Personalized screensaver intelligent recommendation method and device based on user behaviors and terminal

Abstract

The invention discloses a personalized screensaver intelligent recommendation method and device based on user behaviors and a terminal. The personalized screensaver intelligent recommendation method comprises the steps of collecting and obtaining watching data of a user; performing feature extraction on the collected watching data by adopting a data mining technology to generate a user behavior tag; based on a recommendation algorithm of the user behavior tag and the content tag, screening out a content poster matched with the user behavior tag from poster information of a preset content database; when it is detected that the intelligent terminal starts the screensaver, the screened content poster is controlled to be displayed. The invention provides the system capable of intelligently recommending the personalized screensaver content based on the user behavior, the watching behavior and preference of the user can be analyzed, the related content poster is intelligently pushed, and the watching experience of the user is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent terminals, and in particular to a method, device, intelligent terminal and storage medium for intelligently recommending personalized screen savers based on user behavior. Background Art

[0002] As the core of modern home entertainment, the functions of smart TVs have expanded from single program playback to rich Internet services. However, the screen saver function of smart TVs still remains at displaying static pictures or simple animations, failing to fully utilize their intelligent potential.

[0003] Existing screensaver systems generally lack personalized content recommendations and are unable to provide customized services based on users' viewing habits and preferences. In addition, the analysis and application of user behavior data are relatively rudimentary and fail to deeply explore user needs, resulting in a disconnect between screensaver content and user interests.

[0004] Therefore, the existing technology still needs to be improved and developed. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in view of the problems and defects of the above-mentioned prior art, a method, device, intelligent terminal and storage medium for intelligently recommending personalized screensavers based on user behavior are provided. The present invention provides a system that can intelligently recommend personalized screensaver content based on user behavior, can analyze the user's viewing behavior and preferences, and intelligently push related content posters to enhance the user's viewing experience.

[0006] The technical solution adopted by the present invention to solve the problem is as follows:

[0007] A personalized screen saver intelligent recommendation method based on user behavior, comprising:

[0008] Collect and obtain users' viewing data;

[0009] Using data mining technology to extract features from the collected viewing data and generate user behavior tags;

[0010] Based on the recommendation algorithm of user behavior tags and content tags, content posters matching the user behavior tags are screened out from the poster information in the preset content database;

[0011] When it is detected that the smart terminal starts the screen saver, the screened content posters are displayed.

[0012] The method for intelligently recommending personalized screen savers based on user behavior, wherein before the step of collecting and acquiring the user's viewing data, the method comprises:

[0013] A content database containing rich program posters and related information is pre-built, and each poster is set with a corresponding poster tag.

[0014] The method for intelligently recommending personalized screen savers based on user behavior, wherein before the step of collecting and acquiring the user's viewing data, the method comprises:

[0015] The content database is regularly updated to include posters related to the latest shows and popular events.

[0016] In the method for intelligently recommending personalized screen savers based on user behavior, the step of collecting and acquiring the user's viewing data includes:

[0017] Collect users' viewing data in real time, wherein the viewing data includes viewing time, channel selection, program type, and search history.

[0018] The method for intelligently recommending personalized screen savers based on user behavior, wherein the step of extracting features from the collected viewing data using data mining technology to generate user behavior tags comprises:

[0019] Cluster analysis or classification algorithms are used to extract features from the viewing data to generate user behavior tags, where the user behavior tags include: sports enthusiasts, news followers, and children's program preference.

[0020] The method for intelligently recommending personalized screen savers based on user behavior, wherein the recommendation algorithm based on user behavior tags and content tags, the step of screening content posters matching the user behavior tags from the poster information in the preset content database, comprises:

[0021] Recommendation algorithms based on user behavior tags and content tags use collaborative filtering, content recommendation or deep learning methods; filter out content that matches user behavior tags from poster information in a preset content database;

[0022] An intelligent recommendation engine is used to further analyze the screening results and select content posters whose matching degree reaches a predetermined value.

[0023] The method for intelligently recommending personalized screen savers based on user behavior, wherein, after the step of controlling the display of the screened content posters when the screen saver is detected to be started by the smart terminal, further comprises:

[0024] Collect user feedback on content posters through remote control operation instructions, including viewing time and feedback button selection;

[0025] Based on the feedback information, the intelligent recommendation engine adjusts the recommendation algorithm and optimizes the recommended content.

