Custom course system construction method and system

Abstract

The invention relates to the technical field of curriculum construction, and particularly discloses a custom curriculum system construction method and system.The method comprises the steps that browsing data, containing browsing parameters, of a user are obtained based on preset permissions, the browsing data containing the browsing parameters are recognized, and the information amount of each piece of browsing data is determined; obtaining personal information of a user, and determining the integrating degree of each piece of browsing data according to the personal information; selecting browsing data as reference data according to the integrating degree and the information amount, selecting courses in a preset course library based on the reference data, and constructing the course library; using parameters pointing to all courses in the course library are obtained in real time, and the course selection process is adjusted according to the using parameters; according to the method, the browsing data containing the browsing parameters are acquired, the target course is quickly matched in the course library and the course library is constructed in combination with the personal information of the user, and then the course matching process is optimized according to the feedback condition of the user on the course, so that the efficiency and the accuracy are high.

Description

Technical Field

[0001] The present invention relates to the technical field of course construction, and in particular to a method and system for constructing a custom course system. Background Art

[0002] With the improvement of living standards, people's learning needs are gradually increasing, and they often take the initiative to learn new knowledge. With the development of the Internet, online educational resources are extremely rich, making it a normal thing for people to acquire knowledge online.

[0003] Under the existing technical background, everyone has the potential to become a lecturer and share their own technical experience, etc. This makes the course library very large. It is difficult for users to select useful courses from these course libraries. If a convenient course push solution can be provided, it can greatly save users' reference time. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for constructing a customized course system to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for constructing a customized course system, the method comprising:

[0007] Obtaining browsing data containing browsing parameters of the user based on preset permissions, identifying the browsing data containing browsing parameters, and determining the amount of information of each browsing data;

[0008] Obtaining the user's personal information and determining the relevance of each browsing data based on the personal information;

[0009] Selecting browsing data as reference data according to the degree of fit and the amount of information, selecting courses from a preset course library based on the reference data, and constructing a course library;

[0010] The usage parameters pointing to each course in the course library are obtained in real time, and the course selection process is adjusted according to the usage parameters.

[0011] As a further solution of the present invention: the steps of obtaining the browsing data containing browsing parameters of the user based on the preset authority, identifying the browsing data containing browsing parameters, and determining the information volume of each browsing data include:

[0012] Send a browsing data access request to the user and receive the access permission granted by the user;

[0013] Based on the access authority, the browsing data of the user including browsing parameters is obtained; the browsing parameters include browsing duration and a browsing time point set, and the browsing time point in the browsing time point set is the time point at which browsing starts;

[0014] Identifying the browsing parameters and determining the adjustment coefficient;

[0015] Identifying the browsing data, determining the amount of information, and adjusting the amount of information according to the adjustment coefficient;

[0016] The process of determining the adjustment coefficient is as follows:

[0017] Wherein, X is the adjustment coefficient, α is the preset adjustment coefficient, T is the browsing time, and N is the total number of time points in the browsing time point concentration.

[0018] As a further solution of the present invention: the steps of identifying the browsing data, determining the amount of information, and adjusting the amount of information according to the adjustment coefficient include:

[0019] Obtaining the type of browsing data, and when the type is text, calculating the TF-IDF value of each word in the text, counting the TF-IDF values ​​of all words, and generating a value set;

[0020] Calculating the similarity between the browsing data and other browsing data according to the value set, and determining the amount of information according to the similarity;

[0021] When the type is an image sequence, grayscale conversion is performed on each image in the image sequence, and the grayscale mean is calculated to obtain a grayscale mean array;

[0022] Calculate the similarity between the browsing data and other browsing data based on the grayscale mean array, and determine the amount of information according to the similarity;

[0023] The calculation process of the information volume is:

[0024] In the formula, Y is the amount of information, β is the preset adjustment coefficient, E[S] represents the mean of the similarity with other browsing data, σ[S] represents the standard deviation of the similarity with other browsing data; S represents the similarity set with other browsing data, and the number of similarities in the similarity set is the same as the number of other browsing data.

