S13 includes:
and S133, screening out a target television program matched with the viewing preference data of the user group from the pre-stored television program classification information, and recommending the target television program to the user group.
In step S125, a historical viewing record of an independent user, which is a user group formed by the user a, the user B, and the user C, is obtained, and viewing preference data of the user group is determined according to the historical viewing record.
In step S133, the viewing preference data of the user group is used as a query criterion, a target tv program is screened from the pre-stored program classification information, and the target tv program is automatically recommended to the user a, the user B, and the user C who participate in viewing the video at the same time. That is, when multiple persons watch videos simultaneously, after the viewing preference data of the user group is calculated, the target television program recommended for the user group is screened out from the pre-stored program classification information based on the viewing preference data of the user group.
In this embodiment, a recommendation method for television programs is provided, where viewing preference data of a user group is determined based on a face recognition result of multiple users and a current viewing mode, and a target television program matched with the viewing preference data of the user group is screened from pre-stored television program classification information. The method combines the preference data of the user group with the program style types, realizes more accurate recommendation of the corresponding television programs for the user group, and improves the instantaneity, accuracy and intelligence of television program recommendation in a multi-user film watching scene; the experience degree of each user is enhanced; the stickiness of each user to the content of the television program is increased.
Example 3
As shown in fig. 7, the recommendation system for television programs of this embodiment includes: an acquisition module 210, a determination module 220, a recommendation module 230, a second receiving module 240, a display module 250, and a switching module 260.
The acquisition module 210 is configured to acquire face feature data of a target user for face recognition.
And the determining module 220 is used for determining the viewing preference data of the target user based on the face recognition result.
And a recommending module 230, configured to screen out a target television program matching the viewing preference data from pre-stored television program classification information, and recommend the target television program to a target user, where the television program classification information is generated according to EPG information and Genre information extracted from the transport stream media data.
The television program classification information comprises television program type data and television program style genre data; the target television programs include television programs in the current time period and/or television programs in a future preset time period.
And a second receiving module 240, configured to receive a user selection instruction.
And the display module 250 is configured to display the user list according to the user selection instruction, so that the target user queries the television programs to be recommended corresponding to other users according to the user list.
The switching module 260 is configured to switch to play the television program to be played when the start time of playing the television program to be played in the target television program is monitored.
The acquisition module 210 acquires facial feature data of a target user through a facial information acquisition device including a depth camera different from a conventional two-dimensional camera. The depth camera can be integrated inside the intelligent television terminal, can be hung outside the intelligent television terminal and can be integrated inside the mobile terminal. The operation of acquiring the face feature data of the target user by using the face acquisition device can be triggered by starting the intelligent television terminal by the target user or triggered at a preset interval time after the intelligent television terminal is started. In the process of face recognition, data which can reflect the facial structure characteristics of a target user, such as eyes, a nose or a mouth of the target user, can be extracted from the face feature data.
The determining module 220 may obtain viewing preference data corresponding to the target user from a viewing preference model trained in advance based on a deep learning algorithm, or may obtain viewing preference data corresponding to the target user from a pre-established database.
In the embodiment, the sample sets of the historical film watching records of a plurality of historical users can be obtained in advance, the sources and the number of the sample sets are not limited, and the larger the number of the sample sets is, the more accurate the output result of the film watching preference model is. Specifically, the face recognition result of the historical user and the historical viewing record are used as the input of the viewing preference model, the viewing preference data is used as the output of the viewing preference model, and the viewing preference model is generated.
The recommendation module 230 extracts EPG (electronic program guide) information and Genre (Genre/style) information from a digital tv TS (Transport Stream of media files). The EPG information indicates television program information of the last several days of each channel, and the Genre information indicates Genre or Genre information of each television program. The target television programs screened from the pre-stored television program classification information can comprise a plurality of programs to be recommended, and the programs to be recommended are sorted according to the preference degree of the user to be recommended, so that the recommended target television programs are as much as possible in accordance with the preference of the user, the recommended programs are sorted according to the preference degree of the user, the ordering and the focusing are strong, and the experience degree of the user is improved.