[0026] A personalized screen saver intelligent recommendation device based on user behavior, wherein the device comprises:

[0027] A pre-setting module is used to pre-build a content database containing rich program posters and related information, and each poster is set with a corresponding poster tag;

[0028] Update module, used to regularly update the content database to include posters related to the latest shows and popular events

[0029] A collection and acquisition module is used to collect and acquire the viewing data of users;

[0030] A feature extraction and label generation module, used to extract features from the collected viewing data using data mining technology to generate user behavior labels;

[0031] An intelligent recommendation module is used to filter out content posters that match user behavior tags from poster information in a preset content database based on a recommendation algorithm of user behavior tags and content tags;

[0032] The screen saver control module is used to control the display of the filtered content posters when it is detected that the smart terminal starts the screen saver.

[0033] An intelligent terminal includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, including the method for executing any one of the methods described above.

[0034] A computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any one of the methods described above.

[0035] Beneficial effects of the invention: The invention provides a method, device, intelligent terminal and storage medium for intelligently recommending personalized screen savers based on user behavior, and provides a system capable of intelligently recommending personalized screen saver content based on user behavior, capable of analyzing user viewing behavior and preferences, intelligently pushing related content posters, and enhancing user viewing experience. The invention is capable of intelligently recommending personalized screen saver content based on user behavior, which is of great significance for improving user experience, enhancing user stickiness, and creating new commercial value. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a flow chart of a personalized screen saver intelligent recommendation method based on user behavior provided by an embodiment of the present invention.

[0038] Figure 2 It is a principle block diagram of an embodiment of a personalized screen saver intelligent recommendation device based on user behavior provided by the present invention.

[0039] Figure 3 It is a block diagram of the internal structure principle of the intelligent terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0041] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0042] The existing screensaver systems in the prior art generally lack personalized content recommendations and cannot provide customized services based on users' viewing habits and preferences. In addition, the analysis and application of user behavior data are relatively rudimentary, and fail to deeply explore user needs, resulting in a disconnect between screensaver content and user interests. At the same time, intelligent recommendation algorithms still face technical challenges in terms of real-time performance, accuracy, and multi-source data fusion. Therefore, developing a system that can intelligently recommend personalized screensaver content based on user behavior is of great significance for improving user experience, enhancing user stickiness, and creating new business value.

[0043] The present invention proposes a personalized screen saver intelligent recommendation method based on user behavior, which can analyze the user's viewing behavior and preferences, intelligently push related content posters, and enhance the user's viewing experience.

[0044] like Figure 1 As shown, a personalized screen saver intelligent recommendation method based on user behavior in embodiment 1 of the present invention includes the following steps:

[0045] Step S100: pre-build a content database containing rich program posters and related information, and each poster is provided with a corresponding poster tag.

[0046] In the embodiment of the present invention, a database containing rich program posters and related information needs to be pre-built during the specific implementation, and each poster is attached with a poster label, wherein the poster label includes program type, theme, popularity, etc.

[0047] Specifically, in the embodiment of the present invention, a database is created, which includes posters of different programs and important information related thereto. Each poster is not only a visual presentation of the program, but also needs to be attached with corresponding tags (such as program type, theme, popularity) to facilitate the classification and comparison of programs.

[0048] Among them, program type refers to the category of the program, such as TV series, variety shows, movies, etc. This helps users quickly find the content they are interested in.

[0049] Theme: Indicates the main content or focus of the program, such as romance, comedy, science fiction, etc. The theme can guide viewers to more accurately choose programs that suit their interests.

[0050] Popularity: This can be measured by indicators such as audience ratings, number of viewers, or social media discussion heat, reflecting the popularity of the program among the audience.

[0051] Through this structured information, it is convenient to identify the program posters that the user is interested in in the following steps. Therefore, building such a poster database containing rich information is very beneficial to improving user experience, optimizing content management and data analysis.

[0052] The benefit of this step is that, by using the tag system, users can quickly filter by program type, theme, and other conditions, greatly improving the efficiency of information retrieval. And by analyzing the relevant tags, the present invention can identify trends and understand which types or themes of programs are more popular, thereby providing data support for subsequent program production or promotion. And the present invention, by analyzing the user's viewing history, facilitates the subsequent steps to combine tags to provide personalized program recommendations, thereby enhancing user experience and satisfaction.

[0053] Step S200: regularly update the content database to include posters related to the latest programs and hot events.

