Personalized reading recommendation method and system, computer equipment and storage medium

Abstract

The invention relates to a personalized reading recommendation method and system, computer equipment and a storage medium, and the method comprises the steps: collecting reading behavior data of a user, constructing a personalized reading portrait of the user according to the reading behavior data, and analyzing the personalized reading portrait based on a preset reading prediction model to obtain reading prediction data of the user; matching and generating a corresponding recommended reading material based on the personalized reading portrait of the user and the reading prediction data; performing stage division on the reading behavior data and the recommended reading material, and dynamically adjusting the recommended reading material under the condition that the user completes reading in a preset stage so as to accord with the current reading progress and reading interest of the user; and updating the reading material library according to a preset time period, and updating the index corresponding to the reading material. The method has the effect of improving the reading recommendation accuracy of the user.

Description

Technical Field

[0001] The present application relates to the technical field of educational technology, and in particular to a personalized reading recommendation method, system, computer device and storage medium. Background Art

[0002] At present, with the popularity of digital reading platforms, users often find it difficult to quickly find content that suits their interests and needs when faced with a massive amount of reading materials. Existing personalized recommendation methods mostly rely on static user information, such as user historical behavior data or preference settings, to generate recommended content. However, these methods often cannot reflect changes in user interests in real time, and fail to consider the differences in user needs at different reading stages, resulting in poor ability to accurately capture and dynamically adjust users' personalized needs.

[0003] The above-mentioned existing technical solutions have the following defects: most of the existing personalized recommendation methods rely on static user information, resulting in poor ability to accurately push personalized needs of users, so there is room for improvement. Summary of the invention

[0004] In order to improve the accuracy of reading recommendations for users, the present application provides a personalized reading recommendation method, system, computer device and storage medium.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A personalized reading recommendation method, the personalized reading recommendation method comprising: Collecting the user's reading behavior data, constructing a personalized reading profile of the user according to the reading behavior data, and analyzing the personalized reading profile based on a preset reading prediction model to obtain the user's reading prediction data; Based on the personalized reading portrait of the user and the reading prediction data, matching and generating corresponding recommended reading materials; Divide the reading behavior data and the recommended reading materials into stages, and dynamically adjust the recommended reading materials to match the user's current reading progress and reading interests when the user completes the reading of a preset stage; Update the reading material library according to a preset time period and update the index corresponding to the reading material.

[0006] By adopting the above technical solution, by collecting the user's reading behavior data, and building the user's personalized reading portrait based on the reading behavior data, and analyzing the personalized reading portrait based on the preset reading prediction model to obtain the user's reading prediction data, it is possible to more accurately capture the user's interests and needs, and then provide personalized basic data for the recommendation system, thereby improving the accuracy and relevance of the recommended content; by matching and generating corresponding recommended reading materials based on the user's personalized reading portrait and reading prediction data, it is possible to ensure that the recommended content is highly matched with the user's interests, thereby improving user satisfaction and reading experience; by dividing the reading behavior data and recommended reading materials into stages, and dynamically adjusting the recommended reading materials when the user completes the preset stage reading, it is possible to update the recommended content in real time based on the user's current interest changes, thereby enhancing the flexibility and response speed of the recommendation system; by updating the reading material library according to the preset time period and updating the corresponding index of the reading material, it is possible to ensure that the recommendation system continues to provide the latest and diverse reading content, thereby improving the timeliness and breadth of the system's content.

[0007] In one example, the present application may be further configured as follows: constructing a personalized reading portrait of the user according to the reading behavior data, and analyzing the personalized reading portrait based on a preset reading prediction model to obtain the reading prediction data of the user, specifically including: Extracting reading feature data from the reading behavior data, classifying the reading feature data, and constructing the personalized reading portrait of the user based on the classified reading feature data; The personalized reading portrait is input into the reading prediction model, and the reading prediction data is obtained by analyzing the behavior pattern of the personalized reading portrait.

