An AI-based automated course recommendation management system and method

Abstract

This invention discloses an automated course recommendation management system and method based on artificial intelligence, belonging to the field of artificial intelligence technology. The invention includes an information tagging module, an edge database module, a time-segmentation analysis module, an intelligent push module, and an error feedback module. The information tagging module collects user information and user browsing information records. The edge database module stores the collected user information and browsing information records. The time-segmentation analysis module analyzes user usage of the course app, information browsing types, and browsing habits. The intelligent push module dynamically adjusts the course app's information push mode based on users' course app usage habits and information reception habits at different times. The error feedback module periodically analyzes the errors in the information pushed to users and provides feedback on these errors. This invention enables intelligent push of information content based on user habits during the course app usage process.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to an automated course recommendation management system and method based on artificial intelligence. Background Technology

[0002] Artificial intelligence-based automated course recommendation refers to using artificial intelligence technology to analyze user behavior and interest data, automatically generating personalized recommendation schemes, and achieving efficient and accurate course matching.

[0003] Currently, with the development of people's course needs, internet companies are paying particular attention to achieving real-time online and offline course interaction and instant push of new information. This is an opportunity of the new era, but it also brings many troubles. Due to the high openness of instant course text and images, short course videos, and live course broadcasts, the number of users participating is huge, and the amount of information brought by such a large number of users is quite "explosive". If such a huge amount of information is not filtered and targeted to users, the instant information and real-time interactive information received by each user on the course app will be quite messy. Therefore, there is an urgent need for a method to dynamically adjust the information push of the course app according to the information needs of users at different stages. Summary of the Invention

[0004] The purpose of this invention is to provide an automated course recommendation management system and method based on artificial intelligence to solve the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] An AI-based automated course recommendation and management system includes an information tagging module, an edge database module, a time period analysis module, an intelligent push module, and an error feedback module.

[0007] The information tagging module is used to collect user information and user browsing information records; the edge database module is used to store the collected user information and browsing information records in the user edge database; the time period analysis module is used to analyze the information content and browsing habits of users during different time periods when they use the course app; the intelligent push module dynamically adjusts the course app information push mode based on users' course app usage habits and information acceptance habits during different time periods; the error feedback module periodically analyzes the error situation of the information pushed to users and provides feedback on the error situation.

[0008] The information tagging module is connected to the edge database module; the edge database module is connected to the time period analysis module; the time period analysis module is connected to the intelligent streaming module; and the intelligent streaming module is connected to the error feedback module.

[0009] The information tagging module includes a user information collection unit and a user browsing information recording unit. The user information collection unit is used to collect the user's real-name information and verify its authenticity when the user uses the course app for the first time. The user browsing information recording unit is used to record the type of information browsed, the duration of browsing a single piece of information, the total duration of a single piece of information, the duration of a single use of the course app, and the time period during which the user uses the course app when browsing information. The user browsing information includes text and image information, video information, and live broadcast information.

[0010] The edge database module includes a user information repository and a user habit record repository; the user information repository is used to store the identity information collected by users of the course app; the user habit record repository is used to store the content of the information browsed by users when using the course app to receive information, as well as the users' personal habits and browsing operations when browsing information.

[0011] The time period analysis module includes a time period usage habit analysis unit and a multi-time period information reception analysis unit. The time period usage habit analysis unit analyzes the user's usage of the course app in different time periods, including analyzing the fragmentation of the user's time using the course app and judging the user's level of focus when using the course app. The multi-time period information reception analysis unit analyzes the user's information reception needs in different time periods based on the type and duration of information received by the user in different time periods.

[0012] The intelligent streaming module includes a multi-time period information streaming unit and a predictive information judgment unit; the multi-time period information streaming unit pushes information content that users are interested in based on the information receiving type and browsing habits of users at different times; the predictive information judgment unit judges the push of a information items based on the user's current level of focus on the information being browsed, where a is a constant.