It is understood that the genre data includes at least one of a director genre, an actor genre, a drama genre, a title genre, a language genre, and a channel genre. The style genre data includes at least one of an education style genre, an entertainment style genre, a movie style genre, a news style genre, a sports style genre, a children style genre, a drama style genre, a music style genre, a comedy style genre, a game style genre, a scientific style genre, and a shopping style genre.
The target tv programs include tv programs of all channels available for the current day or in the current time period (e.g., 3-4 hours), and the target tv programs may also include tv programs of all channels available for a future time period (e.g., 2-3 days). That is, the target user can watch the television program which is being played at the current time interval, and simultaneously can obtain the advance television program which is interested by the target user and is to be played on a certain channel in the future, and can reserve the television program which is interested at the future time interval, so that the viscosity of the target user to the live television program is enhanced.
The second receiving module 240 receives a user selection instruction generated by a target user through a physical key on a remote controller, or a user selection instruction generated through text input, or a user selection instruction generated through voice input.
The display module 250 controls the smart television to display the user list, prompts the target user to select one or more users to be viewed from the user list established and stored by a plurality of different other users, and queries the television programs to be recommended corresponding to the one or more users to be viewed. The target user can check the television programs to be recommended of other users through inquiring, for example, the target user can check the television programs to be recommended of other people in the family members and adjust the television programs to be played in the target television programs at any time, so that the television program list is more flexible, the watching selection range of the target user is expanded, and the experience of the target user on the smart television is enhanced.
And after the target user selects to receive the target television program recommended by the intelligent television, the target user can receive a user detection instruction and then starts monitoring the target television program. Monitoring of the target television program may also be automatically initiated. When the playing start time of the television program to be played is reached, the switching module 260 switches to the channel of the television program to be played. The problem that in traditional program recommendation, the recommended television program content cannot be automatically switched on the same intelligent television device according to the user's disuse is solved, wherein the set is based on the account number logged in by the user. The television programs to be played are automatically and intelligently switched, so that the time that a target user misses watching a favorite live television program is reduced, and the user experience of the intelligent television is enhanced.
In one possible implementation, the recommendation system further includes: the device comprises a first recording module, a second recording module, a generating module and an updating module;
the first input module is used for inputting the face feature data of a plurality of users into the database in a face recognition mode.
And the second entry module is used for entering the program watching record corresponding to each user into the database.
And the generating module is used for generating viewing preference data corresponding to different users according to the program viewing records.
And the updating module is used for updating the film watching preference data corresponding to the user according to the program watching record of the user.
A database is established in advance and stored in the intelligent television in advance. The method comprises the steps of collecting face feature data of a plurality of different users, for example, the face feature data of a plurality of users in family members can be collected, a first input module carries out face recognition on the face feature data and then inputs the face feature data into a database to obtain a program watching record of each user, and a second input module inputs the program watching record into the database which stores the face feature data. In addition, a plurality of different users can also obtain the face feature data of the users through the smart television in a recognizable range of the smart television and store the face feature data in the database. The database is used for comparing the face feature data of the user to determine the identity information of the user.
The method comprises the steps of obtaining program watching records of each user in the past days, the past months or other historical time periods, which are pre-stored in a database, confirming what types of television programs are interesting to the user from the program watching records according to the watching time length of the programs, arranging the television programs according to the sequence of the interest degrees from large to small, and generating watching preference data corresponding to different users by a generating module.
And after the user finishes watching the television program once, the updating module updates the program watching record of the same user in the database in real time, so that the watching preference data corresponding to the user is adjusted.