[0008] By adopting the above technical solution, by extracting reading feature data from reading behavior data and classifying the reading feature data, a personalized reading portrait of the user is constructed based on the classified reading feature data, which can more carefully analyze the user's reading preferences and behavior patterns, thereby providing stronger support for the precise matching of subsequent recommended content; by inputting the personalized reading portrait into the reading prediction model and analyzing the behavior pattern of the personalized reading portrait to obtain the reading prediction data, the user's future reading interests and needs can be predicted in real time, thereby adjusting the recommended content in advance and improving the accuracy and efficiency of personalized recommendations.

[0009] In one example, the present application may be further configured as follows: the construction of the reading prediction model specifically includes: Acquire the historical reading behavior data of the user, and classify the reading behavior data according to the reading preference type of the user to obtain different types of model training data sets; The preset machine learning algorithm is iteratively trained according to the model training data set to obtain the reading prediction model.

[0010] By adopting the above technical solution, by obtaining the user's historical reading behavior data and classifying the reading behavior data according to the user's reading preference type, different types of model training data sets are obtained, which can provide more accurate and targeted training data for the machine learning model, thereby improving the response speed and accuracy of the prediction model to changes in user interests; by iteratively training the preset machine learning algorithm according to the model training data set, a reading prediction model is obtained, which can optimize the adaptability of the recommendation system in different user groups, so that the model maintains efficient recommendation accuracy and stability in the face of changing reading needs.

[0011] In one example, the present application may be further configured as follows: matching and generating corresponding recommended reading materials based on the personalized reading portrait of the user and the reading prediction data, specifically including: According to the reading prediction data, matching the recommended reading materials that meet the reading prediction data; The reading preferences of the personalized reading portrait are sorted, and the recommended reading materials are displayed in order from high to low.

[0012] By adopting the above technical solution, by matching recommended reading materials that meet the reading prediction data according to the reading prediction data, it is possible to ensure that the recommended content meets the user's real-time interests, thereby improving user experience and satisfaction; by sorting the reading preferences based on personalized reading portraits, and displaying the recommended reading materials in order from high to low, it is possible to prioritize the most relevant materials based on the user's preferences for different content, thereby enhancing the personalization and accuracy of the recommendations.

[0013] In one example, the present application may be further configured as follows: the reading behavior data and the recommended reading materials are divided into stages, and when the user completes the reading of a preset stage, the recommended reading materials are dynamically adjusted, specifically including: Acquire the historical reading preferences of the user, associate the reading behavior data of the user with the historical reading preferences, identify the reading behavior pattern of the user through time series analysis, and divide the reading behavior pattern into multiple learning stages; When the user completes the current stage of reading, the reading interaction behavior of the user is obtained, and the reading interaction behavior is analyzed through an incremental learning mechanism to determine the user's in-depth reading interest; Based on the in-depth reading interest, the recommended reading material is further adjusted.

[0014] By adopting the above technical solution, by obtaining the user's historical reading preferences, associating the user's reading behavior data with the historical reading preferences, identifying the user's reading behavior pattern through time series analysis, and dividing the reading behavior pattern into multiple learning stages, it is possible to more finely capture the user's interest changes at different reading stages, thereby optimizing the dynamic adjustment of recommended content; by obtaining the user's reading interaction behavior when the user completes the current stage of reading, analyzing the reading interaction behavior through an incremental learning mechanism, and judging the user's deep reading interest, it is possible to further understand the user's reading depth and preference, avoid shallow recommendations, and improve the depth and accuracy of the recommendation system; by further adjusting the recommended reading materials based on deep reading interests, it is possible to ensure that the recommended content is more in line with the user's deep needs, thereby improving the system's personalized recommendation capabilities and user participation.