[0054] In addition, in the embodiment of the present invention, the constructed content database is also updated regularly. For example, posters related to the latest programs and hot events can be collected and regularly updated to the content database.

[0055] Step S300: collecting and obtaining the viewing data of the user;

[0056] In the embodiment of the present invention, when a user turns on the TV and watches TV, the user's viewing data is collected in real time, including viewing time, channel selection, program type, search history, etc.

[0057] Among them, real-time collection of user viewing data is the key to understanding user viewing habits and preferences. This process mainly includes the following aspects:

[0058] About viewing time: It records the time a user spends on a certain program or channel, which can reflect the user's attention to the content and his or her overall interest.

[0059] About channel selection: It tracks the channels watched by users and helps understand what types of programs users like and their viewing preferences.

[0060] About program types: Specifically, it analyzes the categories of programs watched by users, such as TV series, documentaries, animations, etc., in order to identify the user's areas of interest.

[0061] About search history: Specifically, it records the search queries conducted by users, including what aspects they are interested in or what types of programs they are looking for, which helps understand users' needs and expectations.

[0062] In the embodiment of the present invention, by continuously collecting and analyzing these data, not only can the effect of content recommendation be improved, but also the needs of different user groups can be understood in a larger scope, thereby optimizing the overall content strategy and increasing user stickiness. Such a dynamic monitoring and feedback system is an effective tool for improving user experience and business growth.

[0063] Step S400: using data mining technology to extract features from the collected viewing data and generate user behavior tags;

[0064] In the embodiment of this step, data mining technology is used to extract features from the collected data to generate user behavior labels, such as "sports enthusiast", "news follower", "children's program preference", etc.

[0065] Use cluster analysis or classification algorithms to extract features from the viewing data and generate user behavior tags, which include: sports enthusiasts, news followers, and children's program preference.

[0066] In the embodiment of the present invention, the use of data mining technology is a process of extracting useful information from the viewing data. In this process, the present invention analyzes the viewing data of users, identifies some typical behavior patterns, and generates behavior tags for each user. The specific steps are as follows:

[0067] In the present invention, firstly, the collected viewing data is sorted and analyzed to identify key features such as the user's viewing time, viewing frequency, and selected program type.

[0068] Then feature extraction is performed: based on the user's viewing behavior, features are extracted. For example, if a user watches sports programs for more than 50 hours, he can be labeled as a "sports fan"; if a user continuously follows a news channel and watches related news programs, he can be labeled as a "news follower."

[0069] The extracted features are then transformed into user behavior labels that can quickly represent the user's interests and preferences. For example, users can be classified as "children's program preference" or "suspense drama fan".

[0070] For example, when an online video platform labels user behavior, here are a few specific examples:

[0071] User X: After data analysis, it is shown that user X has watched a large number of football matches and sports news in the past month, and has watched documentaries significantly less than other users, so the present invention generates a label "sports enthusiast" for him, so that the latest sports events and related sports posters can be recommended to him as screen saver posters in the following steps.

[0072] User Y: Through analysis, it is found that user Y likes to watch international news and discussion programs, and actively searches for videos related to international affairs. The present invention generates a label "news follower" for him, which is convenient for pushing the latest news programs and in-depth analysis content as TV screen saver posters.

[0073] User Z: It is observed that user Z often watches children's cartoons and educational programs, and never watches adult content. The present invention generates a label "children's program preferencer" for her, which facilitates the subsequent steps to recommend screen saver posters focusing on children's content.

[0074] It can be seen that the present invention can not only quickly identify user interests through such user behavior tag generation, but also more effectively meet the needs of individual users and improve overall user loyalty and satisfaction. Compared with traditional recommendation systems, this method is more intelligent and flexible and can respond to user changes in a timely manner.

[0075] In the present invention, accurate personalized content recommendation can be achieved by generating user behavior tags. Screen saver posters that users are most likely to be interested in can be pushed to users based on tags, thereby improving the relevance of content. When the recommended screen saver posters that users see are in line with their interests, they are more likely to feel satisfied, thereby improving the overall user experience and promoting continued use.

[0076] Step S500: Based on the recommendation algorithm of the user behavior tag and the content tag, the content posters matching the user behavior tag are screened out from the poster information in the preset content database;

[0077] In an embodiment of the present invention, a recommendation algorithm based on user behavior tags and content tags may adopt collaborative filtering, content recommendation or deep learning methods; filter out content that matches the user behavior tags from poster information in a preset content database; and use an intelligent recommendation engine to further analyze the screening results and filter out content posters whose matching degree reaches a predetermined value.