It should be noted that, the recommendation system for television programs in this embodiment may be: a single chip, a chip module, or an electronic device, or a chip module integrated into an electronic device. Each module included in each apparatus and product described in the above embodiments may be a software module, or may also be a hardware module, or may also be a part of a software module, and a part of a hardware module. For example, for each device or product applied to or integrated in a chip, each module included in the device or product may be implemented by hardware such as a circuit, or at least a part of the modules/units may be implemented by a software program running on a processor integrated in the chip, and the rest of the modules may be implemented by hardware such as a circuit; for each device and product applied to or integrated in the chip module, each module included in the device and product may be implemented in a hardware manner such as a circuit, and different modules may be located in the same component (e.g., a chip, a circuit module, etc.) or different components of the chip module, or at least part of the modules/units may be implemented in a software program, the software program runs on a processor integrated in the chip module, and the rest of the modules may be implemented in a hardware manner such as a circuit; for each device and product applied to or integrated in a base station or an electronic device, each module included in the device and product may be implemented by hardware such as a circuit, different modules may be located in the same component (e.g., a chip, a circuit module, etc.) or different components in the electronic device, or at least a part of the modules/units may be implemented by a software program running on a processor integrated in the electronic device, and the rest of the modules/units may be implemented by hardware such as a circuit.
In this embodiment, a recommendation system for television programs is provided, where a determination module determines viewing preference data of a target user according to a face recognition result, and a recommendation module screens out a target television program matching the viewing preference data from pre-stored television program classification information. According to the method, the user preference and the program style type are combined, so that the corresponding television program is more accurately recommended to the user, and the real-time performance, the accuracy and the intelligence of television program recommendation are improved; the experience degree of the user is enhanced; the user's stickiness to the tv program content is increased.
Example 4
On the basis of embodiment 2, in the recommendation system for television programs of this embodiment, the face recognition result is a plurality of faces, and target users corresponding to the plurality of faces form a user group.
In a possible implementation, as shown in fig. 8, the recommendation system further includes: a first receiving module 211 and an obtaining module 212.
The first receiving module 211 is configured to receive a mode selection instruction.
The obtaining module 212 is configured to obtain a current viewing mode of the smart television according to the mode selection instruction; the current viewing mode is one of a master user viewing mode, a user set viewing mode, and a user group viewing mode.
The determining module 220 is specifically configured to: and determining viewing preference data of the user group based on the face recognition result according to the current viewing mode.
Specifically, the multi-user viewing scene may be divided into a master user scene, a user group scene and a user group scene, where the master user scene corresponds to a master user viewing mode, the user group scene corresponds to a user group viewing mode, and the user group scene corresponds to a user group viewing mode. In this embodiment, the obtaining module 212 analyzes the mode selection instruction to determine the current viewing mode of the smart television, and recommends television programs for the user group in different television program recommendation manners in different current viewing modes.
In one possible implementation, the recommendation system includes:
the determining module 220 is specifically configured to:
selecting a main target user from a user group;
viewing preference data for the primary target user is determined.
The recommendation module 230 is specifically configured to:
and screening out target television programs matched with the viewing preference data of the main target users from the pre-stored program classification information, and recommending the target television programs to the user group.
Under the scene that a plurality of users watch the film at the same time, the face recognition result is a plurality of faces. For example, two parents watch the film at the same time, two parents and children watch the film at the same time, and one family with three mouths watch the film at the same time. The determining module 220 selects a user from the user group as a main target user, for example, the user a may be selected as a main target user from the user a, the user B, and the user C that participate in viewing the film at the same time. And after the face characteristic data of the user A is subjected to face recognition, inquiring the film watching preference data of the user A from a preset database according to a face recognition result.
Taking the viewing preference data of the user a as the query criteria, the recommending module 230 screens out the target television program from the pre-stored program classification information, and automatically recommends the target television program to the user a, the user B, and the user C who participate in viewing the video at the same time. That is, when a plurality of users watch videos simultaneously, a certain user is selected as a main target user, and a target television program recommended for a user group is screened from the pre-stored program classification information according to the main target user.
In one possible implementation, the recommendation system includes:
the determining module 220 is specifically configured to:
determining viewing preference data of each target user;
and calculating preference intersection data of the user group according to the viewing preference data of each target user.
The recommendation module 230 is specifically configured to:
and screening out a target television program matched with the preference intersection data of the user group from the pre-stored television program classification information, and recommending the target television program to the user group.
And acquiring the A film watching preference data corresponding to the A users who simultaneously participate in film watching, the B film watching preference data corresponding to the B users and the C film watching preference data corresponding to the C users. In this embodiment, according to the viewing preference data a, the viewing preference data B, and the viewing preference data C, the determining module 220 calculates the D preference intersection data of the user group consisting of A, B and the user group consisting of the user C by using a set mathematical calculation formula. For example, if the a user prefers a television program of DEF genre, the B user prefers a television program of EFG genre, and the C user prefers a television program of EFH genre, the preference intersection data of the user group formed by the a user, the B user, and the C user is a television program of EF genre.