[0015] In one example, the present application may be further configured as follows: associating the reading behavior data of the user with the historical reading preference, identifying the reading behavior pattern of the user through time series analysis, and dividing the reading behavior pattern into multiple learning stages, specifically including: Using a similarity calculation algorithm to match the user's historical reading preference data with the user's reading behavior data to generate a related data set; Performing time series analysis on the associated data set, arranging the reading behavior data in chronological order, and grouping them according to preset time intervals, comparing the behavior characteristics of the users in each time interval, and identifying changes in user behavior patterns; Based on the changes in the user behavior pattern, the user's reading behavior pattern is divided into multiple learning stages according to significant change points in the user behavior pattern.

[0016] By adopting the above technical solution, by using a similarity calculation algorithm to match the user's historical reading preference data with the user's reading behavior data to generate a related data set, it is possible to more accurately combine the user's historical interests with the current behavior, provide stronger correlation support, and thus provide more accurate basic data for the construction of user portraits; by performing time series analysis on the related data set, arranging the reading behavior data in chronological order, and grouping them according to preset time intervals, comparing the user's behavior characteristics within each time interval, and identifying changes in user behavior patterns, it is possible to capture the user's behavior changes at different time points, and provide a basis for subsequent stage division, so that the adjustment of recommended content can adapt to the user's dynamic needs; by dividing the user's reading behavior pattern into multiple learning stages based on the changes in the user's behavior pattern according to the significant change points of the user's behavior pattern, it is possible to clearly define the user's interest change process, so as to provide recommended content that best meets user needs at different stages, thereby improving the accuracy of recommendations and user participation.

[0017] The second object of the invention is achieved by the following technical solutions: A personalized reading recommendation system, the personalized reading recommendation system comprising: A user behavior data collection module is used to collect the user's reading behavior data, construct a personalized reading profile of the user according to the reading behavior data, and analyze the personalized reading profile based on a preset reading prediction model to obtain the user's reading prediction data; A recommended material generation module, used to match and generate corresponding recommended reading materials based on the personalized reading portrait of the user and the reading prediction data; A stage division and adjustment module, for dividing the reading behavior data and the recommended reading materials into stages, and dynamically adjusting the recommended reading materials to match the current reading progress and reading interests of the user when the user completes the reading of a preset stage; The material library updating module is used to update the reading material library according to a preset time period and update the index corresponding to the reading material.

[0018] By adopting the above technical solution, by collecting the user's reading behavior data, and building the user's personalized reading portrait based on the reading behavior data, and analyzing the personalized reading portrait based on the preset reading prediction model to obtain the user's reading prediction data, it is possible to more accurately capture the user's interests and needs, and then provide personalized basic data for the recommendation system, thereby improving the accuracy and relevance of the recommended content; by matching and generating corresponding recommended reading materials based on the user's personalized reading portrait and reading prediction data, it is possible to ensure that the recommended content is highly matched with the user's interests, thereby improving user satisfaction and reading experience; by dividing the reading behavior data and recommended reading materials into stages, and dynamically adjusting the recommended reading materials when the user completes the preset stage reading, it is possible to update the recommended content in real time based on the user's current interest changes, thereby enhancing the flexibility and response speed of the recommendation system; by updating the reading material library according to the preset time period and updating the corresponding index of the reading material, it is possible to ensure that the recommendation system continues to provide the latest and diverse reading content, thereby improving the timeliness and breadth of the system's content.

[0019] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned personalized reading recommendation method when executing the computer program.

[0020] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which implements the steps of the personalized reading recommendation method when executed by a processor.

[0021] In summary, this application includes the following beneficial technical effects: 1. By collecting the reading behavior data of users, and building personalized reading portraits of users based on the reading behavior data, and analyzing the personalized reading portraits based on the preset reading prediction model to obtain the reading prediction data of users, it is possible to more accurately capture the interests and needs of users, and then provide personalized basic data for the recommendation system, thereby improving the accuracy and relevance of recommended content; by matching and generating corresponding recommended reading materials based on the personalized reading portraits and reading prediction data of users, it is possible to ensure that the recommended content is highly matched with the interests of users, thereby improving user satisfaction and reading experience; by dividing the reading behavior data and recommended reading materials into stages, and dynamically adjusting the recommended reading materials when the user completes the reading of the preset stages, it is possible to update the recommended content in real time based on the current changes in the user's interests, thereby enhancing the flexibility and responsiveness of the recommendation system; by updating the reading material library according to the preset time period and updating the corresponding index of the reading materials, it is possible to ensure that the recommendation system continues to provide the latest and diverse reading content, thereby improving the timeliness and breadth of the system's content; 2. By extracting reading feature data from reading behavior data and classifying the reading feature data, a personalized reading profile of the user is constructed based on the classified reading feature data, which can analyze the user's reading preferences and behavior patterns in more detail, thereby providing stronger support for the precise matching of subsequent recommended content; by inputting the personalized reading profile into the reading prediction model and analyzing the behavior patterns of the personalized reading profile to obtain reading prediction data, the user's future reading interests and needs can be predicted in real time, thereby adjusting the recommended content in advance and improving the accuracy and efficiency of personalized recommendations; 3. By obtaining the user's historical reading behavior data and classifying the reading behavior data according to the user's reading preference type, different types of model training data sets can be obtained, which can provide more accurate and targeted training data for the machine learning model, thereby improving the response speed and accuracy of the prediction model to changes in user interests; by iteratively training the preset machine learning algorithm according to the model training data set, a reading prediction model is obtained, which can optimize the adaptability of the recommendation system in different user groups, so that the model maintains efficient recommendation accuracy and stability in the changing reading needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a personalized reading recommendation method in an embodiment of the present application; Figure 2 is a flowchart for implementing step S10 in the personalized reading recommendation method in one embodiment of the present application; Figure 3 This is a flowchart for implementing the construction of a reading prediction model in a personalized reading recommendation method in one embodiment of the present application; Figure 4 is a flowchart for implementing step S20 in the personalized reading recommendation method in one embodiment of the present application; Figure 5 is a flowchart for implementing step S30 in the personalized reading recommendation method in one embodiment of the present application; Figure 6 is a flowchart for implementing step S31 in the personalized reading recommendation method in one embodiment of the present application; Figure 7 This is a principle block diagram of a personalized reading recommendation system in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses a personalized reading recommendation method, which specifically includes the following steps: S10: Collect the user's reading behavior data, build a personalized reading portrait of the user based on the reading behavior data, and analyze the personalized reading portrait based on a preset reading prediction model to obtain the user's reading prediction data.

[0025] Specifically, by collecting the user's reading history over a period of time, such as the category, duration, frequency and other information of the articles the user has read, a basic reading profile of the user is established, which covers the user's interests, preferred content, reading habits, etc., and then by inputting these data into a preset reading prediction model, the model will learn and analyze the user's reading behavior patterns, thereby predicting the user's future reading interests and preferences, and generating the user's reading prediction data.

[0026] S20: Based on the user's personalized reading portrait and reading prediction data, match and generate corresponding recommended reading materials.

[0027] Specifically, the model will match the user's personalized reading profile and reading prediction data. The model will filter out candidate materials that meet the user's needs from the material library based on these data, and then prioritize these candidate materials according to the intensity of the user's interest. The system will select the content that best meets the current user's interests and needs, generate a recommendation list, and finally display the recommendation list to the user.

[0028] S30: Divide the reading behavior data and recommended reading materials into stages, and dynamically adjust the recommended reading materials to match the user's current reading progress and reading interests when the user completes the reading of a preset stage.

[0029] Specifically, when dividing the user's reading behavior data into stages, it is divided into different stages according to the user's actual reading progress and the category of reading content, such as the initial interest stage, in-depth reading stage, and long-term reading stage, etc., and the division of recommended reading materials is dynamically adjusted according to the user's needs at each stage. Specifically, if the user completes the reading task of a certain stage, the system will update the recommended content based on his feedback and behavior patterns at that stage, so that the recommended content is in line with the user's current reading progress and interests.

[0030] S40: updating the reading material library according to a preset time period, and updating the index corresponding to the reading material.

[0031] Specifically, the reading material library is updated regularly, and the cycle can be set to daily, weekly or monthly. The system will add new reading resources to the material library based on new reading content and user needs, and classify and organize existing materials. At the same time, it will update the index information of the materials to ensure that users obtain the latest and most relevant content.

[0032] In one embodiment, if Figure 2 As shown, in step S10, a personalized reading portrait of the user is constructed based on the reading behavior data, and the personalized reading portrait is analyzed based on a preset reading prediction model to obtain the user's reading prediction data, which specifically includes: S11: extract reading feature data from the reading behavior data, classify the reading feature data, and build a personalized reading profile of the user based on the classified reading feature data.

[0033] Specifically, some key features are extracted from the user's historical reading data, such as the user's preferred article topics, reading time, number of articles read each time, marking and commenting behaviors, etc. These feature data are then classified and organized according to dimensions such as interest type, time period, and interaction intensity. Finally, a multi-dimensional personalized reading portrait is constructed, which can reflect the user's specific preferences and needs.

[0034] S12: Input the personalized reading portrait into the reading prediction model, and obtain the reading prediction data by analyzing the behavior pattern of the personalized reading portrait.

[0035] Specifically, the constructed personalized reading portrait is used as input and analyzed through the preset reading prediction model. The model infers the user's future reading interests and needs based on the statistical characteristics of the user's historical behavior. The model will conduct an in-depth analysis of this data, identify the patterns and rules, and generate corresponding reading prediction data. This data includes not only the user's short-term interests, but also covers the user's potential long-term preferences.

[0036] In one embodiment, if Figure 3 As shown in the figure, the construction of the reading prediction model includes: S101: Obtain historical reading behavior data of a user, and classify the reading behavior data according to the user's reading preference type to obtain different types of model training data sets.

[0037] Specifically, by analyzing the user's historical behavior data, we extract the user's reading preference data in different time periods, such as their preferred article types, topics and authors. These data are further classified into several different groups, such as novels, history, science and technology, etc., and then different training data sets are generated based on these classified data for subsequent model training.

[0038] S102: Iteratively train a preset machine learning algorithm according to a model training data set to obtain a reading prediction model.

[0039] Specifically, by inputting the above classified training data set into the preset machine learning algorithm, the model is optimized using iterative training. The model will go through multiple iterations, continuously adjusting parameters and updating learning results until the model can accurately predict the user's reading interests and preferences, and finally obtain a reading prediction model for recommendation.

[0040] In one embodiment, if Figure 4 As shown, in step S20, corresponding recommended reading materials are matched and generated based on the user's personalized reading portrait and reading prediction data, specifically including: S21: According to the reading prediction data, matching recommended reading materials that meet the reading prediction data.

[0041] Specifically, based on the generated reading prediction data, the system will compare the user's current reading needs with the resources in the material library, and screen out candidate materials that meet the current predicted interests. The selection of candidate materials will comprehensively consider the user's historical behavior and current interests to ensure that the recommended content best meets user needs.

[0042] S22: Sort the reading preferences based on the personalized reading portrait, and display the recommended reading materials in order from high to low.

[0043] Specifically, recommended reading materials will be sorted according to the reading preferences in the user portrait, usually weighted by factors such as relevance, the degree of match with user interests, and the user's past interactive behavior. Finally, the sorted recommended reading materials will be displayed to the user in sequence to ensure the accuracy and timeliness of the content.

[0044] In one embodiment, if Figure 5 As shown, in step S30, the reading behavior data and the recommended reading materials are divided into stages, and when the user completes the reading of the preset stage, the recommended reading materials are dynamically adjusted, specifically including: S31: Obtain the user's historical reading preferences, associate the user's reading behavior data with the historical reading preferences, identify the user's reading behavior pattern through time series analysis, and divide the reading behavior pattern into multiple learning stages.