[0025] As a further solution of the present invention: the step of obtaining the user's personal information and determining the degree of fit of each browsing data according to the personal information includes:

[0026] Obtain users' professional and interest tags;

[0027] Extract keywords from each browsing data based on AI model;

[0028] Compare the user's professional tags and interest tags with the keywords of each browsing data, and determine the degree of fit based on the comparison results.

[0029] As a further solution of the present invention: the step of selecting browsing data as reference data according to the degree of fit and the amount of information, selecting courses from a preset course library based on the reference data, and constructing a course library further includes:

[0030] The fit and information content are used as two dependent variables to calculate the evaluation values, which are used to characterize the importance of browsing data;

[0031] Select browsing data whose evaluation value reaches a preset threshold as reference data;

[0032] Read the keywords of the parameter data, match and select courses in the preset course library, and build a course library.

[0033] As a further solution of the present invention: the step of obtaining the usage parameters pointing to each course in the course library in real time and adjusting the course selection process according to the usage parameters comprises:

[0034] Send the course library to the user and obtain the user's browsing parameters for each course as passive usage parameters;

[0035] Obtain the user's operation information on each course as active usage parameters;

[0036] Determining the user's preference for each course according to the passive use parameter and the active use parameter;

[0037] The benchmark selection coefficient of each course in the course library is determined according to the preference; the benchmark selection coefficient is proportional to the preference.

[0038] The technical solution of the present invention also provides a system for building a customized course system, the system comprising:

[0039] An information volume calculation module, used to obtain the browsing data containing browsing parameters of the user based on the preset authority, identify the browsing data containing browsing parameters, and determine the information volume of each browsing data;

[0040] A compatibility calculation module, used to obtain the user's personal information and determine the compatibility of each browsing data according to the personal information;

[0041] A course library construction module, used to select browsing data as reference data according to the degree of fit and the amount of information, select courses from a preset course library based on the reference data, and construct a course library;

[0042] The selection and updating module is used to obtain the usage parameters pointing to each course in the course library in real time and adjust the course selection process according to the usage parameters.

[0043] As a further solution of the present invention: the information volume calculation module includes:

[0044] The permission acquisition unit is used to send a browsing data access request to the user and receive the access permission granted by the user;

[0045] A search execution unit, used for acquiring browsing data containing browsing parameters of the user based on the search authority; the browsing parameters include browsing duration and a browsing time point set, and the browsing time point in the browsing time point set is a time point for starting browsing;

[0046] A parameter identification unit, used to identify the browsing parameter and determine the adjustment coefficient;

[0047] A data identification unit, used to identify the browsing data, determine the amount of information, and adjust the amount of information according to the adjustment coefficient;

[0048] The process of determining the adjustment coefficient is as follows:

[0049] Wherein, X is the adjustment coefficient, α is the preset adjustment coefficient, T is the browsing time, and N is the total number of time points in the browsing time point concentration.

[0050] As a further solution of the present invention: the fit calculation module includes:

[0051] A tag query unit, used to obtain professional tags and interest tags of users;

[0052] A keyword extraction unit, used to extract keywords for each browsing data based on an AI model;

[0053] The comparison unit is used to compare the user's professional tags and interest tags as well as the keywords of each browsing data, and determine the degree of fit based on the comparison results.

[0054] As a further solution of the present invention: the course library construction module includes:

[0055] An evaluation value calculation unit, used to calculate the evaluation value by taking the fit degree and the amount of information as two dependent variables, and used to characterize the importance of the browsing data;

[0056] A selection unit, used to select browsing data whose evaluation value reaches a preset threshold as reference data;

[0057] The matching unit is used to read the keywords of the parameter data, match and select courses in the preset course library, and build a course library.

[0058] Compared with the prior art, the beneficial effects of the present invention are: the present invention obtains browsing data containing browsing parameters based on the granted permissions, combines the user's personal information, quickly matches the target courses in the course library, builds the course library, and then, based on the user's feedback on the courses, optimizes the course matching process with high efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0060] Figure 1 A flowchart of the methodology for building a custom curriculum.

[0061] Figure 2 Build a system diagram for your custom curriculum. DETAILED DESCRIPTION

[0062] Under the existing technical background, everyone has the potential to become a lecturer and share their own technical experience, etc. This makes the course library very large. It is difficult for users to select useful courses from these course libraries. If a convenient course push solution can be provided, it can greatly save users' reference time.

[0063] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] Figure 1 The flowchart of the method for constructing a custom course system is shown in the following figure. In an embodiment of the present invention, a method for constructing a custom course system includes:

[0065] Step S100: obtaining the browsing data of the user containing the browsing parameters based on the preset authority, identifying the browsing data containing the browsing parameters, and determining the information volume of each browsing data;

[0066] Under the premise of having the permission, the user's browsing data and browsing parameters are obtained. The browsing data is the user's daily browsing data in various apps. The daily browsing data can be obtained according to the permissions granted by the user. The browsing parameters reflect how much effort the user spends on each browsing data during the browsing process. By identifying the browsing parameters and browsing data, the amount of information of each browsing data can be calculated.

[0067] Step S200: obtaining the user's personal information, and determining the degree of fit of each browsing data according to the personal information;

[0068] The user's personal information is obtained. The personal information does not involve overly private information such as the user's ID number, and only includes professional tags or interest tags. The personal information can be used to determine the degree of compatibility between each browsing data and the user.

[0069] Step S300: selecting browsing data as reference data according to the degree of fit and the amount of information, selecting courses from a preset course library based on the reference data, and constructing a course library;

[0070] Browsing data can be filtered from two aspects: fit and information volume. Browsing data that fits the user and contains sufficient information can be selected as reference data for creating custom courses. The plan to create custom courses is essentially to combine existing courses and then build a course library that matches the user.

[0071] Step S400: acquiring usage parameters pointing to each course in the course library in real time, and adjusting the course selection process according to the usage parameters;

[0072] After the course library is built, each course in the course library is sent to the user to obtain the user's feedback on each course, which is called usage parameters. Usage parameters can be understood as browsing parameters for each course. The course selection process is adjusted according to the usage parameters, which can continuously optimize the matching degree between the built course library and the user.

[0073] Regarding step S100, the steps of obtaining the browsing data of the user containing the browsing parameters based on the preset authority, identifying the browsing data containing the browsing parameters, and determining the information volume of each browsing data include:

[0074] Send a browsing data access request to the user and receive the access permission granted by the user;

[0075] Based on the access authority, the browsing data of the user including browsing parameters is obtained; the browsing parameters include browsing duration and a browsing time point set, and the browsing time point in the browsing time point set is the time point at which browsing starts;

[0076] Identifying the browsing parameters and determining the adjustment coefficient;

[0077] The browsing data is identified, the amount of information is determined, and the amount of information is adjusted according to the adjustment coefficient.

[0078] A browsing data access request is sent to the user, and the access permission granted by the user is received. The access request is generally a access request directed to a certain App, and the permission authorization process is completed directly by the user; after the user grants the access permission, the user's browsing data containing browsing parameters is obtained based on the access permission. The browsing parameters include browsing time and browsing time point set. The browsing time is the total browsing time of a certain browsing data, and the browsing time point in the browsing time point set is the time point when browsing starts; the browsing time and the browsing time point set are analyzed to calculate the adjustment coefficient, and then the browsing data is identified, the amount of information is calculated, the amount of information is corrected according to the adjustment coefficient, and the final amount of information is obtained.

[0079] The process of determining the adjustment coefficient is as follows:

[0080] Wherein, X is the adjustment coefficient, α is the preset adjustment coefficient, T is the browsing time, and N is the total number of time points in the browsing time point concentration.

[0081] The adjustment coefficient ranges from 0 to 1. It is proportional to the browsing time and the total number of time points in which the browsing time points are concentrated. That is, the longer the browsing time and the greater the total number of time points, the more important the corresponding browsing data is, and the amount of information obtained needs to be adjusted to a greater extent.

[0082] Furthermore, the step of identifying the browsing data, determining the amount of information, and adjusting the amount of information according to the adjustment coefficient includes:

[0083] Obtaining the type of browsing data, and when the type is text, calculating the TF-IDF value of each word in the text, counting the TF-IDF values ​​of all words, and generating a value set;

[0084] Calculating the similarity between the browsing data and other browsing data according to the value set, and determining the amount of information according to the similarity;

[0085] When the type is an image sequence, grayscale conversion is performed on each image in the image sequence, and the grayscale mean is calculated to obtain a grayscale mean array;

[0086] The similarity between the browsing data and other browsing data is calculated based on the grayscale mean array, and the amount of information is determined according to the similarity.

[0087] In the context of prior art, there are two main types of browsing data, one is text data, and the other is image (video) data. For text data, the TF-IDF value of each word in the text is calculated, and the TF-IDF values ​​of all words are counted to obtain a value set. By comparing the value sets corresponding to different browsing data, the similarity between two browsing data can be obtained; wherein TF is term frequency, which refers to the number of times a certain word appears in a certain document, and IDF is inverse document frequency, which is used to measure the prevalence of a certain word in the entire document set. The product of TF and IDF is calculated to obtain the TF-IDF value; this calculation process requires pre-counting all text data, creating a text database, and calculating the TF-IDF value inside the text database.

[0088] When the type is an image sequence, grayscale conversion is performed on each image in the image sequence, and the grayscale mean is calculated to obtain a grayscale mean array, and the similarity between the browsing data and other browsing data is calculated based on the grayscale mean array.

[0089] Finally, no matter what type of browsing data is, it will be converted into its similarity with other browsing data, and the amount of information is determined according to the similarity. The calculation process of the amount of information is:

[0090] In the formula, Y is the amount of information, β is the preset adjustment coefficient, E[S] represents the mean of the similarity with other browsing data, σ[S] represents the standard deviation of the similarity with other browsing data; S represents the similarity set with other browsing data, and the number of similarities in the similarity set is the same as the number of other browsing data.

[0091] Regarding the calculation process of the amount of information, if the mean is smaller, it means the similarity is smaller. At this time, the current browsing data is more unique and the amount of information is greater. If the standard deviation is smaller, it means the similarity is more stable. At this time, it means that the similarity between the current browsing data and other browsing data is almost the same. At this time, it is not particularly unique data and the amount of information is small.

[0092] Regarding step S200, the step of obtaining the user's personal information and determining the degree of fit of each browsing data according to the personal information includes:

[0093] Obtain users' professional and interest tags;

[0094] Extract keywords from each browsing data based on AI model;

[0095] Compare the user's professional tags and interest tags with the keywords of each browsing data, and determine the degree of fit based on the comparison results.

[0096] In one example of the technical solution of the present invention, personal information is limited to professional tags and interest tags, and then the browsing data is input into the existing AI model to extract keywords for each browsing data. The professional tags and keywords are compared, and the interest tags and keywords are compared. The degree of fit can be determined based on whether they are the same or which ones are the same. The more similarities there are, the higher the degree of fit.

[0097] Step S300, the browsing data is selected as reference data according to the degree of fit and the amount of information, and a course is selected from a preset course library based on the reference data. The step of constructing a course library also includes:

[0098] The fit and information content are used as two dependent variables to calculate the evaluation values, which are used to characterize the importance of browsing data;

[0099] Select browsing data whose evaluation value reaches a preset threshold as reference data;

[0100] Read the keywords of the parameter data, match and select courses in the preset course library, and build a course library.

[0101] The evaluation value is calculated by taking the fit and the amount of information as two dependent variables to characterize the importance of the browsed data. The evaluation value is proportional to the fit and the amount of information. The simplest solution is to multiply by a preset coefficient, then superimpose and combine with a preset constant to obtain a binary linear function as the calculation scheme for the evaluation value.

[0102] The evaluation value is compared with the preset threshold. When the evaluation value reaches the preset threshold, the corresponding browsing data is used as reference data; the reference data keywords (obtained in step S200) are read, and the keywords are used as indexes to match and select courses in the course library to obtain the course degree.

[0103] Step S400, the step of obtaining the usage parameters pointing to each course in the course library in real time and adjusting the course selection process according to the usage parameters includes:

[0104] Send the course library to the user and obtain the user's browsing parameters for each course as passive usage parameters;

[0105] Obtain the user's operation information on each course as active usage parameters;

[0106] Determining the user's preference for each course according to the passive use parameter and the active use parameter;

[0107] The benchmark selection coefficient of each course in the course library is determined according to the preference; the benchmark selection coefficient is proportional to the preference.

[0108] After the course library is built, the course library is sent to the user to obtain the user's browsing parameters for each course as passive use parameters, and then the user's operation information for each course is obtained as active use parameters. The passive use parameters use the same data structure as the browsing parameters, that is, the browsing time and the browsing time point set. The active use parameters are mainly operation information, and the operation information includes collection and likes, etc. The user's preference for each course can be determined based on the passive use parameters and the active use parameters. In order to simplify the calculation process, different operations can be assigned values, and then the active use parameters are limited to a numerical value. For example, collection and likes correspond to positive values, collections correspond to larger values, and dislikes correspond to negative values, etc.; based on this, the longer the browsing time, the more data in the browsing time point set, the larger the active use parameter, and the higher the preference is. This application only limits the correlation relationship, not the numerical relationship. The specific numerical relationship is determined by the staff according to the situation, and the present invention will not go into details.

[0109] The benchmark selection coefficient of each course in the course library is determined according to the preference. One solution is to calculate the ratio of the preference to the preference threshold, and use the ratio as the benchmark selection coefficient. For courses with lower preferences, the corresponding benchmark selection coefficient is smaller, such as 80%. When constructing the course library, the corresponding course will only be selected again when the matching degree is high enough and sufficient to smooth out the 80% scaling range.

[0110] Figure 2 1 is a structural diagram of a custom course system construction system. In an embodiment of the present invention, a custom course system construction system 10 includes:

[0111] The information volume calculation module 11 is used to obtain the browsing data containing browsing parameters of the user based on the preset authority, identify the browsing data containing browsing parameters, and determine the information volume of each browsing data;

[0112] A compatibility calculation module 12 is used to obtain the user's personal information and determine the compatibility of each browsing data according to the personal information;

[0113] A course library construction module 13 is used to select browsing data as reference data according to the degree of fit and the amount of information, select courses from a preset course library based on the reference data, and construct a course library;

[0114] The selection and updating module 14 is used to obtain the usage parameters pointing to each course in the course library in real time, and adjust the course selection process according to the usage parameters.

[0115] Furthermore, the information volume calculation module 11 includes:

[0116] The permission acquisition unit is used to send a browsing data access request to the user and receive the access permission granted by the user;

[0117] A search execution unit, used for acquiring browsing data containing browsing parameters of the user based on the search authority; the browsing parameters include browsing duration and a browsing time point set, and the browsing time point in the browsing time point set is a time point for starting browsing;

[0118] A parameter identification unit, used to identify the browsing parameter and determine the adjustment coefficient;

[0119] A data identification unit, used to identify the browsing data, determine the amount of information, and adjust the amount of information according to the adjustment coefficient;

[0120] The process of determining the adjustment coefficient is as follows:

[0121] Wherein, X is the adjustment coefficient, α is the preset adjustment coefficient, T is the browsing time, and N is the total number of time points in the browsing time point concentration.

[0122] Specifically, the fit calculation module 12 includes:

[0123] A tag query unit, used to obtain professional tags and interest tags of users;

[0124] A keyword extraction unit, used to extract keywords for each browsing data based on an AI model;

[0125] The comparison unit is used to compare the user's professional tags and interest tags as well as the keywords of each browsing data, and determine the degree of fit based on the comparison results.

[0126] In addition, the course library construction module 13 includes:

[0127] An evaluation value calculation unit, used to calculate the evaluation value by taking the fit degree and the amount of information as two dependent variables, and used to characterize the importance of the browsing data;

[0128] A selection unit, used to select browsing data whose evaluation value reaches a preset threshold as reference data;

[0129] The matching unit is used to read the keywords of the parameter data, match and select courses in the preset course library, and build a course library.

[0130] In summary, the work content of this system includes:

[0131] Based on preset permissions, the user's browsing data containing browsing parameters is obtained, the browsing data containing browsing parameters is identified, and the amount of information of each browsing data is determined; the user's personal information is obtained, and the fit of each browsing data is determined according to the personal information; the browsing data is selected as reference data according to the fit and the amount of information, and courses are selected from a preset course library based on the reference data to build a course library; the usage parameters pointing to each course in the course library are obtained in real time, and the course selection process is adjusted according to the usage parameters.