Using the D-preference intersection data as a query criterion, the recommending module 230 screens out a target television program from the pre-stored program classification information, and automatically recommends the target television program to the user a, the user B, and the user C who participate in watching the movie at the same time. That is, when multiple persons watch videos simultaneously, after the preference intersection data of the user group watching videos simultaneously is calculated, the target television program recommended for the user group is screened out from the pre-stored program classification information based on the preference intersection data of the user group.
In one possible implementation, the recommendation system includes:
the determining module 220 is specifically configured to:
determining viewing preference data of a user group;
the recommendation module 230 is specifically configured to:
and screening out a target television program matched with the viewing preference data of the user group from the pre-stored television program classification information, and recommending the target television program to the user group.
For example, a user a prefers a television program of a war film, B user B prefers a television program of a drama, and C user C prefers a television program of an animation film, but a user group formed by the user a, the user B, and the user C prefers a television program of a news simulcast, that is, in the case where three users A, B and C watch television programs on site simultaneously, the user group prefers a television program of a news simulcast. Therefore, in the user group mode corresponding to multi-user viewing, the target television program matched with the viewing preference data of the user group is automatically recommended.
The viewing preference data of the user group is used as a query criterion to screen out a target television program from the pre-stored program classification information, and the recommending module 230 automatically recommends the target television program to the user a, the user B, and the user C who participate in viewing the video at the same time. That is, when multiple persons watch videos simultaneously, after the viewing preference data of the user group is calculated, the target television program recommended for the user group is screened out from the pre-stored program classification information based on the viewing preference data of the user group.
In this embodiment, a recommendation system for television programs is provided, in which a determining module determines viewing preference data of a user group according to a face recognition result, and a recommendation module screens out a target television program matching the viewing preference data of the user group from pre-stored television program classification information. The invention combines the preference data of the user group with the program style types, realizes more accurate recommendation of corresponding television programs for the user group, and improves the real-time performance, accuracy and intelligence of television program recommendation in a multi-user film watching scene; the experience degree of each user is enhanced; the stickiness of each user to the content of the television program is increased.
Example 5
Fig. 9 is a schematic structural diagram of an intelligent television provided in this embodiment. The smart tv includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the method for recommending a television program according to embodiment 1 or embodiment 2, and the smart tv 90 shown in fig. 9 is only an example and should not bring any limitation to the functions and the scope of the embodiment of the present invention.
The smart tv 90 may be embodied in the form of a general purpose computing device, which may be a server device, for example. The components of the smart tv 90 may include, but are not limited to: the at least one processor 91, the at least one memory 92, and a bus 93 that connects the various system components (including the memory 92 and the processor 91).
The bus 93 includes a data bus, an address bus, and a control bus.
Memory 92 may include volatile memory, such as Random Access Memory (RAM) 921 and/or cache memory 922, and may further include Read Only Memory (ROM) 923.
Memory 92 may also include a program/utility 925 having a set (at least one) of program modules 924, such program modules 924 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The processor 91 executes various functional applications and data processing, such as a recommendation method of a television program according to embodiment 1 or embodiment 2 of the present invention, by running the computer program stored in the memory 92.
The smart tv 90 may also communicate with one or more external devices 94 (e.g., keyboard, pointing device, etc.). Such communication may be through an input/output (I/O) interface 95. Also, the model-generated smart television 90 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via a network adapter 96. As shown, the network adapter 96 communicates with the other modules of the model-generated smart television 90 via bus 93. It should be understood that although not shown in fig. 9, other hardware and/or software modules may be used in conjunction with the model-generated smart tv 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Example 6
The present embodiment provides a computer-readable storage medium on which a computer program is stored, the program implementing the recommendation method of a television program of embodiment 1 or embodiment 2 when executed by a processor.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation, the present invention can also be implemented in the form of a program product including program code for causing a terminal device to execute a recommendation method for a television program that implements embodiment 1 or embodiment 2 when the program product is run on the terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may be executed entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.