[0045] Specifically, by combining the user's historical reading preferences with the current reading behavior data, a similarity calculation algorithm is used to associate the two to generate a related data set; then the data is processed using a time series analysis algorithm, divided according to the chronological order of the user's behavior, and the changes in the user's reading interests are identified. Finally, the user's behavior patterns are divided into multiple stages, such as the initial interest stage, the in-depth reading stage, etc.

[0046] S32: When the user completes the current stage of reading, the user's reading interaction behavior is obtained, and the reading interaction behavior is analyzed through an incremental learning mechanism to determine the user's deep reading interest.

[0047] Specifically, when a user completes a reading task, the system will use an incremental learning algorithm to analyze the feedback information in real time based on the user's interactive behavior, such as annotations, comments, likes, and other data, and extract the user's deep interests. The incremental learning mechanism can automatically update the model and adjust the recommendation strategy so that the recommended content can more accurately match the user's real interests.

[0048] S33: Further adjust the recommended reading materials based on in-depth reading interests.

[0049] Specifically, based on the deep interests obtained from user interactive behaviors, the system will recalculate and adjust the weights of recommended materials, giving priority to content that users are deeply interested in, ensuring that the recommended content better meets user needs.

[0050] In one embodiment, if Figure 6 As shown, in step S31, the user's reading behavior data is associated with the historical reading preference, the user's reading behavior pattern is identified through time series analysis, and the reading behavior pattern is divided into multiple learning stages, specifically including: S311: Use a similarity calculation algorithm to match the user's historical reading preference data with the user's reading behavior data to generate a related data set.

[0051] Specifically, a similarity calculation algorithm, such as cosine similarity, is used to generate a related data set by comparing the user's reading interests and behavior data based on the user's historical behavior and preference data for subsequent time series analysis.

[0052] S312: Perform time series analysis on the associated data set, arrange the reading behavior data in chronological order, and group them according to preset time intervals, compare the behavior characteristics of users in each time interval, and identify changes in user behavior patterns.

[0053] Specifically, the user's reading data is sorted in chronological order and grouped in time intervals such as days, weeks, and months. Through the time series analysis model, the behavioral differences in each time period are compared to identify the fluctuations and changes in user interests.

[0054] S313: Based on the change of the user's behavior pattern, the user's reading behavior pattern is divided into multiple learning stages according to significant change points of the user's behavior pattern.

[0055] Specifically, based on the results of time series analysis, the system will divide the stages according to the significant turning points of user interest changes. Each stage will be marked as a specific learning stage, such as the initial stage, in-depth stage, continuous stage, etc., to ensure that the recommendation system can flexibly adapt to the different needs of users.

[0056] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0057] In one embodiment, a personalized reading recommendation system is provided, and the personalized reading recommendation system corresponds one-to-one to the personalized reading recommendation method in the above embodiment. Figure 7 As shown, the personalized reading recommendation system includes a user behavior data collection module, a recommended material generation module, a stage division and adjustment module, and a material library update module. The detailed description of each functional module is as follows: A user behavior data collection module is used to collect the user's reading behavior data, build a personalized reading portrait of the user based on the reading behavior data, and analyze the personalized reading portrait based on a preset reading prediction model to obtain the user's reading prediction data; A recommended material generation module is used to match and generate corresponding recommended reading materials based on the user's personalized reading profile and reading prediction data; The stage division and adjustment module is used to divide the reading behavior data and recommended reading materials into stages, and dynamically adjust the recommended reading materials to match the user's current reading progress and reading interests when the user completes the preset stage of reading; The material library updating module is used to update the reading material library according to a preset time period and update the index corresponding to the reading material.