[0078] In this step, the embodiment combines the user's interest preferences with the content features for deep matching, so as to push the most relevant content posters to the user, thereby improving the user experience.

[0079] Specifically, regarding the use of user behavior tags, the recommendation algorithm in the present invention first refers to the user's behavior tags, that is, the tags generated by previous data analysis (such as "sports enthusiast", "TV drama fan", "children's program preference", etc.). These tags reflect the user's interests and preferences and are an important basis for model recommendations.

[0080] Regarding the definition of content tags, in a specific embodiment of the present invention, in the content database, each program or movie is assigned a series of content tags, such as "action", "comedy", "children", "documentary", "sports", etc. These tags describe the characteristics of the content, so that the algorithm can identify potential associations with user behavior tags.

[0081] The implementation of the recommendation algorithm in the present invention is as follows: first, tag matching. The recommendation algorithm used in the present invention will match the user's behavior tag with the content tag of the poster. For example, if the user's tag is "sports enthusiast", the embodiment of the present invention will search the database for all the content containing the tag "sports" for matching.

[0082] In the embodiment of the present invention, after the matching is completed, the program contents meeting the conditions are screened out and their content posters are automatically extracted. These content posters are used to display recommended contents to users.

[0083] Then, the present invention organizes the screened content posters, generates a recommendation list and pushes them as screen saver pictures of the user's television.

[0084] For example, when using the recommendation algorithm of the embodiment of the present invention, the following are several specific examples:

[0085] User A: User A's behavior tag is identified as "action movie lover". The present invention searches its content database and finds multiple movies with the "action" tag, and selects posters of the "Wolf Warrior" series and the "Fast and Furious" series, and recommends these content posters to User A as screen saver posters.

[0086] User B: User B is marked as a "children's program preferencer". The recommendation system selects content with the "children" label from the database, including content posters of "Pigsy X" and "Sponge X", which meet the preferences of user B.

[0087] It can be seen that the present invention can quickly connect the user's interest screen saver poster with a rich content library through this process, making the user experience more pleasant.

[0088] The present invention combines user behavior tags with content tags to recommend content posters that are more in line with the user's interests, making the recommendation results more accurate and in line with user needs. When users see content posters that are highly relevant to their interests, their willingness to watch will naturally increase, thereby increasing user participation and activity. In addition, users do not need to search for programs of interest in a large amount of content. The present invention will automatically select the most relevant content posters for them, significantly improving user efficiency.

[0089] Step S600: When it is detected that the smart terminal starts the screen saver, control the display of the filtered content posters.

[0090] In the embodiment of the present invention, when it is detected that a smart terminal such as a smart TV starts a screen saver, controlling the display of the selected content poster is a function of the smart terminal (such as a smart TV, a smart projector, etc.) when the user is idle. This step is intended to utilize the screen saver state to efficiently display content related to user preferences, thereby increasing the user's willingness to subscribe to and watch platform content.

[0091] The smart terminal example of the present invention, such as a smart TV, can monitor the current usage status in real time through a built-in sensor or system monitoring function. When the user does not operate for a certain period of time (such as no input on the remote control or no change on the display), the TV terminal will automatically switch to the screen saver state.

[0092] In the embodiment of the present invention, once the screen saver state is detected, the recommendation engine will be automatically activated. This period of time just provides a window for the platform to display selected content posters to users.

[0093] The present invention selects content posters that are highly relevant to user interests based on previously generated user behavior tags and content tags. This stage of screening takes into account factors such as the user's past viewing history, preference tags, and popular trends. The content of the posters usually includes new episodes online, upcoming popular movies, or recommended programs that users may be interested in, ensuring that each poster can attract the user's attention.

[0094] Then, in the terminal TV screen saver state, the present invention will cyclically display these selected content posters. The content posters can include information such as program introduction, rating, viewing time, etc. to increase user interest. This display form is not only beautiful, but also allows users to subtly access recommended content during idle time.

[0095] For example, if a smart TV has a screen saver enabled when the user has not operated it for a long time, the present invention may perform the following operations:

[0096] User X: User X was identified as a "science fiction movie lover" in the screen saver state. In this state, the screen saver of the television of the present invention will actively display related science fiction movie posters, such as "Blade Runner" and "Interstellar", as well as the ratings, introductions and other information of these films. As users see these posters, they may recall the pleasant experience of watching the movies before, and curiosity will further prompt users to click to watch.