[0013] The error feedback module includes a streaming error analysis unit and a dynamic correction unit. The streaming error analysis unit determines whether a user pays attention to a single piece of information based on the duration and actions the user takes to view the information in the course app's intelligent streaming feed, and calculates the error of the course app's intelligent streaming feed by statistically analyzing the percentage of information the user does not pay attention to in different time periods. The dynamic correction unit performs similar filtering on information that the user does not pay attention to in different time periods, and records the filtered information in the edge database and links it with the user information. The filtered information is stored in the database and updated periodically, with the new information overwriting the old information.

[0014] An AI-based method for automated course recommendation and management, comprising the following steps:

[0015] S100. For users who are using the course app for the first time, request authorization from the user to provide real-name information and browse data collection; after the user authorizes the authorization, collect the user's identity information and the user's habits of receiving information using the course app, and store the collected data in the database;

[0016] S200: Analyze the types of information and browsing habits of users at different times, and intelligently push information services to users based on the analysis results;

[0017] S300: Perform error analysis on the push information service and dynamically correct the error based on the results of the error analysis.

[0018] The specific steps in S100 for collecting the identity information of first-time users of the course app and their habits of receiving information using the course app, and storing the collected data in the database, are as follows:

[0019] S101. When a user downloads and uses the course app for the first time, a pop-up window requests the user's real-name information and authorization to access the user's browsing history on the course app. After obtaining the user's authorization, the system collects the user's identity information, including the user's name, gender, ID number, and contact information. The system verifies the authenticity of the collected user identity information in the background. If the information is correct, the user information collection is successful; otherwise, the system re-collects the information until authentication is successful. The collected user identity information is stored in an edge database close to the user's device in the network. Storing the data in an edge database facilitates retrieval and storage, and can achieve low latency.

[0020] S102. After successfully collecting and authenticating user identity information, the user's browsing information type and browsing operation are recorded and learned over a period of T. The recorded time period, duration of each use, and type of information browsed by the user using the course app are stored in an edge database close to the user's end.

[0021] The specific steps in S200 for analyzing the types of information and browsing habits of users at different times, and intelligently pushing information services to users based on the analysis results, are as follows:

[0022] S201. Retrieve user data from the database, including the app usage patterns throughout the day, the types of information viewed by users at different times (c), the duration of each view (t), and the duration of each view. The K-means clustering algorithm was used to classify users' course app usage across multiple time periods throughout the day within period T. Based on the classification results, the time periods for users to use the course app throughout the day were divided into concentrated information reception periods and scattered information reception periods. The average duration of course app usage during the concentrated information reception periods was calculated based on statistical data. The average duration of user time using the course app during fragmented information reception periods. ;

[0023] S202, through formula Calculate the user's focus level for a single message; the course app uses big data to identify the core information points of different types of single messages. Implantation; via formula Calculate the proportion of core information in a single message; according to the formula Calculate the required browsing time for a single piece of information at different browsing ratios. Where v is the browsing multiplier used by the user when browsing information; and t represents the duration t of browsing a single piece of information versus the single-multiplier browsing duration of that single piece of information. and multiplier browsing time Perform size comparison; among which, The preceding section defines the setup time for the information. This setup time refers to the duration of the information content from the beginning of the information to the core information point. The time allotted for the subsequent explanation of the core information is as follows. The duration of the core information content of a single message;

[0024] When the user browses at 1x speed, if If a user has performed one or more complete browsing actions on the current information, then the user's focus level is [high / low]. If the user is interested in the current information, then the user is interested in the current information; if Then calculate the user's focus level q on the current information and the proportion w of core information in the current information; if If the user is not interested in the current information, then the user is not interested in the current information. If the user's focus on a single piece of information is less than 1 but greater than the proportion of the core information in that information, it means that the user is interested in the current information, but only in the core information, so the user will drag the progress bar.