[0058] Optionally, the user behavior data collection module specifically includes: The feature data extraction submodule is used to extract reading feature data from the reading behavior data, classify the reading feature data, and build a personalized reading profile of the user based on the classified reading feature data; The prediction model analysis submodule is used to input the personalized reading portrait into the reading prediction model and obtain the reading prediction data by analyzing the behavior pattern of the personalized reading portrait.

[0059] Optionally, read about building a predictive model, including: The historical data classification module is used to obtain the user's historical reading behavior data and classify the reading behavior data according to the user's reading preference type to obtain different types of model training data sets; The model training module is used to iteratively train the preset machine learning algorithm according to the model training data set to obtain a reading prediction model.

[0060] Optionally, the recommended material generation module specifically includes: A recommendation matching submodule is used to match recommended reading materials that meet the reading prediction data according to the reading prediction data; The sorting and display submodule is used to sort the reading preferences based on the personalized reading portrait, and to display the recommended reading materials in order from high to low.

[0061] Optionally, the stage division and adjustment module specifically includes: The historical preference association submodule is used to obtain the user's historical reading preferences, associate the user's reading behavior data with the historical reading preferences, identify the user's reading behavior pattern through time series analysis, and divide the reading behavior pattern into multiple learning stages; The incremental learning analysis submodule is used to obtain the user's reading interaction behavior when the user completes the current stage of reading, analyze the reading interaction behavior through the incremental learning mechanism, and determine the user's deep reading interest; The recommendation adjustment submodule is used to further adjust the recommended reading materials based on in-depth reading interests.

[0062] Optionally, the historical preference association submodule specifically includes: A similarity calculation unit, used to match the user's historical reading preference data with the user's reading behavior data using a similarity calculation algorithm to generate a related data set; A time series analysis unit is used to perform time series analysis on the associated data set, arrange the reading behavior data in chronological order, and group them according to preset time intervals, compare the behavior characteristics of users in each time interval, and identify changes in user behavior patterns; The stage division unit is used to divide the user's reading behavior pattern into multiple learning stages based on the changes in the user's behavior pattern and according to significant change points in the user's behavior pattern.

[0063] For the specific definition of the personalized reading recommendation system, please refer to the definition of the personalized reading recommendation method above, which will not be repeated here. Each module in the above-mentioned personalized reading recommendation system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0064] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a personalized reading recommendation method is implemented.

[0065] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Collect the user's reading behavior data, build a personalized reading profile of the user based on the reading behavior data, and analyze the personalized reading profile based on a preset reading prediction model to obtain the user's reading prediction data; Match and generate corresponding recommended reading materials based on the user's personalized reading profile and reading prediction data; Divide reading behavior data and recommended reading materials into stages, and dynamically adjust recommended reading materials to match the user's current reading progress and reading interests when the user completes the preset stage of reading; Update the reading material library according to a preset time period and update the index corresponding to the reading material.

[0066] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Collect the user's reading behavior data, build a personalized reading profile of the user based on the reading behavior data, and analyze the personalized reading profile based on a preset reading prediction model to obtain the user's reading prediction data; Match and generate corresponding recommended reading materials based on the user's personalized reading profile and reading prediction data; Divide reading behavior data and recommended reading materials into stages, and dynamically adjust recommended reading materials to match the user's current reading progress and reading interests when the user completes the preset stage of reading; Update the reading material library according to a preset time period and update the index corresponding to the reading material.

[0067] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0068] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0069] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A personalized reading recommendation method, characterized in that: The personalized reading recommendation method comprises: Collecting the user's reading behavior data, constructing a personalized reading profile of the user according to the reading behavior data, and analyzing the personalized reading profile based on a preset reading prediction model to obtain the user's reading prediction data; Based on the personalized reading portrait of the user and the reading prediction data, matching and generating corresponding recommended reading materials; Divide the reading behavior data and the recommended reading materials into stages, and dynamically adjust the recommended reading materials to match the user's current reading progress and reading interests when the user completes the reading of a preset stage; Update the reading material library according to a preset time period and update the index corresponding to the reading material.