[0097] User Y: User Y's behavior tag shows that she likes "family comedy". During the screen saver, the TV may display some popular family comedy series content posters, such as "Friends X" and "Modern Family X". The content posters will be printed with recommendations and information such as "New Season Returns" to attract users to quickly play them in their spare time.

[0098] User Z: User Z has always liked watching "documentaries". In screen saver mode, the smart terminal may play documentary content posters related to the environment and history, combined with the ratings or hot comments mentioned above, which not only helps users find content posters of interest, but also subtly increases the popularity and exposure of the content.

[0099] It can be seen that through this intelligent terminal screen saver display method, the present invention can effectively utilize the user's idle time, reach the target users and recommend relevant content, improve user experience and audience retention. In this process, a perfect combination of personalized recommendation and functionality is achieved, thereby optimizing the relationship between users and content platforms. In addition, the present invention has the following benefits:

[0100] 1) It can improve content exposure: by displaying content posters in screen saver mode, the content can get additional exposure opportunities. Users can also receive content recommendations from the platform without actively watching, thereby potentially increasing the audience's click-through rate.

[0101] 2) It can enhance user attraction: Visual poster display is eye-catching and can effectively attract users' attention. When users see the programs they are interested in, it may stimulate their desire to watch and reduce the loss rate of content.

[0102] 3) It can optimize the user experience: users are pushed relevant content when they are idle, which allows them to easily find new programs when they want to watch. In this way, the overall viewing experience provided by the platform will be smoother and more enjoyable.

[0103] In another embodiment, the method for intelligently recommending personalized screen savers based on user behavior further includes the steps of:

[0104] S601. Collect and obtain user feedback information on content posters through operation instructions of the remote control, including viewing time and selection of feedback buttons; based on the feedback information, the intelligent recommendation engine adjusts the recommendation algorithm and optimizes the recommended content.

[0105] That is, in the embodiment of the present invention, through the remote control, the user can use a specific button to give feedback while viewing the content poster. For example, the user can choose "like", "dislike" or "neutral" to express the attitude towards the content.

[0106] In addition, the present invention can also record the time the user spends viewing the content poster. This means that the present invention not only focuses on the user's choice, but also focuses on the user's actual viewing behavior of the content. These data can provide more comprehensive user preference information.

[0107] The collected viewing time and feedback button selections can then be integrated and transmitted to the intelligent recommendation engine. The engine analyzes this data to identify which content is popular and which content fails to arouse the user's interest. Based on these analyses, the present invention can find out the content type, style, theme, etc. preferred by the user, so as to understand the user's needs more accurately.

[0108] In addition, the intelligent recommendation engine of the present invention can adjust the recommendation algorithm in real time based on user feedback information, which may include recalculating the user's interest model, updating the content rating, and regenerating the recommendation list according to the user's preferences.

[0109] In addition, the recommendation of the present invention can also identify the preferences of similar users and use "group intelligence" to further optimize the recommended content.

[0110] Then, users will see content recommendations that are more in line with their interests and preferences in future uses. This personalized recommendation can enhance the user experience, increase user satisfaction, and promote longer use.

[0111] It can be seen that users of the present invention will experience more personalized content recommendations, and can more easily find their favorite program and movie content posters, thereby improving usage stickiness. In addition, users like to see content posters related to their interests, and such highly matched recommendations will help improve overall satisfaction and further promote user loyalty.

[0112] The second embodiment provides a personalized screen saver intelligent recommendation method based on user behavior, including the following steps:

[0113] Step S11: Initialize the system;

[0114] In the embodiment of the present invention, when the smart TV system is started, the relevant modules of the screen saver recommendation system are initialized.

[0115] Step S12: user behavior data collection;

[0116] When users watch TV, the user behavior analysis module can collect their viewing data, including viewing time, channel selection, program type, search history, etc.

[0117] Step S13: generating behavior labels;

[0118] Based on the collected data, cluster analysis or classification algorithms are used to generate user behavior labels, such as "sports enthusiast", "news follower", "children's program preference", etc.

[0119] Step S14: content screening and recommendation;

[0120] In the embodiment of the present invention, the content matching the user behavior tag can be screened according to the poster information in the content database, and the screening result can be further analyzed by the intelligent recommendation engine to select the most appropriate content poster for recommendation.

[0121] Step S15: displaying a screen saver poster;

[0122] In the embodiment of the present invention, when the television enters the screen saver state, the screen saver display module displays the recommended poster and waits for user feedback.

[0123] For example, when the user is not watching TV, the screen saver display module will display the posters selected by the intelligent recommendation engine.

[0124] Step S16: user interaction and feedback collection;

[0125] That is, in the present invention, the user can operate the poster through the remote control, such as selecting "like" or "learn more". The user feedback collection module collects and records the user's operation feedback in real time; that is, it can collect the user's feedback on the displayed poster, including the viewing time, the selection of the feedback button, etc. The present invention can also analyze the user feedback, evaluate the recommendation effect, and provide an adjustment basis for the recommendation algorithm.

[0126] Step S17: Recommendation algorithm optimization;

[0127] Based on user feedback, the intelligent recommendation engine adjusts the recommendation algorithm and optimizes the recommendation effect.

[0128] Step S18: content database update and maintenance;

[0129] Update the content database regularly to ensure the timeliness and diversity of the poster content. Maintain and upgrade the system software to adapt to new user needs and technological developments. Of course, the embodiment of the present invention can also synchronize data with other smart TV systems or other devices in the home network to update the content database, allowing third-party applications or services to be integrated with the smart screen saver system through the system interface;

[0130] Step S19: data analysis and reporting;

[0131] Regularly conduct in-depth analysis of collected user behavior data and feedback, generate reports, and provide reference for content providers and advertisers.

[0132] Exemplary Devices

[0133] like Figure 2 As shown, an embodiment of the present invention provides a personalized screen saver intelligent recommendation device based on user behavior, the device comprising:

[0134] The pre-setting module 310 is used to pre-build a content database containing rich program posters and related information, and each poster is provided with a corresponding poster tag;

[0135] An updating module 320, for regularly updating the content database to include posters related to the latest programs and popular events;

[0136] The collection and acquisition module 330 is used to collect and acquire the viewing data of the user;

[0137] A feature extraction and label generation module 340 is used to extract features from the collected viewing data and generate user behavior labels using data mining technology;

[0138] The intelligent recommendation module 350 is used to filter out content posters matching the user behavior tags from the poster information in the preset content database based on the recommendation algorithm of the user behavior tags and the content tags;

[0139] The screen saver control module 360 ​​is used to control the display of the screened content posters when it is detected that the smart terminal starts the screen saver, as described above in detail.

[0140] Based on the above embodiments, the present invention further provides an intelligent terminal, whose principle block diagram can be shown as follows: Figure 3 As shown. The intelligent terminal includes a processor, a memory, a network interface, a display screen, and a database connected through a system bus. Among them, the processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the intelligent terminal is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a personalized screen saver intelligent recommendation method based on user behavior is implemented. The database of the intelligent terminal is used to store a personalized screen saver intelligent recommendation program based on user behavior.

[0141] Those skilled in the art will understand that Figure 3 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the smart terminal to which the scheme of the present invention is applied. The specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] In one embodiment, a smart terminal is provided, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include instructions for performing the following operations:

[0143] Collect and obtain users' viewing data;

[0144] Using data mining technology to extract features from the collected viewing data and generate user behavior tags;

[0145] Based on the recommendation algorithm of user behavior tags and content tags, content posters matching the user behavior tags are screened out from the poster information in the preset content database;

[0146] When it is detected that the smart terminal starts the screen saver, the screened content posters are displayed, as described above.

[0147] The step of collecting and obtaining the viewing data of the user includes:

[0148] A content database containing rich program posters and related information is pre-built, and each poster is set with a corresponding poster tag.

[0149] The step of collecting and obtaining the viewing data of the user includes:

[0150] The content database is regularly updated to include posters related to the latest shows and popular events.

[0151] The step of collecting and obtaining the user's viewing data includes:

[0152] Collect users' viewing data in real time, wherein the viewing data includes viewing time, channel selection, program type, and search history.

[0153] The step of using data mining technology to extract features from the collected viewing data and generate user behavior tags includes:

[0154] Cluster analysis or classification algorithms are used to extract features from the viewing data to generate user behavior tags, where the user behavior tags include: sports enthusiasts, news followers, and children's program preference.

[0155] The recommendation algorithm based on user behavior tags and content tags, wherein the step of screening content posters matching the user behavior tags from the poster information in the preset content database comprises:

[0156] Recommendation algorithms based on user behavior tags and content tags use collaborative filtering, content recommendation or deep learning methods; filter out content that matches user behavior tags from poster information in a preset content database;

[0157] An intelligent recommendation engine is used to further analyze the screening results and select content posters whose matching degree reaches a predetermined value.

[0158] Wherein, after the step of controlling the display of the screened content posters when detecting that the smart terminal starts the screen saver, the method further includes:

[0159] Collect user feedback on content posters through remote control operation instructions, including viewing time and feedback button selection;

[0160] Based on the feedback information, the intelligent recommendation engine adjusts the recommendation algorithm and optimizes the recommended content, as described above.

[0161] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0162] In summary, the present invention provides a method, device, intelligent terminal and storage medium for intelligently recommending personalized screen savers based on user behavior, and provides a system capable of intelligently recommending personalized screen saver content based on user behavior, capable of analyzing user viewing behavior and preferences, intelligently pushing related content posters, and enhancing user viewing experience. The system capable of intelligently recommending personalized screen saver content based on user behavior of the present invention is of great significance for improving user experience, enhancing user stickiness, and creating new commercial value.

Claims

1. A personalized screen saver intelligent recommendation method based on user behavior, characterized in that: include: Collect and obtain users' viewing data; Using data mining technology to extract features from the collected viewing data and generate user behavior tags; Based on the recommendation algorithm of user behavior tags and content tags, content posters matching the user behavior tags are screened out from the poster information in the preset content database; When it is detected that the smart terminal starts the screen saver, the screened content posters are displayed.

2. The personalized screen saver intelligent recommendation method based on user behavior according to claim 1, characterized in that: The step of collecting and obtaining the user's viewing data includes: A content database containing rich program posters and related information is pre-built, and each poster is set with a corresponding poster tag.

3. The personalized screen saver intelligent recommendation method based on user behavior according to claim 2, characterized in that: The step of collecting and obtaining the user's viewing data includes: The content database is regularly updated to include posters related to the latest shows and popular events.

4. The personalized screen saver intelligent recommendation method based on user behavior according to claim 1, characterized in that: The step of collecting and obtaining the user's viewing data comprises: Collect users' viewing data in real time, wherein the viewing data includes viewing time, channel selection, program type, and search history.

5. The personalized screen saver intelligent recommendation method based on user behavior according to claim 1, characterized in that: The step of using data mining technology to extract features from the collected viewing data and generate user behavior tags includes: Cluster analysis or classification algorithms are used to extract features from the viewing data to generate user behavior tags, where the user behavior tags include: sports enthusiasts, news followers, and children's program preference.

6. The personalized screen saver intelligent recommendation method based on user behavior according to claim 1, characterized in that: The recommendation algorithm based on user behavior tags and content tags, the step of screening content posters matching the user behavior tags from the poster information in the preset content database comprises: Recommendation algorithms based on user behavior tags and content tags use collaborative filtering, content recommendation or deep learning methods; filter out content that matches user behavior tags from poster information in a preset content database; An intelligent recommendation engine is used to further analyze the screening results and select content posters whose matching degree reaches a predetermined value.

7. The personalized screen saver intelligent recommendation method based on user behavior according to claim 1, characterized in that: After the step of controlling the display of the screened content posters when it is detected that the smart terminal starts the screen saver, the following step further comprises: Collect user feedback on content posters through remote control operation instructions, including viewing time and feedback button selection; Based on the feedback information, the intelligent recommendation engine adjusts the recommendation algorithm and optimizes the recommended content.

8. A personalized screen saver intelligent recommendation device based on user behavior, characterized in that: The device comprises: A pre-setting module is used to pre-build a content database containing rich program posters and related information, and each poster is set with a corresponding poster tag; An update module for regularly updating the content database to include posters related to the latest programs and popular events; A collection and acquisition module is used to collect and acquire the viewing data of users; A feature extraction and label generation module, used to extract features from the collected viewing data using data mining technology to generate user behavior labels; An intelligent recommendation module is used to filter out content posters that match user behavior tags from poster information in a preset content database based on a recommendation algorithm of user behavior tags and content tags; The screen saver control module is used to control the display of the filtered content posters when it is detected that the smart terminal starts the screen saver.

9. An intelligent terminal, characterized in that: The device comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include being used to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method as described in any one of claims 1 to 7.

Images