[0025] When the user's browsing speed is v, calculate the required browsing time for the information at the current speed. ;like If a user has performed one or more complete browsing actions on the current information, then the user's focus level is [high / low]. If the user is interested in the current information, then the user is interested in the current information; if Through formula Calculate the user's level of focus on the current information; where, This represents the user's focus level when browsing information at multiple browsing speeds; expressed by the formula... Calculate the proportion of core information in a single message at multiple browsing speeds; if If the user is not interested in the current information, then the user is not interested in the current information. If so, the user is dragging the progress bar for the current information;

[0026] S203. Based on the user's level of focus when receiving information, and The information was filtered out, and the set of information types of interest viewed by users at different times was statistically analyzed. and Where c represents the set of information types for the centralized information reception period. This is a collection of information types for fragmented information reception periods. ;

[0027] Based on the number of similar information Using the x-axis as the x-axis and the user's attention level q as the y-axis, a nonlinear regression model was used to obtain the attention decay curve of a user continuously receiving the same type of information; its curve expression is: ,in These are the regression coefficients; calculated on the curve. The value corresponding to b is the integer part of the number of pre-push messages 'a' from the course app; the value is taken on the curve. Time corresponding Value, pair The rounded value is the maximum threshold z for the number of consecutive messages of the same type received by a user; therefore, when the course app provides information pre-push service, it pushes information content that users are interested in to users at different times, with the number of pre-push messages being a, and dynamically adjusts the number of pre-push messages to maintain the number of messages of the same type. When a user's attention level decreases to 0 when receiving the same type of information continuously, it means that the number of information received at this time is the limit for the current user. The course app can use this value to pre-push the number of information to facilitate information control. At the same time, in order to ensure that users do not experience a decrease in user interest due to the continuous appearance of the same type of information while browsing information, the course app limits the number of the same type of information to pre-push the information.

[0028] The specific steps of performing error analysis on the push information service and dynamically correcting the operation based on the error analysis results in S300 are as follows:

[0029] S301. Taking the number of messages 'a' pre-pushed by the course app as a group, randomly query the user's browsing status of m groups of messages within the current period T; calculate the user's focus 'q' under the corresponding browsing multiplier; determine the time period during which the user browses the m groups of messages, and separately count whether it falls within the concentrated information reception period or the scattered information reception period. The amount of information and ; through formula Calculate the error rate of the course app's push notification service; calculate the error rate of the currently randomly selected information group by summing the products of the proportion of error information appearing in the corresponding group and the proportion of errors in the time period of the corresponding group, and use this value to represent the error rate of the entire system; where... This is the error ratio coefficient for the centralized information reception period. This refers to the error ratio coefficient for the period of receiving fragmented information; its calculation formulas are as follows: , ; and Because users spend a significant amount of time on the course app during peak information reception periods, maintaining user engagement and freshness is crucial. Therefore, minimizing error messages is essential, resulting in a higher error rate during this time. When errors occur, they are marked and filtered out according to the same type; when At that time, the pre-push information content is cleaned, and information is recalculated and pushed based on the user's information reception preferences and browsing habits within the current period; among which... Set constants for the system;

[0030] S302. Record the filtered information in the database and update the filtered records periodically T. The update method is to overwrite the old data with the new data. Since the user's focus on different information changes with the type and quantity of information they browse in different periods, information that the user is not interested in in different periods is temporarily filtered out and recorded. In the next period, the old records are overwritten with the new filtered records. This cycle is repeated to ensure that the types of information that the user browses are diverse.

[0031] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention achieves the classification of the fragmentation of user time periods when using the course app through the joint action of multiple modules, and analyzes the user's focus on information in different time periods; by calculating the user's focus on different information values, it classifies the types and content of information that the user is interested in in different time periods; by analyzing the degree of change in the user's focus on the same type of information, it calculates the number of pre-push information and the limit on the number of pushes of the same type of information in the course app's background; by randomly sampling historical browsing data in the user's usage cycle, it calculates the error of the course app's push in the current cycle, and by comparing the calculation results with the threshold, it dynamically adjusts the information push for the user; this invention combines multi-functional modules and analysis methods to achieve intelligent push of information content based on the user's habits during the use of the course app. Attached Figure Description

[0032] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0033] Figure 1 This is a schematic diagram of the structure of an automated course recommendation management system based on artificial intelligence according to the present invention;

[0034] Figure 2 This is a flowchart illustrating the steps of an AI-based automated course recommendation and management method according to the present invention. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] Please see Figures 1-2 The present invention provides the following technical solution:

[0037] An AI-based automated course recommendation and management system includes an information tagging module, an edge database module, a time period analysis module, an intelligent push module, and an error feedback module.