Claims (12)

1. A method for recommending television programs, the method comprising:
collecting face feature data of a target user to perform face recognition;
determining viewing preference data of the target user based on a face recognition result;
screening out a target television program matched with the viewing preference data from pre-stored television program classification information, and recommending the target television program to the target user; the television program classification information is generated based on EPG information and Genre information extracted from transport stream media data.
2. The method of claim 1, wherein the face recognition result is a plurality of faces, and the target users corresponding to the plurality of faces form a user group;
the step of determining viewing preference data of the target user based on the face recognition result includes:
selecting a main target user from the user group;
determining viewing preference data of the main target user;
the step of screening out the target television program matched with the viewing preference data from the pre-stored television program classification information and recommending the target television program to the target user comprises the following steps:
screening out a target television program matched with the viewing preference data of the main target user from pre-stored program classification information, and recommending the target television program to the user group;
or the like, or, alternatively,
the step of determining viewing preference data of the target user based on the face recognition result includes:
determining viewing preference data of each target user;
calculating preference intersection data of the user group according to the viewing preference data of each target user;
the step of screening out the target television program matched with the viewing preference data from the pre-stored program classification information and recommending the target television program to the target user comprises the following steps:
screening out a target television program matched with the preference intersection data of the user group from pre-stored television program classification information, and recommending the target television program to the user group;
or the like, or, alternatively,
the step of determining viewing preference data of the target user based on the face recognition result includes:
determining viewing preference data of the user group;
the step of screening out the target television program matched with the viewing preference data from the pre-stored program classification information and recommending the target television program to the target user comprises the following steps:
and screening out a target television program matched with the viewing preference data of the user group from pre-stored television program classification information, and recommending the target television program to the user group.
3. The method of recommending television programs according to claim 2, wherein said recommending method further comprises:
receiving a mode selection instruction;
acquiring a current watching mode of the smart television according to the mode selection instruction; the current watching mode is one of a master user watching mode, a user set watching mode and a user group watching mode;
the step of determining viewing preference data of the target user based on the face recognition result includes:
and determining the viewing preference data of the user group based on a face recognition result according to the current viewing mode.
4. The method for recommending television programs according to claim 1, wherein said recommending method further comprises:
inputting the face feature data of a plurality of users into a database in a face recognition mode;
entering a program viewing record corresponding to each user into the database;
and generating viewing preference data corresponding to different users according to the program viewing records.
5. The method for recommending television programs according to claim 4, wherein said recommending method further comprises:
and updating the viewing preference data corresponding to the user according to the program viewing record of the user.
6. The method of recommending television programs according to claim 1, wherein said television program classification information includes television program genre data and television program genre data.
7. The method for recommending television programs according to claim 1, wherein said target television programs include television programs in a current time slot and/or television programs in a future preset time slot.
8. A recommendation method for television programs according to claim 1, characterized in that said recommendation method further comprises:
receiving a user selection instruction;
and displaying a user list according to the user selection instruction so that the target user can inquire the television programs to be recommended corresponding to other users according to the user list.
9. The method for recommending television programs according to claim 1, wherein said recommending method further comprises:
and when the starting time of the television program to be played in the target television program is monitored, switching to playing the television program to be played.
10. A recommendation system for television programs, said recommendation system comprising:
the acquisition module is used for acquiring the face characteristic data of a target user to perform face recognition;
the first determination module is used for determining viewing preference data of the target user based on a face recognition result;
the recommending module is used for screening out a target television program matched with the viewing preference data from pre-stored television program classification information and recommending the target television program to the target user; the television program classification information is generated based on EPG information and Genre information extracted from transport stream media data.
11. An intelligent television comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing a method for recommending television programs according to any of claims 1-9.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a recommendation method for a television program according to any one of claims 1 to 9.
CN202210730250.5A 2022-06-24 2022-06-24 Television program recommendation method and system, smart television and medium Pending CN115278370A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210730250.5A CN115278370A (en) 2022-06-24 2022-06-24 Television program recommendation method and system, smart television and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210730250.5A CN115278370A (en) 2022-06-24 2022-06-24 Television program recommendation method and system, smart television and medium