2. The personalized reading recommendation method according to claim 1, characterized in that: The step of constructing a personalized reading portrait of the user according to the reading behavior data, and analyzing the personalized reading portrait based on a preset reading prediction model to obtain the reading prediction data of the user specifically includes: Extracting reading feature data from the reading behavior data, classifying the reading feature data, and constructing the personalized reading portrait of the user based on the classified reading feature data; The personalized reading portrait is input into the reading prediction model, and the reading prediction data is obtained by analyzing the behavior pattern of the personalized reading portrait.

3. The personalized reading recommendation method according to claim 2, characterized in that: The construction of the reading prediction model specifically includes: Acquire the historical reading behavior data of the user, and classify the reading behavior data according to the reading preference type of the user to obtain different types of model training data sets; The preset machine learning algorithm is iteratively trained according to the model training data set to obtain the reading prediction model.

4. The personalized reading recommendation method according to claim 1, characterized in that: The matching and generating corresponding recommended reading materials based on the personalized reading portrait of the user and the reading prediction data specifically includes: According to the reading prediction data, matching the recommended reading materials that meet the reading prediction data; The reading preferences of the personalized reading portrait are sorted, and the recommended reading materials are displayed in order from high to low.

5. The personalized reading recommendation method according to claim 1, characterized in that: The step of dividing the reading behavior data and the recommended reading materials into stages, and dynamically adjusting the recommended reading materials when the user completes the reading of a preset stage, specifically includes: Acquire the historical reading preferences of the user, associate the reading behavior data of the user with the historical reading preferences, identify the reading behavior pattern of the user through time series analysis, and divide the reading behavior pattern into multiple learning stages; When the user completes the current stage of reading, the reading interaction behavior of the user is obtained, and the reading interaction behavior is analyzed through an incremental learning mechanism to determine the user's in-depth reading interest; Based on the in-depth reading interest, the recommended reading material is further adjusted.

6. The personalized reading recommendation method according to claim 1, characterized in that: The associating the reading behavior data of the user with the historical reading preference, identifying the reading behavior pattern of the user through time series analysis, and dividing the reading behavior pattern into multiple learning stages specifically includes: Using a similarity calculation algorithm to match the user's historical reading preference data with the user's reading behavior data to generate a related data set; Performing time series analysis on the associated data set, arranging the reading behavior data in chronological order, and grouping them according to preset time intervals, comparing the behavior characteristics of the users in each time interval, and identifying changes in user behavior patterns; Based on the changes in the user behavior pattern, the user's reading behavior pattern is divided into multiple learning stages according to significant change points in the user behavior pattern.

7. A personalized reading recommendation system, characterized in that: The personalized reading recommendation system includes: A user behavior data collection module is used to collect the user's reading behavior data, construct a personalized reading profile of the user according to the reading behavior data, and analyze the personalized reading profile based on a preset reading prediction model to obtain the user's reading prediction data; A recommended material generation module, used to match and generate corresponding recommended reading materials based on the personalized reading portrait of the user and the reading prediction data; A stage division and adjustment module, for dividing the reading behavior data and the recommended reading materials into stages, and dynamically adjusting the recommended reading materials to match the current reading progress and reading interests of the user when the user completes the reading of a preset stage; The material library updating module is used to update the reading material library according to a preset time period and update the index corresponding to the reading material.

8. The personalized reading recommendation system according to claim 7, characterized in that: The user behavior data collection module specifically includes: A feature data extraction submodule, used to extract reading feature data from the reading behavior data, classify the reading feature data, and construct the personalized reading portrait of the user based on the classified reading feature data; The prediction model analysis submodule is used to input the personalized reading portrait into the reading prediction model, and obtain the reading prediction data by analyzing the behavior pattern of the personalized reading portrait.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the personalized reading recommendation method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the personalized reading recommendation method according to any one of claims 1 to 6 are implemented.

Images