Content recommendation method and device, storage medium and electronic device

Abstract

The invention discloses a content recommendation method and device, a storage medium and an electronic device, and relates to the technical field of smart home, and the content recommendation method comprises the steps: obtaining initial portrait data of a target object and target behavior data of the target object in a target application; sending the initial portrait data and the target behavior data to a target artificial intelligence model; first recommendation content generated by the target artificial intelligence model is obtained, the target application is indicated to display the first recommendation content, and the first recommendation content is the recommendation content generated by the target artificial intelligence model according to first portrait data. The first portrait data is portrait data generated by the target artificial intelligence model according to the target behavior data and the initial portrait data. By adopting the technical scheme, the problem that the quality of the recommended content is poor is solved.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and more specifically, to a content recommendation method and device, a storage medium, and an electronic device. Background Art

[0002] With the development of the Internet and mobile technology, personalized content has become an important feature of digital products and services. Personalized content refers to providing users with customized information and services based on their personal preferences, interests, and behavioral habits, which can improve user experience, increase user stickiness, and promote user participation in product use.

[0003] In related technologies, personalized algorithms are usually used to recommend personalized content. However, the calculation method of the personalized algorithm is relatively simple, and the factors considered are relatively single. It is easy to fall into the dilemma of "information cocoon" and "over-recommendation", and it is impossible to truly understand the real needs and interests of users.

[0004] With regard to the problem of poor quality of recommended content in related technologies, no effective solution has been proposed so far.

[0005] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0006] The embodiments of the present application provide a content recommendation method and device, a storage medium, and an electronic device to at least solve the problem of poor quality of recommended content.

[0007] According to one aspect of an embodiment of the present application, a content recommendation method is provided, including: obtaining initial portrait data of a target object and target behavior data of the target object in a target application; sending the initial portrait data and the target behavior data to a target artificial intelligence model; obtaining first recommended content generated by the target artificial intelligence model, and instructing the target application to display the first recommended content, wherein the first recommended content is the recommended content generated by the target artificial intelligence model based on the first portrait data, and the first portrait data is portrait data generated by the target artificial intelligence model based on the target behavior data and the initial portrait data.

[0008] In an exemplary embodiment, before obtaining the first recommended content generated by the target artificial intelligence model, the method further includes: after sending the initial portrait data and the target behavior data to the target artificial intelligence model, obtaining the first portrait data generated by the target artificial intelligence model; and when the first portrait data satisfies a first preset condition, instructing the target artificial intelligence model to generate recommended content based on the first portrait data.

[0009] In an exemplary embodiment, the method also includes: when the first portrait data does not meet the first preset condition, adjusting the first portrait data to obtain second portrait data that meets the preset condition; instructing the target artificial intelligence model to generate recommended content based on the second portrait data; obtaining the second recommended content generated by the target artificial intelligence model based on the second portrait data, and instructing the target application to display the second recommended content.

[0010] In an exemplary embodiment, the method also includes: when the first portrait data does not meet the first preset condition, adjusting the first parameter of the target artificial intelligence model to obtain a first artificial intelligence model, wherein when the first parameter of the target artificial intelligence model is adjusted, the strategy for generating portrait data by the target artificial intelligence model changes; obtaining third portrait data generated by the first artificial intelligence model based on the target behavior data and the initial portrait data; when the third portrait data meets the first preset condition, instructing the target artificial intelligence model to generate recommended content based on the third portrait data; obtaining third recommended content generated by the target artificial intelligence model based on the third portrait data, and instructing the target application to display the third recommended content.

[0011] In an exemplary embodiment, instructing the target application to display the first recommended content includes: when the first recommended content includes multiple sub-recommended content, determining the display order of the multiple sub-recommended content according to a preset sorting rule; and instructing the target application to display the first recommended content according to the display order.

[0012] In an exemplary embodiment, after instructing the target application to display the first recommended content, the method further includes: obtaining feedback data sent by the target application, wherein the feedback data is used to indicate the target object's satisfaction with the first recommended content; sending the feedback data to the target artificial intelligence model; obtaining fourth recommended content generated by the target artificial intelligence model, and instructing the target application to display the fourth recommended content, wherein the fourth recommended content is recommended content generated by the target artificial intelligence model based on fourth portrait data, and the fourth portrait data is portrait data generated by the target artificial intelligence model based on the feedback data and the first portrait data.

[0013] In an exemplary embodiment, after obtaining the first recommended content generated by the target artificial intelligence model, the method also includes: determining whether the first recommended content meets a second preset condition, and if it is determined that the first recommended content meets the second preset condition, instructing the target application to display the first recommended content; if the first recommended content does not meet the second preset condition, adjusting the second parameter of the target artificial intelligence model to obtain a second artificial intelligence model, wherein when the second parameter of the target artificial intelligence model is adjusted, the strategy for generating recommended content by the target artificial intelligence model changes; obtaining the fifth recommended content generated by the second artificial intelligence model, and if the fifth recommended content meets the second preset condition, instructing the target application to display the fifth recommended content, wherein the fifth recommended content is the recommended content generated by the second artificial intelligence model based on the first portrait data.

[0014] According to another aspect of an embodiment of the present application, a content recommendation device is also provided, including: an acquisition module for acquiring initial portrait data of a target object and target behavior data of the target object in a target application; a sending module for sending the initial portrait data and the target behavior data to a target artificial intelligence model; an indication module for acquiring first recommended content generated by the target artificial intelligence model, and instructing the target application to display the first recommended content, wherein the first recommended content is the recommended content generated by the target artificial intelligence model based on the first portrait data, and the first portrait data is the portrait data generated by the target artificial intelligence model based on the target behavior data and the initial portrait data.

[0015] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned content recommendation method when running.

[0016] According to another aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the content recommendation method through the computer program.

[0017] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and the computer program performs the above-mentioned content recommendation method when executed by a processor.

[0018] Through this application, the initial portrait data and target behavior data of the target object are sent to the artificial intelligence model to obtain the recommended content generated by the artificial intelligence model, and the target application is instructed to display the generated recommended content. Since the artificial intelligence model uses both the initial portrait data and target behavior data of the target object to generate recommended content, the recommended content is more personalized, thereby solving the problem of poor quality of recommended content. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] In order to more clearly illustrate the embodiments of the present application 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 is a schematic diagram of a hardware environment of a content recommendation method according to an embodiment of the present application;

[0022] Figure 2 is a flow chart of a content recommendation method according to an embodiment of the present application;

[0023] Figure 3 is a flow chart of an optional server performing content recommendation according to an embodiment of the present application;

[0024] Figure 4 is a timing diagram of content recommendation by an optional server according to an embodiment of the present application;

[0025] Figure 5 is a structural block diagram of a content recommendation device according to an embodiment of the present application;

[0026] Figure 6 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] According to one aspect of the embodiments of the present application, a content recommendation method is provided. The content recommendation method is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (IntelligenceHouse) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the above content recommendation method can be applied to Figure 1 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0030] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0031] In order to solve the above problems, a content recommendation method is provided in this embodiment, including but not limited to being applied in the whole house intelligent digital control application scenario. Figure 2 : is a flow chart of a content recommendation method according to an embodiment of the present application, the process includes the following steps S202-S206:

[0032] Step S202: Acquire initial portrait data of the target object and target behavior data of the target object in the target application;

[0033] Optionally, the initial portrait data of the target object includes but is not limited to: the target object's age, gender, occupation, etc.; the target behavior data of the target object includes but is not limited to data on the target object's browsing, clicking, purchasing, etc. behaviors in the target application.

[0034] It should be noted that by collecting the initial portrait data of the target object and the behavioral data displayed by the target object in the target application, we can obtain comprehensive information about the target object, so as to better understand the needs, preferences and behavioral characteristics of the target object, and then more accurately recommend personalized content to the target object.

[0035] Step S204: sending the initial portrait data and the target behavior data to a target artificial intelligence model;

[0036] Optionally, the target artificial intelligence model is a Gemini model.

[0037] Optionally, the general artificial intelligence model is trained by using a supervised learning mechanism to obtain a target artificial intelligence model.

[0038] Step S206: Obtain the first recommended content generated by the target artificial intelligence model, and instruct the target application to display the first recommended content, wherein the first recommended content is the recommended content generated by the target artificial intelligence model based on the first portrait data, and the first portrait data is the portrait data generated by the target artificial intelligence model based on the target behavior data and the initial portrait data.

[0039] Optionally, when the target artificial intelligence model is a Gemini model, the Gemini model will preprocess the initial portrait data and target behavior data (such as data cleaning and feature extraction) to convert the data format of the initial portrait data and the target behavior data into a format that can be input into the model. The Gemini model will then extract relevant feature information from the initial portrait data and the target behavior data, such as the interests and hobbies, historical behaviors, etc. of the target object, to generate first portrait data, thereby generating corresponding recommended content based on the first portrait data.

[0040] Optionally, the form of the recommended content includes but is not limited to: text, image, video, and the best presentation form is selected according to the preferences of the target object.

[0041] In the above steps, the initial portrait data and target behavior data of the target object are sent to the artificial intelligence model to obtain the recommended content generated by the artificial intelligence model, and the target application is instructed to display the generated recommended content. Since the artificial intelligence model uses both the initial portrait data and target behavior data of the target object to generate recommended content, the recommended content is more personalized, thereby solving the problem of poor quality of recommended content.

[0042] In an exemplary embodiment, before the above step S206, the method further includes the following steps S11-S12:

[0043] Step S11: after sending the initial portrait data and the target behavior data to the target artificial intelligence model, obtaining the first portrait data generated by the target artificial intelligence model;

[0044] Step S12: When the first portrait data meets the first preset condition, instruct the target artificial intelligence model to generate recommended content based on the first portrait data.

[0045] Optionally, after the artificial intelligence model generates the first portrait data, the first portrait data is displayed on an indication interface, and a first instruction is obtained through the indication interface, wherein the first instruction is an instruction issued on the instruction interface by the target object through the first portrait data displayed on the indication interface, and the first instruction is used to indicate whether the first portrait data meets a first preset condition.

[0046] Optionally, the first preset condition is that the correlation between the first portrait data, the initial portrait data and the target behavior data is greater than or equal to a first preset threshold.

[0047] Optionally, a correlation algorithm is used to calculate the correlation between the first portrait data, the initial portrait data and the target behavior data. When the correlation is greater than or equal to a first preset threshold, the first portrait data meets the first preset condition; when the correlation is less than the first preset threshold, the first portrait data does not meet the first preset condition.

[0048] Optionally, the association algorithm includes but is not limited to: cosine similarity, Euclidean distance, Pearson correlation coefficient, Jaccard similarity coefficient, etc.

[0049] It should be noted that, when the first portrait data meets the first preset condition, the above step S206 is executed, and when the first portrait data does not meet the first preset condition, the following steps S21-S23 and / or steps S31-S34 are executed.

[0050] In an exemplary embodiment, the method further comprises the following steps S21-S23:

[0051] Step S21: When the first portrait data does not satisfy the first preset condition, adjusting the first portrait data to obtain second portrait data satisfying the preset condition;

[0052] Optionally, the staff adjusts the first portrait data according to preset adjustment rules.

[0053] It should be noted that the failure of the first portrait data to meet the first preset condition indicates that the first portrait data does not reflect the expected degree of personalization, and thus the first portrait data needs to be adjusted. Compared with the first portrait data, the second portrait data is more in line with the portrait and behavior of the target object, making the recommended content generated by the target artificial intelligence model more personalized.

[0054] Step S22: instructing the target artificial intelligence model to generate recommended content according to the second portrait data;

[0055] Step S23: Obtain the second recommended content generated by the target artificial intelligence model based on the second portrait data, and instruct the target application to display the second recommended content.

[0056] In an exemplary embodiment, the method further comprises the following steps S31-S34:

[0057] Step S31: When the first portrait data does not satisfy the first preset condition, adjusting the first parameter of the target artificial intelligence model to obtain a first artificial intelligence model, wherein when the first parameter of the target artificial intelligence model is adjusted, the strategy of generating portrait data by the target artificial intelligence model changes;

[0058] Optionally, the strategies for the target artificial intelligence model to generate portrait data include but are not limited to: generative adversarial networks, variational autoencoders, autoregressive models, etc. When the first parameter of the target artificial intelligence model is adjusted, the target artificial intelligence model will change from the current strategy to other optional strategies.

[0059] Step S32: obtaining third portrait data generated by the first artificial intelligence model according to the target behavior data and the initial portrait data;

[0060] Step S33: when the third portrait data satisfies the first preset condition, instructing the target artificial intelligence model to generate recommended content according to the third portrait data;

[0061] Step S34: Obtain the third recommended content generated by the target artificial intelligence model based on the third portrait data, and instruct the target application to display the third recommended content.

[0062] In an exemplary embodiment, the above step S206 can be implemented by the following steps S41-S42:

[0063] Step S41: when the first recommended content includes a plurality of sub-recommended contents, determining a display order of the plurality of sub-recommended contents according to a preset sorting rule;

[0064] Optionally, the multiple sub-recommendation contents may be sorted based on their heat and popularity, or based on their real-time generation time, or based on the relevance of the sub-recommendation contents to the portrait and behavior of the target object, thereby making the first recommended content more personalized.

[0065] Step S42: instructing the target application to display the first recommended content according to the display order.

[0066] In an exemplary embodiment, the method further includes: when the multiple sub-recommended contents all satisfy the second preset condition, instructing the target application to display the first recommended content according to the display order; when there are some sub-recommended contents in the multiple sub-recommended contents that do not satisfy the first recommended content, instructing the target application to display all sub-recommended contents in the first recommended content except the some sub-recommended contents according to the display order.

[0067] In an exemplary embodiment, when the proportion of some sub-recommended contents to the plurality of sub-recommended contents is greater than a second preset threshold, the plurality of sub-recommended contents are not displayed.

[0068] In an example embodiment, when the proportion of some sub-recommended contents to the multiple sub-recommended contents is greater than a second preset threshold, the second parameter of the target artificial intelligence model is adjusted to obtain a second artificial intelligence model.

[0069] In an exemplary embodiment, after instructing the target application to display the first recommended content, the method further includes the following steps S51-S53:

[0070] Step S51: Acquire feedback data sent by the target application, wherein the feedback data is used to indicate the target object's satisfaction with the first recommended content;

[0071] Step S52: sending the feedback data to the target artificial intelligence model;

[0072] Step S53: Obtain the fourth recommended content generated by the target artificial intelligence model, and instruct the target application to display the fourth recommended content, wherein the fourth recommended content is the recommended content generated by the target artificial intelligence model based on the fourth portrait data, and the fourth portrait data is the portrait data generated by the target artificial intelligence model based on the feedback data and the first portrait data.

[0073] Optionally, through the above steps S51-S53, the target artificial intelligence model can be adjusted in real time according to the target object's satisfaction with the first recommended content, making small adjustments when the satisfaction is high and making large adjustments when the satisfaction is low, thereby generating more personalized content for the target object.

[0074] In an exemplary embodiment, after obtaining the first recommended content generated by the target artificial intelligence model, the method further includes the following steps S61-S63:

[0075] Step S61: determining whether the first recommended content meets a second preset condition, and if it is determined that the first recommended content meets the second preset condition, instructing the target application to display the first recommended content;

[0076] Optionally, after the artificial intelligence model generates the first recommended content, the first recommended content is displayed on the indication interface, and a second instruction is obtained through the indication interface, wherein the second instruction is an instruction issued on the instruction interface by the target object through the indication interface of the first recommended content displayed by the target object through the indication interface, and the second instruction is used to indicate whether the first recommended content meets a second preset condition.

[0077] Optionally, the second preset condition is that the proportion of hot news content in the first recommended content exceeds 20%, and the correlation with the historical behavior data of the target object is greater than 80%.

[0078] It should be noted that the second preset condition is to judge the first recommended content. When the first recommended content meets the second preset condition, it means that the first recommended content is highly personalized, so that the target application can be instructed to recommend the first recommended content to the target object.

[0079] Step S62: When the first recommended content does not meet the second preset condition, adjusting the second parameter of the target artificial intelligence model to obtain a second artificial intelligence model, wherein when the second parameter of the target artificial intelligence model is adjusted, the strategy of the target artificial intelligence model to generate recommended content changes;

[0080] Step S63: Obtain the fifth recommended content generated by the second artificial intelligence model, and if the fifth recommended content meets the second preset condition, instruct the target application to display the fifth recommended content, wherein the fifth recommended content is the recommended content generated by the second artificial intelligence model based on the first portrait data.

[0081] Optionally, the execution entity of the above steps is a server.

[0082] Obviously, the embodiments described above are only some embodiments of the present application, not all embodiments. In order to better understand the above method, the above process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application. Optionally:

[0083] Figure 3 The figure shows a process of recommendation by a server, specifically:

[0084] 1. The system starts and initializes;

[0085] (1) System startup, loading the Gemini model and necessary configuration;

[0086] (2) Initialize the user portrait data of the user in the idle state and prepare to receive the user's first input.

[0087] 2. Collect user behavior data;

[0088] (1) Recording user behavior on the platform (e.g. number of clicks, categories of pages browsed, page dwell time, search history, etc.);

[0089] (2) Collect external data such as social media and purchase history to further enrich user portraits and obtain target behavior data.

[0090] 3. Use the user's initial portrait data and target behavior data to build and update;

[0091] (1) Use the Gemini model to analyze the collected user data and gain a deeper understanding of user interests, preferences, and potential needs;

[0092] (2) Dynamically update user portraits and continuously refine user models based on new behavioral data.

[0093] 4. Generate personalized content;

[0094] (1) Based on the latest user portrait data (i.e., the first portrait data mentioned above), the Gemini model is called to generate personalized content proposals (i.e., the first recommended content mentioned above);

[0095] (2) Content can be in the form of text, images, videos, etc. The best format is selected based on user preferences and scenarios.

[0096] 5. Filter and sort the generated recommended content;

[0097] (1) Apply diversity and novelty algorithms to select the most attractive content that meets user preferences from the generated content;

[0098] (2) Sort the selected content to ensure that the display order maximizes user satisfaction.

[0099] 6. Display and interaction of recommended content;

[0100] (1) Display personalized content to users and provide feedback (such as liking, disliking, commenting, sharing, etc.);

[0101] (2) Monitor the interaction between users and content in real time and collect feedback data.

[0102] 7. Feedback loop and optimization;

[0103] (1) Analyze users’ immediate feedback on content and adjust user portrait data;

[0104] (2) Feedback data is used to train the Gemini model and optimize future content generation and recommendation strategies.

[0105] 8. Security and privacy protection;

[0106] Ensure that all user data processing complies with the privacy policy and implement measures such as data anonymization and encrypted storage.

[0107] Figure 4 The timing of the server performing the above recommendation process is shown in detail:

[0108] 1. System startup and initialization;

[0109] 2. The user logs in to / uses the target application, triggering the collection of behavioral data;

[0110] 2.1 The target application uploads user behavior data to the backend server in real time;

[0111] 2.1.1 The server transfers the user's behavior data to the large model (Gemini model);

[0112] 2.1.1.1 The large model updates the user portrait data based on the latest input data;

[0113] 2.1.1.2 The large model updates the user portrait and feeds it back to the backend server;

[0114] 3. The big model generates personalized content based on user portraits;

[0115] 4. The big model filters and sorts the generated content;

[0116] 5. The large model generates recommended content and sends it to the backend server;

[0117] 5.1 The backend server pushes the recommended content to the application and instructs it to display it;

[0118] 5.2 The target application displays personalized content to users;

[0119] 6. Users provide interactive feedback on recommended content;

[0120] 6.1 The target application uploads the feedback data to the backend server in real time;

[0121] 6.1.1 The backend server updates the user portrait based on the feedback data;

[0122] 6.1.1.1 Adjust the parameters of the large model;

[0123] 6.1.1.2 The big model generates the latest personalized content based on the latest user portraits;

[0124] 7. The large model sends the latest generated recommendations to the backend server;

[0125] 7.1 The server pushes the latest recommended content to the application and instructs it to display it;

[0126] 7.2 The target application displays the latest personalized content to the user.

[0127] It should be noted that this application ensures the diversity and novelty of the recommended content while maintaining a high degree of personalization, meets the wide range of needs of users, and promotes the innovative application of big model technology in the field of personalized services.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0129] In this embodiment, a content recommendation device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0130] Figure 5 is a structural block diagram of a content recommendation device according to an embodiment of the present application, the device comprising:

[0131] An acquisition module 52, used to acquire initial portrait data of a target object and target behavior data of the target object in a target application;

[0132] A sending module 54, used to send the initial portrait data and the target behavior data to a target artificial intelligence model;

[0133] The indication module 56 is used to obtain the first recommended content generated by the target artificial intelligence model and instruct the target application to display the first recommended content, wherein the first recommended content is the recommended content generated by the target artificial intelligence model based on the first portrait data, and the first portrait data is the portrait data generated by the target artificial intelligence model based on the target behavior data and the initial portrait data.

[0134] The above device sends the initial portrait data and target behavior data of the target object to the artificial intelligence model to obtain the recommended content generated by the artificial intelligence model, and instructs the target application to display the generated recommended content. Since the artificial intelligence model uses both the initial portrait data and the target behavior data of the target object to generate the recommended content, the recommended content is more personalized, thereby solving the problem of poor quality of the recommended content.

[0135] In an exemplary embodiment, the above-mentioned device also includes: a generation module, which is used to obtain the first portrait data generated by the target artificial intelligence model after sending the initial portrait data and the target behavior data to the target artificial intelligence model before obtaining the first recommended content generated by the target artificial intelligence model; when the first portrait data meets the first preset condition, instruct the target artificial intelligence model to generate recommended content based on the first portrait data.

[0136] In an exemplary embodiment, the above-mentioned device also includes: an adjustment module, which is used to adjust the first portrait data when the first portrait data does not meet the first preset condition, so as to obtain second portrait data that meets the preset condition; a generation module, which is also used to instruct the target artificial intelligence model to generate recommended content based on the second portrait data; an indication module 56, which is also used to obtain the second recommended content generated by the target artificial intelligence model based on the second portrait data, and instruct the target application to display the second recommended content.

[0137] In an exemplary embodiment, the adjustment module is also used to adjust the first parameter of the target artificial intelligence model to obtain a first artificial intelligence model when the first portrait data does not meet the first preset condition, wherein when the first parameter of the target artificial intelligence model is adjusted, the strategy for generating portrait data by the target artificial intelligence model changes; the generation module is also used to obtain third portrait data generated by the first artificial intelligence model based on the target behavior data and the initial portrait data; when the third portrait data meets the first preset condition, instruct the target artificial intelligence model to generate recommended content based on the third portrait data; the indication module 56 is also used to obtain third recommended content generated by the target artificial intelligence model based on the third portrait data, and instruct the target application to display the third recommended content.

[0138] In an exemplary embodiment, the indication module 56 is further used to determine the display order of the multiple sub-recommended contents according to a preset sorting rule when the first recommended content includes multiple sub-recommended contents; and instruct the target application to display the first recommended content according to the display order.

[0139] In an exemplary embodiment, the above-mentioned device also includes: a feedback module, used to obtain feedback data sent by the target application after instructing the target application to display the first recommended content, wherein the feedback data is used to indicate the target object's satisfaction with the first recommended content; and send the feedback data to the target artificial intelligence model; an indication module 56, also used to obtain the fourth recommended content generated by the target artificial intelligence model, and instruct the target application to display the fourth recommended content, wherein the fourth recommended content is the recommended content generated by the target artificial intelligence model based on the fourth portrait data, and the fourth portrait data is the portrait data generated by the target artificial intelligence model based on the feedback data and the first portrait data.

[0140] In an exemplary embodiment, the indication module 56 is also used to determine whether the first recommended content satisfies a second preset condition, and when it is determined that the first recommended content satisfies the second preset condition, instruct the target application to display the first recommended content; the adjustment module is also used to adjust the second parameter of the target artificial intelligence model to obtain a second artificial intelligence model when the first recommended content does not satisfy the second preset condition, wherein when the second parameter of the target artificial intelligence model is adjusted, the strategy for generating recommended content by the target artificial intelligence model changes; the indication module 56 is also used to obtain the fifth recommended content generated by the second artificial intelligence model, and when the fifth recommended content satisfies the second preset condition, instruct the target application to display the fifth recommended content, wherein the fifth recommended content is the recommended content generated by the second artificial intelligence model based on the first portrait data.

[0141] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0142] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0143] S1, obtaining initial portrait data of a target object and target behavior data of the target object in a target application;

[0144] S2, sending the initial portrait data and the target behavior data to a target artificial intelligence model;

[0145] S3. Obtain the first recommended content generated by the target artificial intelligence model, and instruct the target application to display the first recommended content, wherein the first recommended content is the recommended content generated by the target artificial intelligence model based on the first portrait data, and the first portrait data is the portrait data generated by the target artificial intelligence model based on the target behavior data and the initial portrait data.

[0146] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0147] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0148] The embodiment of the present application also provides an electronic device, such as Figure 6 As shown, the electronic device includes a memory 602 and a processor 604. The memory 602 stores a computer program, and the processor 604 is configured to execute the steps in any of the above method embodiments through the computer program.

[0149] Optionally, in this embodiment, the processor 604 may be configured to perform the following steps through a computer program:

[0150] S1, obtaining initial portrait data of a target object and target behavior data of the target object in a target application;

[0151] S2, sending the initial portrait data and the target behavior data to a target artificial intelligence model;

[0152] S3. Obtain the first recommended content generated by the target artificial intelligence model, and instruct the target application to display the first recommended content, wherein the first recommended content is the recommended content generated by the target artificial intelligence model based on the first portrait data, and the first portrait data is the portrait data generated by the target artificial intelligence model based on the target behavior data and the initial portrait data.

[0153] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0154] Alternatively, a person skilled in the art may understand that: Figure 6 The structure shown is for illustration only. Figure 6 The structure of the electronic device is not limited. For example, the electronic device may also include Figure 6 More or fewer components (such as network interfaces, etc.) as shown in, or with Figure 6 Different configurations shown.

[0155] Among them, the memory 602 can be used to store software programs and modules, such as the program instructions / modules corresponding to the content recommendation method and device in the embodiments of the present application. The processor 604 executes various functional applications and data processing by running the software programs and modules stored in the memory 602, that is, to implement the above-mentioned content recommendation method. The memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 602 may further include a memory remotely located relative to the processor 604, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 602 can be specifically, but not limited to, used to store information such as system configuration files. As an example, such as Figure 6 As shown, the memory 602 may include, but is not limited to, the acquisition module 52, the sending module 54 and the indication module 56 in the content recommendation device. In addition, it may also include, but is not limited to, other module units in the content recommendation device (such as the first determination module and the second determination module), which will not be described in detail in this example.

[0156] Optionally, the transmission device 606 is used to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one example, the transmission device 606 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 606 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0157] In addition, the electronic device further includes: a display 608; and a connection bus 610, which is used to connect various module components in the electronic device.

[0158] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0159] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0160] The embodiments of the present application also provide a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any one of the above method embodiments.

[0161] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0162] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0163] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A content recommendation method, characterized in that: include: Obtaining initial portrait data of a target object and target behavior data of the target object in a target application; Sending the initial portrait data and the target behavior data to a target artificial intelligence model; Obtain the first recommended content generated by the target artificial intelligence model, and instruct the target application to display the first recommended content, wherein the first recommended content is the recommended content generated by the target artificial intelligence model based on the first portrait data, and the first portrait data is the portrait data generated by the target artificial intelligence model based on the target behavior data and the initial portrait data.

2. The content recommendation method according to claim 1, characterized in that: Before obtaining the first recommended content generated by the target artificial intelligence model, the method further includes: After sending the initial portrait data and the target behavior data to the target artificial intelligence model, obtaining the first portrait data generated by the target artificial intelligence model; When the first portrait data satisfies a first preset condition, instruct the target artificial intelligence model to generate recommended content based on the first portrait data.

3. The content recommendation method according to claim 2, characterized in that: The method further comprises: When the first portrait data does not satisfy the first preset condition, adjusting the first portrait data to obtain second portrait data satisfying the preset condition; instructing the target artificial intelligence model to generate recommended content according to the second portrait data; Obtain the second recommended content generated by the target artificial intelligence model based on the second portrait data, and instruct the target application to display the second recommended content.

4. The content recommendation method according to claim 2, characterized in that: The method further comprises: When the first portrait data does not satisfy the first preset condition, adjusting the first parameter of the target artificial intelligence model to obtain a first artificial intelligence model, wherein when the first parameter of the target artificial intelligence model is adjusted, the strategy of generating portrait data by the target artificial intelligence model changes; Obtain third portrait data generated by the first artificial intelligence model according to the target behavior data and the initial portrait data; In the case where the third portrait data satisfies the first preset condition, instructing the target artificial intelligence model to generate recommended content according to the third portrait data; Obtain the third recommended content generated by the target artificial intelligence model based on the third portrait data, and instruct the target application to display the third recommended content.

5. The content recommendation method according to claim 1, characterized in that: Instructing the target application to display the first recommended content includes: In the case where the first recommended content includes a plurality of sub-recommended contents, determining a display order of the plurality of sub-recommended contents according to a preset sorting rule; Instruct the target application to display the first recommended content according to the display order.

6. The content recommendation method according to claim 1, characterized in that: After instructing the target application to display the first recommended content, the method further includes: Acquiring feedback data sent by the target application, wherein the feedback data is used to indicate the satisfaction degree of the target object with the first recommended content; Sending the feedback data to the target artificial intelligence model; Obtain the fourth recommended content generated by the target artificial intelligence model, and instruct the target application to display the fourth recommended content, wherein the fourth recommended content is the recommended content generated by the target artificial intelligence model based on fourth portrait data, and the fourth portrait data is portrait data generated by the target artificial intelligence model based on the feedback data and the first portrait data.

7. The content recommendation method according to claim 1, characterized in that: After obtaining the first recommended content generated by the target artificial intelligence model, the method further includes: determining whether the first recommended content satisfies a second preset condition, and if it is determined that the first recommended content satisfies the second preset condition, instructing the target application to display the first recommended content; When the first recommended content does not meet the second preset condition, adjusting the second parameter of the target artificial intelligence model to obtain a second artificial intelligence model, wherein when the second parameter of the target artificial intelligence model is adjusted, the strategy of the target artificial intelligence model to generate recommended content changes; Obtain the fifth recommended content generated by the second artificial intelligence model, and if the fifth recommended content meets the second preset condition, instruct the target application to display the fifth recommended content, wherein the fifth recommended content is the recommended content generated by the second artificial intelligence model based on the first portrait data.

8. A content recommendation device, characterized in that: include: An acquisition module, used to acquire initial portrait data of a target object and target behavior data of the target object in a target application; A sending module, used to send the initial portrait data and the target behavior data to a target artificial intelligence model; An indication module is used to obtain the first recommended content generated by the target artificial intelligence model and instruct the target application to display the first recommended content, wherein the first recommended content is the recommended content generated by the target artificial intelligence model based on the first portrait data, and the first portrait data is the portrait data generated by the target artificial intelligence model based on the target behavior data and the initial portrait data.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images