Publications (1)

Publication Number Publication Date
CN115278370A true CN115278370A (en) 2022-11-01

Family

ID=83761062

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210730250.5A Pending CN115278370A (en) 2022-06-24 2022-06-24 Television program recommendation method and system, smart television and medium

Country Status (1)

Country Link
CN (1) CN115278370A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012222586A (en) * 2011-04-08 2012-11-12 Hitachi Consumer Electronics Co Ltd Information processing device
CN105681901A (en) * 2016-01-19 2016-06-15 天脉聚源(北京)传媒科技有限公司 Program recommending method and device
CN105898413A (en) * 2016-05-24 2016-08-24 青岛海信电器股份有限公司 Television program recommendation method, television and recommendation server
CN112784069A (en) * 2020-12-31 2021-05-11 重庆空间视创科技有限公司 IPTV content intelligent recommendation system and method
CN114501075A (en) * 2020-11-11 2022-05-13 深圳Tcl新技术有限公司 Program recommendation method, smart television and computer readable storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012222586A (en) * 2011-04-08 2012-11-12 Hitachi Consumer Electronics Co Ltd Information processing device
CN105681901A (en) * 2016-01-19 2016-06-15 天脉聚源(北京)传媒科技有限公司 Program recommending method and device
CN105898413A (en) * 2016-05-24 2016-08-24 青岛海信电器股份有限公司 Television program recommendation method, television and recommendation server
CN114501075A (en) * 2020-11-11 2022-05-13 深圳Tcl新技术有限公司 Program recommendation method, smart television and computer readable storage medium
CN112784069A (en) * 2020-12-31 2021-05-11 重庆空间视创科技有限公司 IPTV content intelligent recommendation system and method

Similar Documents

Publication Publication Date Title
US20240098221A1 (en) Method and apparatus for delivering video and video-related content at sub-asset level
EP2541963B1 (en) Method for identifying video segments and displaying contextually targeted content on a connected television
US8595781B2 (en) Methods for identifying video segments and displaying contextual targeted content on a connected television
US9510051B1 (en) Pop-ups for video suggestions based on social messages
US11636335B2 (en) System and method for content discovery
US8494346B2 (en) Identifying a performer during a playing of a video
RU2577189C2 (en) Profile based content retrieval for recommender systems
US10523987B2 (en) Systems and methods for generating aggregated media assets on related content from different sources
CN110149558A (en) A kind of video playing real-time recommendation method and system based on content recognition
US20150256885A1 (en) Method for determining content for a personal channel
CN102118639A (en) Information processing apparatus, information processing method, and program
US20140259038A1 (en) Demographic prediction channel
US10225591B2 (en) Systems and methods for creating and managing user profiles
KR20150035824A (en) Dynamic media segment pricing
US20170374426A1 (en) Binary tv
US20200221052A1 (en) Electronic apparatus and control method thereof
US20230334082A1 (en) System and method for providing additional information based on multimedia content being viewed
RU2301503C2 (en) Method for setting up a personal channel in multi-channel digital television
CN115278370A (en) Television program recommendation method and system, smart television and medium
US20120254906A1 (en) Movie recommendation system and movie recommendation method
GB2438646A (en) System for content item recommendation
EP3628123B1 (en) Systems and methods for generating aggregated media assets on related content from different sources
CN104427361B (en) Television service system and method for providing video and audio service
JP2001275056A (en) Program guide device, and device and method for inference
US20240048789A1 (en) Systems and methods for providing personalized media content to a user

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination