A data recommendation method and device, electronic equipment and computer readable medium

Abstract

The application discloses a data recommendation method and device, an electronic device and a computer readable medium, relates to the technical field of big data analysis and mining, and specifically includes receiving a data recommendation request, obtaining a corresponding user identifier, and then obtaining corresponding simulation practice area user behavior data and corresponding practice area user behavior data based on the user identifier; generating a first user benefit label and a second user benefit label based on the simulation practice area user behavior data and the practice area user behavior data respectively; determining a user benefit label correlation coefficient according to the first user benefit label and the second user benefit label, and then optimizing the data recommendation model according to the user benefit label correlation coefficient; inputting the practice area user behavior data into the data recommendation model to obtain target recommended benefit data, and outputting the target benefit data. Thus, data recommendation can be automatically realized, and the accuracy of data recommendation for users can be improved.

Description

Technical Field

[0001] This application relates to the field of big data analysis and mining technology, and in particular to a data recommendation method, apparatus, electronic device and computer-readable medium. Background Technology

[0002] In scenarios where financial products are recommended to users, excessive incentives can easily lead to aggressive and extreme financial decisions that exceed users' financial capabilities, resulting in user losses and churn. On the other hand, conservative incentives may hinder the conversion of users' financial contributions into growth in the face of market competition, leading to low accuracy in data recommendations. Summary of the Invention

[0003] In view of this, embodiments of this application provide a data recommendation method, apparatus, electronic device, and computer-readable medium that can solve the problem of low accuracy in existing data recommendation methods.

[0004] To achieve the above objectives, according to one aspect of an embodiment of this application, a data recommendation method is provided, comprising:

[0005] Receive data recommendation requests, obtain the corresponding user identifiers, and then obtain the corresponding user behavior data in the simulation practice area and the corresponding user behavior data in the practice area based on the user identifiers;

[0006] Based on user behavior data from the simulation practice area and user behavior data from the practice area, a first user rights label and a second user rights label are generated respectively.

[0007] Based on the first user rights label and the second user rights label, the correlation coefficient of the user rights label is determined, and then the data recommendation model is optimized based on the correlation coefficient of the user rights label.

[0008] User behavior data from the practice area is input into the data recommendation model to obtain target recommendation benefit data, and then the target benefit data is output.

[0009] Optionally, after obtaining the target recommendation benefit data, the method further includes:

[0010] The data recommendation model is updated based on the target equity data.

[0011] Optionally, the correlation coefficient of user rights tags is determined, including:

[0012] Determine the first user's rights account entropy value array based on the first user's rights label;

[0013] Determine the entropy value array of the second user's rights account based on the second user's rights label;

[0014] Based on the first user equity account entropy value array and the second user equity account entropy value array, generate a user equity account entropy value correlation matrix;

[0015] The correlation coefficient of user rights tags is determined based on the user rights account entropy correlation matrix.

[0016] Optionally, target recommendation equity data can be obtained, including:

[0017] Determine the recommendation level corresponding to the recommended rights data;

[0018] The recommended benefit data corresponding to a recommendation score greater than a preset threshold is determined as the target benefit data.

[0019] Optionally, the target equity data can be output, including:

[0020] The recommendation scores exceeding a preset threshold are sorted in descending order, and then the corresponding target benefit data are output in sequence.

[0021] Optionally, a data recommendation model is obtained by optimizing the correlation coefficient of user rights tags, including:

[0022] The user rights label correlation coefficient is updated in each iteration optimization cycle with a preset time interval, and the data recommendation model is optimized based on the updated user rights label correlation coefficient.

[0023] Optionally, the user rights tag correlation coefficient is updated in each iteration optimization cycle, including:

[0024] In each iterative optimization cycle, the user behavior data in the simulated practice area and the corresponding user behavior data in the practice area corresponding to the user identifier are reacquired.

[0025] The correlation coefficient of user rights labels is updated based on the user behavior data in the simulation practice area and the corresponding user behavior data in the practice area corresponding to the re-acquired user identifier.

[0026] In addition, this application also provides a data recommendation device, including:

[0027] The receiving unit is configured to receive data recommendation requests, obtain the corresponding user identifier, and then obtain the corresponding simulated practice area user behavior data and the corresponding practice area user behavior data based on the user identifier.

[0028] The tag generation unit is configured to generate a first user rights tag and a second user rights tag based on user behavior data from the simulation practice area and user behavior data from the practice area, respectively.

[0029] The model optimization unit is configured to determine the correlation coefficient of user rights labels based on the first user rights label and the second user rights label, and then optimize the data recommendation model based on the correlation coefficient of user rights labels.

[0030] The data recommendation unit is configured to input user behavior data from the practice area into the data recommendation model to obtain target recommendation benefit data and output target benefit data.

[0031] Optionally, the device further includes an update unit configured to:

[0032] The data recommendation model is updated based on the target equity data.

[0033] Optionally, the model optimization unit is further configured to:

[0034] Determine the first user's rights account entropy value array based on the first user's rights label;

[0035] Determine the entropy value array of the second user's rights account based on the second user's rights label;

[0036] Based on the first user equity account entropy value array and the second user equity account entropy value array, generate a user equity account entropy value correlation matrix;

[0037] The correlation coefficient of user rights tags is determined based on the user rights account entropy correlation matrix.

[0038] Optionally, the data recommendation unit is further configured to:

[0039] Determine the recommendation level corresponding to the recommended rights data;

[0040] The recommended benefit data corresponding to a recommendation score greater than a preset threshold is determined as the target benefit data.

[0041] Optionally, the data recommendation unit is further configured to:

[0042] The recommendation scores exceeding a preset threshold are sorted in descending order, and then the corresponding target benefit data are output in sequence.

[0043] Optionally, the model optimization unit is further configured to:

[0044] The user rights label correlation coefficient is updated in each iteration optimization cycle with a preset time interval, and the data recommendation model is optimized based on the updated user rights label correlation coefficient.

[0045] Optionally, the model optimization unit is further configured to:

[0046] In each iterative optimization cycle, the user behavior data in the simulated practice area and the corresponding user behavior data in the practice area corresponding to the user identifier are reacquired.

[0047] The correlation coefficient of user rights labels is updated based on the user behavior data in the simulation practice area and the corresponding user behavior data in the practice area corresponding to the re-acquired user identifier.

[0048] In addition, this application also provides a data recommendation electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the data recommendation method as described above.

[0049] In addition, this application also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the data recommendation method as described above.

[0050] To achieve the above objectives, according to another aspect of the embodiments of this application, a computer program product is provided.

[0051] A computer program product according to an embodiment of this application includes a computer program that, when executed by a processor, implements the data recommendation method provided in an embodiment of this application.

[0052] One embodiment of the above invention has the following advantages or beneficial effects: This application receives a data recommendation request, obtains the corresponding user identifier, and then obtains the corresponding simulated practice area user behavior data and the corresponding practice area user behavior data based on the user identifier; generates a first user benefit label and a second user benefit label based on the simulated practice area user behavior data and the practice area user behavior data, respectively; determines the user benefit label correlation coefficient based on the first user benefit label and the second user benefit label, and then optimizes the data recommendation model based on the user benefit label correlation coefficient; inputs the practice area user behavior data into the data recommendation model to obtain the target recommended benefit data, and outputs the target benefit data. This allows for automated data recommendation and improves the accuracy of data recommendations for users.

[0053] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0054] The accompanying drawings are provided to better understand this application and do not constitute an undue limitation thereof. Wherein:

[0055] Figure 1 This is a schematic diagram of the main flow of a data recommendation method according to an embodiment of this application;

[0056] Figure 2 This is a schematic diagram of the main flow of a data recommendation method according to an embodiment of this application;

[0057] Figure 3 This is a schematic diagram of the main flow of a data recommendation method according to an embodiment of this application;

[0058] Figure 4 This is a schematic diagram of the main units of a data recommendation device according to an embodiment of this application;

[0059] Figure 5 This is an exemplary system architecture diagram to which embodiments of this application can be applied;

[0060] Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers in the embodiments of this application. Detailed Implementation

[0061] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These embodiments should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the collection, analysis, use, transmission, and storage of user personal information involved in the technical solutions of this application comply with relevant laws and regulations, are used for legitimate and reasonable purposes, are not shared, disclosed, or sold outside of these legitimate uses, and are subject to supervision and management by regulatory authorities. Necessary measures should be taken to prevent unauthorized access to such personal information data, ensure that personnel authorized to access personal information data comply with relevant laws and regulations, and ensure the security of user personal information. Once this user personal information data is no longer needed, the risk should be minimized by restricting or even prohibiting data collection and / or deleting the data.

[0062] When used, including in certain relevant applications, data is deidentified to protect user privacy, for example by removing specific identifiers, controlling the amount or specificity of stored data, controlling how data is stored, and / or other methods.

[0063] Figure 1 This is a schematic diagram of the main flow of a data recommendation method according to an embodiment of this application, as shown below. Figure 1 As shown, data recommendation methods include:

[0064] Step S101: Receive a data recommendation request, obtain the corresponding user identifier, and then obtain the corresponding user behavior data in the simulation practice area and the corresponding user behavior data in the practice area based on the user identifier.

[0065] In this embodiment, the executing entity of the data recommendation method (e.g., a server) can receive data recommendation requests via wired or wireless connections. Specifically, a data recommendation request can be a request to recommend benefits. Benefits: a marketing tool, which may take the form of cash equivalents, financial privileges, or consulting services, such as cash red envelopes, fee discount coupons, financial information, and financial advisory services. After receiving the data recommendation request, the executing entity can obtain the user identifier carried in the request. The user identifier may be, for example, the nickname or ID of the user accessing the platform corresponding to the data recommendation request; this embodiment does not specifically limit the user identifier. After receiving the data recommendation request, the executing entity can obtain the historical user behavior data of the user corresponding to the user identifier in the simulation practice area and the corresponding historical user behavior data in the practice area. Specifically, user behavior data may include financial product access data, financial product purchase data, and financial product holding data; this embodiment does not specifically limit the user behavior data.

[0066] Step S102: Generate a first user rights label and a second user rights label based on user behavior data from the simulation practice area and the practice area, respectively.

[0067] For example, the first user rights label can be the user rights label for the financial simulation practice area, and the second user rights label can be the user rights label for the financial practice area. Specifically, the creation of user rights labels can include creating user rights labels for the financial simulation practice area (i.e., the first user rights label) and user rights labels for the financial channel (i.e., the financial practice area) (i.e., the second user rights label); as well as the generation of data push, label creation, scene-side (financial platform) user rights label records, and rights account entropy value arrays (which may include user rights account entropy value arrays for the financial simulation practice area and user rights account entropy value arrays for the financial channel).

[0068] Step S103: Determine the correlation coefficient of user rights labels based on the first user rights label and the second user rights label, and then optimize the data recommendation model based on the correlation coefficient of user rights labels.

[0069] Based on the generated user rights tags and rights account entropy value arrays, generate an association matrix between the user rights account entropy value arrays of the financial simulation practice area and the user rights account entropy value arrays of the financial channel; based on the user rights tags of the financial simulation practice area (i.e., the first user rights tag) and the user rights tags of the financial channel (i.e., the second user rights tag), through user identification and correlation coefficient calculation, output the user rights tag correlation coefficient (i.e., the user rights tag correlation coefficient) between the user rights tags of the financial simulation practice area and the user rights tags of the financial channel.

[0070] Specifically, the data recommendation model is optimized based on the correlation coefficient of user rights tags, including: updating the correlation coefficient of user rights tags in each iteration optimization cycle with a preset time interval, and optimizing the data recommendation model based on the updated correlation coefficient of user rights tags.

[0071] For example, in the big data computing area and correlation area of ​​the rights and interests platform, the correlation coefficient of user rights and interests tags is received; the Logistic model is dynamically and continuously optimized in a specific time period; after the model is built, the decision algorithm is implemented; the decision algorithm supports outputting 1 to 3 recommended rights and interests (sorted from high to low recommendation degree) based on relevant inputs; for user rights and interests tags in the wealth management channel, the user rights and interests tags in the wealth management channel are reconstructed based on the feedback obtained, so as to continuously iterate and optimize the user rights and interests tags in the wealth management channel, thereby iteratively optimizing and updating the correlation coefficient of user rights and interests tags, and optimizing the latest data recommendation model based on the updated correlation coefficient of user rights and interests tags.

[0072] Specifically, the user rights label correlation coefficient is updated in each iteration optimization cycle, including: re-acquiring the user behavior data in the simulation practice area and the corresponding user behavior data in the practice area corresponding to the user identifier in each iteration optimization cycle; and updating the user rights label correlation coefficient based on the re-acquiring user behavior data in the simulation practice area and the corresponding user behavior data in the practice area corresponding to the user identifier.

[0073] For example, user behavior data can include user browsing history (browsing history of products, benefits, etc.), user usage history (frequency, redemption method, etc.), user consumption of product tiers (type, price, etc.), geographical location, cycle (season, date, etc.), interest relevance (recent consumption relevance, etc.), etc. Based on the newly acquired user behavior data, the user benefit tags corresponding to the financial management simulation practice area and the financial management channel (i.e., the financial management practice area) are updated, thereby updating the corresponding user benefit tag correlation coefficients.

[0074] Step S104: Input the user behavior data of the practice area into the data recommendation model to obtain the target recommendation benefit data, and output the target benefit data.

[0075] Target benefit data refers to the appropriate benefit data recommended to users corresponding to the user identifier.

[0076] Specifically, after obtaining the target recommendation benefit data, the method also includes updating the data recommendation model based on the target benefit data.

[0077] The output target benefit data is used as reverse feedback data to update the data recommendation model, making the output results of the data recommendation model more accurate, more in line with user wishes, and improving the success rate of data recommendation.

[0078] Specifically, obtaining target recommendation benefit data includes: determining the recommendation degree corresponding to the recommendation benefit data; and determining the recommendation benefit data corresponding to the recommendation degree being greater than a preset threshold as target benefit data.

[0079] Specifically, the target benefit data is output, including sorting the recommendation scores that are greater than a preset threshold in descending order, and then outputting the corresponding target benefit data in sequence.

[0080] The determined recommendation scores are sorted in descending order, and the recommendation benefit data corresponding to the top N recommendation scores are determined as the target benefit data. The recommendation scores corresponding to the top N recommendation data are greater than a preset threshold.

[0081] This embodiment receives a data recommendation request, obtains the corresponding user identifier, and then obtains corresponding user behavior data in the simulation practice area and the practice area based on the user identifier. Based on the user behavior data in the simulation practice area and the practice area, a first user benefit label and a second user benefit label are generated respectively. The correlation coefficient between the first and second user benefit labels is determined, and the data recommendation model is then optimized based on the correlation coefficient. The practice area user behavior data is input into the data recommendation model to obtain the target recommended benefit data, and the target benefit data is output. This allows for automated data recommendation and improves the accuracy of user data recommendations.

[0082] Figure 2 This is a schematic diagram of the main flow of a data recommendation method according to an embodiment of this application, such as... Figure 2 As shown, data recommendation methods include:

[0083] Step S201: Receive a data recommendation request, obtain the corresponding user identifier, and then obtain the corresponding user behavior data in the simulation practice area and the corresponding user behavior data in the practice area based on the user identifier.

[0084] For example, user behavior data may include user browsing history (browsing history of products, benefits, etc.), user usage history (frequency, redemption method, etc.), user consumption of product tiers (type, price, etc.), geographical location, period (season, date, etc.), interest relevance (recent consumption relevance, etc.), etc.

[0085] Step S202: Generate a first user rights label and a second user rights label based on user behavior data from the simulation practice area and the practice area, respectively.

[0086] Step S203: Determine the first user rights account entropy value array based on the first user rights label.

[0087] Calculate the entropy value of each first user rights tag, and then generate an array of first user rights account entropy values.

[0088] Step S204: Determine the second user rights account entropy value array based on the second user rights label.

[0089] Calculate the entropy value of each second user rights tag, and then generate an array of second user rights account entropy values.

[0090] Step S205: Generate a user rights account entropy correlation matrix based on the first user rights account entropy value array and the second user rights account entropy value array.

[0091] Call the association matrix generation program to generate an m*n user rights account entropy value association matrix based on the generated first user rights account entropy value array and the generated second user rights account entropy value array, where m can be the number of user rights in the simulation practice area and n can be the number of user rights in the practice area corresponding to that user.

[0092] Step S206: Determine the correlation coefficient of user rights tags based on the user rights account entropy correlation matrix.

[0093] The executing entity can calculate the similarity between each row of entropy values ​​(e.g., m1, m2, m3) and each column of entropy values ​​(e.g., n1, n2, n3) in the user rights account entropy value association matrix. For example, the cosine similarity c1 between m1 and n1, the cosine similarity c2 between m2 and n2, and the cosine similarity c3 between m3 and n3. The executing entity can then determine c1, c2, and c3 as the user rights tag association coefficients.

[0094] Step S207: Optimize the data recommendation model based on the correlation coefficient of user rights tags.

[0095] The system receives the correlation coefficients of user benefit tags; it iterates and optimizes the data recommendation model (i.e., the data recommendation model) dynamically and continuously, using a specific time period as one iteration cycle; after the data recommendation model is built, a decision algorithm is implemented; the decision algorithm supports outputting 1 to 3 recommended benefits (sorted from high to low recommendation degree) based on relevant inputs; for user benefit tags in the wealth management channel, the system reconstructs the user benefit tags based on the received feedback, thereby continuously iterating and optimizing the user benefit tags in the wealth management channel, which in turn iteratively optimizes and updates the correlation coefficients of user benefit tags, and optimizes and obtains the latest data recommendation model based on the updated correlation coefficients of user benefit tags.

[0096] Step S208: Input the user behavior data of the practice area into the data recommendation model to obtain the target recommendation benefit data, and output the target benefit data.

[0097] The embodiments of this application can improve the accuracy of data recommendations to users.

[0098] Figure 3 This is a schematic diagram illustrating an application scenario of a data recommendation method according to an embodiment of this application. The data recommendation method of this embodiment is applied to a data recommendation scenario. In this embodiment, a financial management platform is established with a financial management simulation practice area, including a rights and interests recommendation module and a user rights and interests tag adjustment module; a financial management channel is established on the financial management platform, optimizing the rights and interests recommendation module and the user rights and interests tag adjustment module; a big data computing area is established on the financial management platform to determine the rights and interests tag correlation matrix; a rights and interests platform data area is established on the data exchange platform, allowing access to rights and interests accounts, rights and interests products, modification of correlation data, and addition of rights and interests tag correlation data; on the rights and interests platform, the rights and interests model recommendation algorithm decision engine can be optimized by adding rights and interests tag correlation factors and data input, performing logistic regression, recommending rights and interests, fine-tuning the model, and optimizing the algorithm decision.

[0099] like Figure 3 As shown, the data advancement method of this application embodiment can be implemented in the following ways:

[0100] 1) User Rights Tag Creation: This includes two categories: user rights tags in the financial simulation practice area and user rights tags in the financial channel. It encompasses data push, tag creation, scenario-side (financial platform) user tag recording, and rights account entropy value generation. In the financial simulation practice area and financial channel, data such as financial product data, financial rights product data, financial account data, financial rights transaction data, user behavior data, and user tag data are pushed to the financial platform via financial space data push. Then, the rights platform's big data calculation process generates user tags and outputs arrays of user rights tags and user rights account entropy values, such as [cst_id,prd_no,status,…,cnt]. Finally, the financial platform's big data calculation area outputs user tags and account entropy values.

[0101] 2) Generation of User Rights Tag Correlation Model: Generate a correlation matrix between the entropy values ​​of user rights accounts in the financial simulation practice area and the entropy values ​​of user rights accounts in the financial channel; perform user identification and correlation coefficient calculation, and output the correlation coefficient of user rights tags.

[0102] 3) Optimization of the Rights and Interests Model Recommendation Algorithm: In the big data computing area and correlation area of ​​the rights and interests platform, the correlation coefficients of user rights and interests tags are received; the data recommendation model (i.e., the data recommendation model) is dynamically and continuously optimized with a specific time as one iteration optimization cycle; after the data recommendation model is built, the decision algorithm is implemented; the decision algorithm supports outputting 1 to 3 recommended rights and interests (sorted from high to low recommendation degree) based on relevant inputs; for user rights and interests tags in the wealth management channel, the user rights and interests tags in the wealth management channel are reconstructed based on the received feedback, and the user rights and interests tags in the wealth management channel can be continuously iterated and optimized, thereby iteratively optimizing and updating the correlation coefficients of user rights and interests tags, and optimizing the latest data recommendation model based on the updated correlation coefficients of user rights and interests tags.

[0103] Specifically, the data recommendation model can receive user browsing history (browsing history of products, benefits, etc.), user usage history (frequency, redemption method, etc.), user consumption level of products (type, price, etc.), geographical location, cycle (season, date, etc.), interest relevance (recent consumption relevance, etc.) as input factors. At the same time, it can add input factors such as financial simulation practice area - user benefit tags, financial channel - user benefit tags, and user benefit tag correlation coefficient to output target benefit data.

[0104] This application embodiment uses user behavior data to simulate and quantify users' financial management capabilities and psychological activities, building a learning environment for the data recommendation model; it establishes financial management user rights tags (simulated practice area financial management user rights tags, financial management channel financial management user rights tags), which can be directly used as a decision reference for expert-based rights recommendation in specific scenarios, and can play a role in manually optimizing the data recommendation model based on expert methods, making the data recommendation model more reliable; it constructs a dynamically input and continuously optimized data recommendation model, so that user rights tags are continuously optimized, thereby making the rights recommendation decision algorithm more reliable and automated.

[0105] This application's embodiments fully incorporate the completeness of existing data recommendation model algorithms, combining them with the general and specific business models of wealth management platforms. It fully utilizes effective data such as user behavior in the wealth management simulation practice area to enrich the construction factors of the data recommendation model. Simultaneously, by fully leveraging the simulation practice area as a learning environment for the equity recommendation model, including introducing an expert model optimization mechanism (processing user equity tags for expert equity recommendation decision reference), and automatically, dynamically, and continuously building the data recommendation model, the decision-making algorithm is optimized to achieve more accurate and effective equity recommendations or incentives, thereby improving the effectiveness of the wealth management platform's digital operations.

[0106] Figure 4 This is a schematic diagram of the main units of a data recommendation device according to an embodiment of this application. For example... Figure 4As shown, the data recommendation device 400 includes a receiving unit 401, a tag generation unit 402, a model optimization unit 403, and a data recommendation unit 404.

[0107] The receiving unit 401 is configured to receive data recommendation requests, obtain the corresponding user identifier, and then obtain the corresponding user behavior data in the simulation practice area and the corresponding user behavior data in the practice area based on the user identifier.

[0108] The tag generation unit 402 is configured to generate a first user rights tag and a second user rights tag based on user behavior data from the simulation practice area and user behavior data from the practice area, respectively.

[0109] The model optimization unit 403 is configured to determine the correlation coefficient of user rights labels based on the first user rights label and the second user rights label, and then optimize the data recommendation model based on the correlation coefficient of user rights labels.

[0110] The data recommendation unit 404 is configured to input user behavior data from the practice area into the data recommendation model to obtain target recommendation benefit data and output target benefit data.

[0111] In some embodiments, the apparatus further includes Figure 4 The update unit, not shown, is configured to update the data recommendation model based on the target equity data.

[0112] In some embodiments, the model optimization unit 403 is further configured to: determine a first user rights account entropy array based on a first user rights label; determine a second user rights account entropy array based on a second user rights label; generate a user rights account entropy correlation matrix based on the first user rights account entropy array and the second user rights account entropy array; and determine the user rights label correlation coefficient based on the user rights account entropy correlation matrix.

[0113] In some embodiments, the data recommendation unit 404 is further configured to: determine the recommendation degree corresponding to the recommended benefit data; and determine the recommended benefit data corresponding to the recommendation degree being greater than a preset threshold as the target benefit data.

[0114] In some embodiments, the data recommendation unit 404 is further configured to: sort the recommendation scores greater than a preset threshold in descending order, and then output the corresponding target benefit data in sequence.

[0115] In some embodiments, the model optimization unit 403 is further configured to: update the user rights label correlation coefficient in each iteration optimization cycle with a preset time interval as the iteration optimization cycle, and optimize the data recommendation model based on the updated user rights label correlation coefficient.

[0116] In some embodiments, the model optimization unit 403 is further configured to: reacquire the simulated practice area user behavior data and the corresponding practice area user behavior data corresponding to the user identifier in each iterative optimization cycle; and update the user rights label correlation coefficient based on the reacquired simulated practice area user behavior data and the corresponding practice area user behavior data corresponding to the user identifier.

[0117] It should be noted that the data recommendation method and data recommendation device in this application are related in terms of specific implementation, so repeated content will not be described again.

[0118] Figure 5 An exemplary system architecture 500 is shown that can be applied to the data recommendation method or data recommendation apparatus of the embodiments of this application.

[0119] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, and 503, a network 504, and a server 505. Network 504 serves as the medium for providing communication links between terminal devices 501, 502, and 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0120] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, and 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0121] Terminal devices 501, 502, and 503 can be various electronic devices with data recommendation processing screens and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0122] Server 505 can be a server providing various services, such as a backend management server supporting data recommendation requests submitted by users using terminal devices 501, 502, and 503 (this is just an example). The backend management server can receive data recommendation requests, obtain the corresponding user identifier, and then obtain corresponding user behavior data from the simulation practice area and the practice area based on the user identifier. Based on the simulation practice area user behavior data and the practice area user behavior data, it generates a first user benefit label and a second user benefit label, respectively. Based on the first user benefit label and the second user benefit label, it determines the correlation coefficient of the user benefit label, and then optimizes the data recommendation model based on the correlation coefficient. The practice area user behavior data is input into the data recommendation model to obtain the target recommended benefit data, and the target benefit data is output. This can improve the accuracy of data recommendations for users.

[0123] It should be noted that the data recommendation method provided in this application embodiment is generally executed by server 505, and correspondingly, the data recommendation device is generally set in server 505.

[0124] It should be understood that Figure 5 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0125] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing a terminal device according to the embodiments of this application. Figure 6 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0126] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the computer system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0127] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0128] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this application.

[0129] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0131] The units described in the embodiments of this application can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including a receiving unit, a tag generation unit, a model optimization unit, and a data recommendation unit. The names of these units do not necessarily limit the specific unit itself.

[0132] In another aspect, this application also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to receive a data recommendation request, obtain a corresponding user identifier, and then obtain corresponding simulated practice area user behavior data and corresponding practice area user behavior data based on the user identifier; generate a first user rights label and a second user rights label based on the simulated practice area user behavior data and the practice area user behavior data, respectively; determine a user rights label correlation coefficient based on the first user rights label and the second user rights label, and then optimize the data recommendation model based on the user rights label correlation coefficient; input the practice area user behavior data into the data recommendation model to obtain target recommended rights data, and output the target rights data.

[0133] The computer program product of this application includes a computer program that, when executed by a processor, implements the data recommendation method in the embodiments of this application.

[0134] According to the technical solution of the embodiments of this application, data recommendation can be automated and the accuracy of data recommendation to users can be improved.

[0135] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A data recommendation method, characterized in that, include: Receive a data recommendation request, obtain the corresponding user identifier, and then obtain the corresponding simulated practice area user behavior data and the corresponding practice area user behavior data based on the user identifier; Based on the user behavior data in the simulated practice area and the user behavior data in the practice area, a first user rights label and a second user rights label are generated respectively. Based on the first user rights label and the second user rights label, the correlation coefficient of the user rights label is determined, and then the data recommendation model is optimized based on the correlation coefficient of the user rights label. The user behavior data of the practice area is input into the data recommendation model to obtain the target recommendation benefit data, and the target benefit data is output. The step of determining the correlation coefficient of user rights labels includes: determining a first user rights account entropy value array based on the first user rights label; determining a second user rights account entropy value array based on the second user rights label; generating a user rights account entropy value correlation matrix based on the first user rights account entropy value array and the second user rights account entropy value array; and determining the correlation coefficient of user rights labels based on the user rights account entropy value correlation matrix. The step of optimizing the data recommendation model based on the correlation coefficient of the user rights label includes: updating the correlation coefficient of the user rights label in each iteration optimization cycle with a preset time interval as the iteration optimization cycle, and optimizing the data recommendation model based on the updated correlation coefficient of the user rights label.

2. The method according to claim 1, characterized in that, After obtaining the target recommendation benefit data, the method further includes: The data recommendation model is updated based on the target equity data.

3. The method according to claim 1, characterized in that, The obtained target recommendation equity data includes: Determine the recommendation level corresponding to the recommended rights data; The recommended benefit data corresponding to the recommendation degree being greater than a preset threshold is determined as the target benefit data.

4. The method according to claim 3, characterized in that, The output of the target equity data includes: The recommendation scores exceeding a preset threshold are sorted in descending order, and then the corresponding target benefit data are output in sequence.

5. The method according to claim 1, characterized in that, The step of updating the user rights tag correlation coefficient in each iteration optimization cycle includes: In each iteration optimization cycle, the user behavior data in the simulated practice area and the corresponding user behavior data in the practice area corresponding to the user identifier are reacquired. The correlation coefficient of the user rights label is updated based on the user behavior data in the simulated practice area and the user behavior data in the practice area corresponding to the re-acquired user identifier.

6. A data recommendation device, characterized in that, include: The receiving unit is configured to receive data recommendation requests, obtain the corresponding user identifier, and then obtain the corresponding simulated practice area user behavior data and the corresponding practice area user behavior data based on the user identifier. The tag generation unit is configured to generate a first user rights tag and a second user rights tag based on the user behavior data in the simulated practice area and the user behavior data in the practice area, respectively. The model optimization unit is configured to determine the correlation coefficient of user rights tags based on the first user rights tag and the second user rights tag, and then optimize the data recommendation model based on the correlation coefficient of user rights tags. The data recommendation unit is configured to input the user behavior data of the practice area into the data recommendation model to obtain target recommendation benefit data and output the target benefit data; The model optimization unit is further configured to: determine a first user rights account entropy value array based on the first user rights label; determine a second user rights account entropy value array based on the second user rights label; generate a user rights account entropy value correlation matrix based on the first user rights account entropy value array and the second user rights account entropy value array; and determine the user rights label correlation coefficient based on the user rights account entropy value correlation matrix. The model optimization unit is further configured to: update the user rights label correlation coefficient in each iteration optimization cycle with a preset time interval, and optimize the data recommendation model based on the updated user rights label correlation coefficient.

7. The apparatus according to claim 6, characterized in that, The device further includes an update unit configured to: The data recommendation model is updated based on the target equity data.

8. The apparatus according to claim 6, characterized in that, The data recommendation unit is further configured to: Determine the recommendation level corresponding to the recommended rights data; The recommended benefit data corresponding to the recommendation degree being greater than a preset threshold is determined as the target benefit data.

9. The apparatus according to claim 8, characterized in that, The data recommendation unit is further configured to: The recommendation scores exceeding a preset threshold are sorted in descending order, and then the corresponding target benefit data are output in sequence.

10. A data recommendation electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

11. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-5.

Images