[0038] The information tagging module is used to collect user information and user browsing information records; the edge database module is used to store the collected user information and browsing information records in the user edge database; the time period analysis module is used to analyze the information content and browsing habits of users during different time periods when they use the course app; the intelligent push module dynamically adjusts the course app information push mode based on users' course app usage habits and information acceptance habits during different time periods; the error feedback module periodically analyzes the error situation of the information pushed to users and provides feedback on the error situation.

[0039] The information tagging module is connected to the edge database module; the edge database module is connected to the time period analysis module; the time period analysis module is connected to the intelligent streaming module; and the intelligent streaming module is connected to the error feedback module.

[0040] The information tagging module includes a user information collection unit and a user browsing information recording unit. The user information collection unit is used to collect the user's real-name information and verify its authenticity when the user uses the course app for the first time. The user browsing information recording unit is used to record the type of information browsed, the duration of browsing a single piece of information, the total duration of a single piece of information, the duration of a single use of the course app, and the time period during which the user uses the course app when browsing information. The user browsing information includes text and image information, video information, and live broadcast information.

[0041] The edge database module includes a user information repository and a user habit record repository; the user information repository is used to store the identity information collected by users of the course app; the user habit record repository is used to store the content of the information browsed by users when using the course app to receive information, as well as the users' personal habits and browsing operations when browsing information.

[0042] The time period analysis module includes a time period usage habit analysis unit and a multi-time period information reception analysis unit. The time period usage habit analysis unit analyzes the user's usage of the course app in different time periods, including analyzing the fragmentation of the user's time using the course app and judging the user's level of focus when using the course app. The multi-time period information reception analysis unit analyzes the user's information reception needs in different time periods based on the type and duration of information received by the user in different time periods.

[0043] The intelligent streaming module includes a multi-time period information streaming unit and a predictive information judgment unit; the multi-time period information streaming unit pushes information content that users are interested in based on the information receiving type and browsing habits of users at different times; the predictive information judgment unit judges the push of a information items based on the user's current level of focus on the information being browsed, where a is a constant.

[0044] The error feedback module includes a streaming error analysis unit and a dynamic correction unit. The streaming error analysis unit determines whether a user pays attention to a single piece of information based on the duration and actions the user takes to view the information in the course app's intelligent streaming feed, and calculates the error of the course app's intelligent streaming feed by statistically analyzing the percentage of information the user does not pay attention to in different time periods. The dynamic correction unit performs similar filtering on information that the user does not pay attention to in different time periods, and records the filtered information in the edge database and links it with the user information. The filtered information is stored in the database and updated periodically, with the new information overwriting the old information.

[0045] An AI-based method for automated course recommendation and management, comprising the following steps:

[0046] S100. For users who are using the course app for the first time, request authorization from the user to provide real-name information and browse data collection; after the user authorizes the authorization, collect the user's identity information and the user's habits of receiving information using the course app, and store the collected data in the database;

[0047] S200: Analyze the types of information and browsing habits of users at different times, and intelligently push information services to users based on the analysis results;

[0048] S300: Perform error analysis on the push information service and dynamically correct the error based on the results of the error analysis.

[0049] The specific steps in S100 for collecting the identity information of first-time users of the course app and their habits of receiving information using the course app, and storing the collected data in the database, are as follows:

[0050] S101. When a user downloads and uses the course app for the first time, a pop-up window requests the user's real-name information and authorization to access the user's browsing history on the course app. After obtaining the user's authorization, the system collects the user's identity information, including the user's name, gender, ID number, and contact information. The system verifies the authenticity of the collected user identity information in the background. If the information is correct, the user information collection is successful; otherwise, the system re-collects the information until authentication is successful. The collected user identity information is stored in an edge database close to the user's device in the network. Storing the data in an edge database facilitates retrieval and storage, and can achieve low latency.

[0051] S102. After successfully collecting and authenticating user identity information, the user's browsing information type and browsing operation are recorded and learned over a period of T. The recorded time period, duration of each use, and type of information browsed by the user using the course app are stored in an edge database close to the user's end.

[0052] The specific steps in S200 for analyzing the types of information and browsing habits of users at different times, and intelligently pushing information services to users based on the analysis results, are as follows:

[0053] S201. Retrieve user data from the database, including the app usage patterns throughout the day, the types of information viewed by users at different times (c), the duration of each view (t), and the duration of each view. The K-means clustering algorithm was used to classify users' course app usage across multiple time periods throughout the day within period T. Based on the classification results, the time periods for users to use the course app throughout the day were divided into concentrated information reception periods and scattered information reception periods. The average duration of course app usage during the concentrated information reception periods was calculated based on statistical data. The average duration of user time using the course app during fragmented information reception periods. ;

[0054] S202, through formula Calculate the user's focus level for a single message; the course app uses big data to identify the core information points of different types of single messages. Implantation; via formula Calculate the proportion of core information in a single message; according to the formula Calculate the required browsing time for a single piece of information at different browsing ratios. Where v is the browsing multiplier used by the user when browsing information; and t represents the duration t of browsing a single piece of information versus the single-multiplier browsing duration of that single piece of information. and multiplier browsing time Perform size comparison; among which, The preceding section defines the setup time for the information. This setup time refers to the duration of the information content from the beginning of the information to the core information point. The time allotted for the subsequent explanation of the core information is as follows. The duration of the core information content of a single message;

[0055] When the user browses at 1x speed, if If a user has performed one or more complete browsing actions on the current information, then the user's focus level is [high / low]. If the user is interested in the current information, then the user is interested in the current information; if Then calculate the user's focus level q on the current information and the proportion w of core information in the current information; if If the user is not interested in the current information, then the user is not interested in the current information. If the user's focus on a single piece of information is less than 1 but greater than the proportion of the core information in that information, it means that the user is interested in the current information, but only in the core information, so the user will drag the progress bar.

[0056] When the user's browsing speed is v, calculate the required browsing time for the information at the current speed. ;like If a user has performed one or more complete browsing actions on the current information, then the user's focus level is [high / low]. If the user is interested in the current information, then the user is interested in the current information; if Through formula Calculate the user's level of focus on the current information; where, This represents the user's focus level when browsing information at multiple browsing speeds; expressed by the formula... Calculate the proportion of core information in a single message at multiple browsing speeds; if If the user is not interested in the current information, then the user is not interested in the current information. If so, the user is dragging the progress bar for the current information;

[0057] S203. Based on the user's level of focus when receiving information, and The information was filtered out, and the set of information types of interest viewed by users at different times was statistically analyzed. and Where c represents the set of information types for the centralized information reception period. This is a collection of information types for fragmented information reception periods. ;

[0058] Based on the number of similar information Using the x-axis as the x-axis and the user's attention level q as the y-axis, a nonlinear regression model was used to obtain the attention decay curve of a user continuously receiving the same type of information; its curve expression is: ,in These are the regression coefficients; calculated on the curve. The value corresponding to b is the integer part of the number of pre-push messages 'a' from the course app; the value is taken on the curve. Time corresponding Value, pair The rounded value is the maximum threshold z for the number of consecutive messages of the same type received by a user; therefore, when the course app provides information pre-push service, it pushes information content that users are interested in to users at different times, with the number of pre-push messages being a, and dynamically adjusts the number of pre-push messages to maintain the number of messages of the same type. When a user's attention level decreases to 0 when receiving the same type of information continuously, it means that the number of information received at this time is the limit for the current user. The course app can use this value to pre-push the number of information to facilitate information control. At the same time, in order to ensure that users do not experience a decrease in user interest due to the continuous appearance of the same type of information while browsing information, the course app limits the number of the same type of information to pre-push the information.

[0059] The specific steps of performing error analysis on the push information service and dynamically correcting the operation based on the error analysis results in S300 are as follows:

[0060] S301. Taking the number of messages 'a' pre-pushed by the course app as a group, randomly query the user's browsing status of m groups of messages within the current period T; calculate the user's focus 'q' under the corresponding browsing multiplier; determine the time period during which the user browses the m groups of messages, and separately count whether it falls within the concentrated information reception period or the scattered information reception period. The amount of information and ; through formula Calculate the error rate of the course app's push notification service; calculate the error rate of the currently randomly selected information group by summing the products of the proportion of error information appearing in the corresponding group and the proportion of errors in the time period of the corresponding group, and use this value to represent the error rate of the entire system; where... This is the error ratio coefficient for the centralized information reception period. This refers to the error ratio coefficient for the period of receiving fragmented information; its calculation formulas are as follows: , ; and Because users spend a significant amount of time on the course app during peak information reception periods, maintaining user engagement and freshness is crucial. Therefore, minimizing error messages is essential, resulting in a higher error rate during this time. When errors occur, they are marked and filtered out according to the same type; when At that time, the pre-push information content is cleaned, and information is recalculated and pushed based on the user's information reception preferences and browsing habits within the current period; among which... Set constants for the system;

[0061] S302. Record the filtered information in the database and update the filtered records periodically T. The update method is to overwrite the old data with the new data. Since the user's focus on different information changes with the type and quantity of information they browse in different periods, information that the user is not interested in in different periods is temporarily filtered out and recorded. In the next period, the old records are overwritten with the new filtered records. This cycle is repeated to ensure that the types of information that the user browses are diverse.

[0062] In the embodiment:

[0063] If a short video course app has a platform intelligent streaming system based on big data, when a user uses the app for the first time, the user's identity information is collected and authenticated, and the real identity information is stored in an edge database. After user authentication, the information content and habits of the current user are recorded over a period of one day. The concentrated information reception periods are 7-8 am and 6-8 pm, while the scattered information reception periods are 9-11 am, 2-5 pm, and 9-10 pm. The average usage time of the course app during the concentrated information reception periods is 1 hour, and the average usage time during the scattered information reception periods is 1 / 4 hour.

[0064] The types of information viewed by users during the concentrated information reception period are as follows: The types of information viewed during periods of fragmented information reception are: ; Core information points are embedded into the information content through big data; The duration of information received during the centralized information reception period is ; The user's browsing time is The core information point is The duration of the scattered information reception period is... User browsing time is The core information point is The current user is browsing information at a single-speed rate, according to the formula... Calculate the user's focus level during periods of concentrated information reception. Calculate the user's focus level during periods of fragmented information reception. According to the formula Calculate the proportion of core information in the information received during the centralized information reception period. Calculate the proportion of core information in the fragmented information reception period. By comparing user focus and the proportion of core information, the set of information types that users are interested in during concentrated information reception periods is obtained. The set of information types that users are interested in during fragmented information reception periods is: By using nonlinear regression of historical data, with the number of similar information items (b) as the x-axis and the user's attention level (q) as the y-axis, a curve showing the decay of user attention level when continuously receiving similar information is obtained. The curve expression is as follows: ;when Time corresponding The number of pre-push messages from the course app When q takes respectively and When, the value of u is and The maximum threshold for pre-pushing various types of information by the course app during the concentrated information reception period is: The maximum pre-push threshold for each type of information during the period of receiving scattered information is: ;

[0065] Grouping four pieces of information into four sets, four sets of user browsing data were randomly selected from the current day; two sets came from concentrated information reception periods, and two sets came from scattered information reception periods; the data were then statistically analyzed for each set. The amount of information, where one piece of information is not of interest to the user during a concentrated information reception period, and one piece of information is not of interest to the user during a fragmented information reception period; according to the formula Calculate the error ratio coefficient for the centralized information reception period. According to the formula Calculate the error ratio coefficient for the period of receiving scattered information. According to the formula Calculate the error rate of the course app push information service ,because The system then cleans the information content that is pre-pushed to users, and recalculates and pushes information based on the user's preferred information receiving type and browsing habits in the current period.

[0066] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0067] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An automated course recommendation and management method based on artificial intelligence, characterized in that: The method includes the following steps: S100. For users who are using the course app for the first time, request authorization from the user to provide real-name information and browse data collection; after the user authorizes the authorization, collect the user's identity information and the user's habits of receiving information using the course app, and store the collected data in the database; S200: Analyze the types of information and browsing habits of users at different times, and intelligently push information services to users based on the analysis results; The specific steps in S200 for analyzing the types of information and browsing habits of users at different times, and intelligently pushing information services to users based on the analysis results, are as follows: S201. Retrieve user data from the database, including the app usage patterns throughout the day, the types of information viewed by users at different times (c), the duration of each view (t), and the duration of each view. The K-means clustering algorithm was used to classify users' course app usage across multiple time periods throughout the day within period T. Based on the classification results, the time periods for users to use the course app throughout the day were divided into concentrated information reception periods and scattered information reception periods. The average duration of course app usage during the concentrated information reception periods was calculated based on statistical data. The average duration of time users use the course app during periods of fragmented information reception. ; S202, through formula Calculate the user's focus level for a single message; the course app uses big data to identify the core information points of different types of single messages. Implantation; via formula Calculate the proportion of core information in a single message; according to the formula Calculate the required browsing time for a single piece of information at different browsing ratios. Where v is the browsing multiplier used by the user when browsing information; and t represents the duration t of browsing a single piece of information versus the single-multiplier browsing duration of that single piece of information. and multiplier browsing time Perform size comparison; among which, The time spent preparing information beforehand, The time allotted for the subsequent explanation of the core information is as follows. The duration of the core information content of a single message; When the user browses at 1x speed, if If a user has performed one or more complete browsing actions on the current information, then the user's focus level is [high / low]. If the user is interested in the current information, then the user is interested in the current information; if Then calculate the user's focus level q on the current information and the proportion w of core information in the current information; if If the user is not interested in the current information, then the user is not interested in the current information. If so, the user is dragging the progress bar for the current information; When the user's browsing speed is v, calculate the required browsing time for the information at the current speed. ;like If a user has performed one or more complete browsing actions on the current information, then the user's focus level is [high / low]. If the user is interested in the current information, then the user is interested in the current information; if Through formula Calculate the user's level of focus on the current information; where, This represents the user's focus level when browsing information at multiple browsing speeds; expressed by the formula... Calculate the proportion of core information in a single message at multiple browsing speeds; if If the user is not interested in the current information, then the user is not interested in the current information. If so, the user is dragging the progress bar for the current information; S203. Based on the user's level of focus when receiving information, and The information was filtered out, and the set of information types of interest viewed by users at different times was statistically analyzed. and Where c represents the set of information types for the centralized information reception period. This is a collection of information types for fragmented information reception periods. ; Based on the number of similar information Using the x-axis as the x-axis and the user's attention level q as the y-axis, a nonlinear regression model was used to obtain the attention decay curve of a user continuously receiving the same type of information; its curve expression is: ,in These are the regression coefficients; calculated on the curve. The value corresponding to b is the integer part of the number of pre-push messages 'a' from the course app; the value is taken on the curve. Time corresponding The value, rounded down to the nearest integer (b), represents the maximum threshold z for the number of consecutive messages of the same type received by a user. Therefore, when the course app provides pre-push information services, it pushes information content of interest to users at different times, with a pre-push information count of a. The pre-push information is dynamically adjusted to maintain the number of messages of the same type. ; S300: Perform error analysis on the push information service and dynamically correct the error based on the results of the error analysis.

2. The method for automated course recommendation and management based on artificial intelligence according to claim 1, characterized in that: The specific steps in S100 for collecting the identity information of first-time users of the course app and their habits of receiving information using the course app, and storing the collected data in the database, are as follows: S101. When a user downloads and uses the course app for the first time, a pop-up window requests the user's real-name information and authorization to access the user's browsing information records on the course app. After obtaining the user's authorization, the user's identity information is collected, including the user's name, gender, ID card number, and contact information. The collected user identity information is verified for authenticity through the backend. If it is correct, the user information collection is successful. Conversely, if the authentication fails, the data is collected again until successful; the collected user identity information is stored in an edge database close to the user's end in the network. S102. After successfully collecting and authenticating user identity information, the user's browsing information type and browsing operation are recorded and learned over a period of T. The recorded time period, duration of each use, and type of information browsed by the user using the course app are stored in an edge database close to the user's end.

3. The method for automated course recommendation and management based on artificial intelligence according to claim 2, characterized in that: The specific steps of performing error analysis on the push information service and dynamically correcting the operation based on the error analysis results in S300 are as follows: S301. Taking the number of messages 'a' pre-pushed by the course app as a group, randomly query the user's browsing status of m groups of messages within the current period T; calculate the user's focus 'q' under the corresponding browsing multiplier; determine the time period during which the user browses the m groups of messages, and separately count whether it falls within the concentrated information reception period or the scattered information reception period. The amount of information and ; through formula Calculate the error rate of the course app's push notification service; among which, This is the error ratio coefficient for the centralized information reception period. This refers to the error ratio coefficient for the period of receiving fragmented information; its calculation formulas are as follows: , ; and ;when When errors occur, they are marked and filtered out according to the same type; when At that time, the pre-push information content is cleaned, and information is recalculated and pushed based on the user's information reception preferences and browsing habits within the current period; among which... Set constants for the system; S302. Record the screening information in the database and update the screening records periodically for T. The update method is to overwrite the old data with the new data.

4. An AI-based automated course recommendation management system, applied to the AI-based automated course recommendation management method according to any one of claims 1-3, characterized in that: The AI-based automated course recommendation management system includes an information tagging module, an edge database module, a time period analysis module, an intelligent push module, and an error feedback module. The information tagging module is used to collect user information and user browsing information records; the edge database module is used to store the collected user information and browsing information records in the user edge database; The time period analysis module is used to analyze the information content and browsing habits of users during different time periods when they use the course app; the intelligent push module dynamically adjusts the course app information push mode based on users' course app usage habits and information reception habits during different time periods; the error feedback module periodically analyzes the error situation of the information pushed to users and provides feedback on the error situation. The information tagging module is connected to the edge database module; the edge database module is connected to the time period analysis module; The time period analysis module is connected to the intelligent streaming module; the intelligent streaming module is connected to the error feedback module.

5. The course recommendation and management system based on artificial intelligence according to claim 4, characterized in that: The information tagging module includes a user information collection unit and a user browsing information recording unit. The user information collection unit is used to collect the user's real-name information and verify its authenticity when the user uses the course app for the first time. The user browsing information recording unit is used to record the type of information browsed, the duration of browsing a single piece of information, the total duration of a single piece of information, the duration of a single use of the course app, and the time period during which the user uses the course app when browsing information. The user browsing information includes text and image information, video information, and live broadcast information.

6. The course recommendation and management system based on artificial intelligence according to claim 5, characterized in that: The edge database module includes a user information repository and a user habit record repository; the user information repository is used to store the identity information collected by users of the course app. The user habit record database is used to store the content of information viewed by users when receiving information using the course app, as well as the users' personal habits and browsing operations when viewing information.

7. The course recommendation and management system based on artificial intelligence according to claim 6, characterized in that: The time period analysis module includes a time period usage habit analysis unit and a multi-time period information reception analysis unit; The time-period usage habit analysis unit analyzes the user's use of the course app in different time periods, including analyzing the fragmentation of the user's time using the course app and judging the user's level of focus when using the course app; the multi-time period information reception analysis unit analyzes the user's information reception needs in different time periods based on the type and duration of information received by the user in different time periods.

8. The course recommendation and management system based on artificial intelligence according to claim 7, characterized in that: The intelligent streaming module includes a multi-time period information streaming unit and a predictive information judgment unit; the multi-time period information streaming unit pushes information content that users are interested in based on the information receiving type and browsing habits of users at different times; the predictive information judgment unit judges the push of a information items based on the user's current level of focus on the information being browsed, where a is a constant.

9. The course recommendation and management system based on artificial intelligence according to claim 8, characterized in that: The error feedback module includes a streaming error analysis unit and a dynamic correction unit. The streaming error analysis unit determines whether the user pays attention to a single piece of information based on the duration and operation of the user's browsing of the information in the course app's intelligent streaming, and calculates the error of the course app's intelligent streaming by statistically analyzing the occupancy of information that the user does not pay attention to in different time periods. The dynamic correction unit performs similar filtering on information that the user does not pay attention to in different time periods, and records the filtered information in the edge database and links it with the user information; the filtered information is stored in the database and updated periodically, with the new information overwriting the old information.

Images