[0132] The effects achieved are as follows:

[0133] The present invention obtains browsing data containing browsing parameters, combines the user's personal information, quickly matches the target course in the course library, builds the course library, and then optimizes the course matching process according to the user's feedback on the course, with high efficiency and high accuracy.

[0134] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, a magnetic disk storage, a magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0135] Finally, it should be noted that the power grid security protection method and system based on intelligent perception disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for constructing a customized course system, characterized in that: The method comprises: Obtaining browsing data containing browsing parameters of the user based on preset permissions, identifying the browsing data containing browsing parameters, and determining the amount of information of each browsing data; Obtaining the user's personal information and determining the relevance of each browsing data based on the personal information; Selecting browsing data as reference data according to the degree of fit and the amount of information, selecting courses from a preset course library based on the reference data, and constructing a course library; The usage parameters pointing to each course in the course library are obtained in real time, and the course selection process is adjusted according to the usage parameters.

2. The method for constructing a customized course system according to claim 1, characterized in that: The steps of obtaining the browsing data containing browsing parameters of the user based on the preset authority, identifying the browsing data containing browsing parameters, and determining the information volume of each browsing data include: Send a browsing data access request to the user and receive the access permission granted by the user; Based on the access authority, the browsing data of the user including browsing parameters is obtained; the browsing parameters include browsing duration and a browsing time point set, and the browsing time point in the browsing time point set is the time point at which browsing starts; Identifying the browsing parameters and determining the adjustment coefficient; Identifying the browsing data, determining the amount of information, and adjusting the amount of information according to the adjustment coefficient; The process of determining the adjustment coefficient is as follows: Wherein, X is the adjustment coefficient, α is the preset adjustment coefficient, T is the browsing time, and N is the total number of time points in the browsing time point concentration.

3. The method for constructing a customized course system according to claim 2, characterized in that: The steps of identifying the browsing data, determining the amount of information, and adjusting the amount of information according to the adjustment coefficient include: Obtaining the type of browsing data, and when the type is text, calculating the TF-IDF value of each word in the text, counting the TF-IDF values ​​of all words, and generating a value set; Calculating the similarity between the browsing data and other browsing data according to the value set, and determining the amount of information according to the similarity; When the type is an image sequence, grayscale conversion is performed on each image in the image sequence, and the grayscale mean is calculated to obtain a grayscale mean array; Calculate the similarity between the browsing data and other browsing data based on the grayscale mean array, and determine the amount of information according to the similarity; The calculation process of the information volume is: In the formula, Y is the amount of information, β is the preset adjustment coefficient, E[S] represents the mean of the similarity with other browsing data, σ[S] represents the standard deviation of the similarity with other browsing data; S represents the similarity set with other browsing data, and the number of similarities in the similarity set is the same as the number of other browsing data.

4. The method for constructing a customized course system according to claim 1, characterized in that: The step of obtaining the user's personal information and determining the degree of fit of each browsing data according to the personal information includes: Obtain users' professional and interest tags; Extract keywords from each browsing data based on AI model; Compare the user's professional tags and interest tags with the keywords of each browsing data, and determine the degree of fit based on the comparison results.

5. The method for constructing a custom course system according to claim 4, characterized in that: The step of selecting browsing data as reference data according to the degree of fit and the amount of information, and selecting courses from a preset course library based on the reference data, and constructing a course library further includes: The fit and information content are used as two dependent variables to calculate the evaluation values, which are used to characterize the importance of browsing data; Select browsing data whose evaluation value reaches a preset threshold as reference data; Read the keywords of the parameter data, match and select courses in the preset course library, and build a course library.

6. The method for constructing a customized course system according to claim 1, characterized in that: The step of obtaining the usage parameters pointing to each course in the course library in real time and adjusting the course selection process according to the usage parameters comprises: Send the course library to the user and obtain the user's browsing parameters for each course as passive usage parameters; Obtain the user's operation information on each course as active usage parameters; Determining the user's preference for each course according to the passive use parameter and the active use parameter; The benchmark selection coefficient of each course in the course library is determined according to the preference; the benchmark selection coefficient is proportional to the preference.

7. A custom course system construction system, characterized in that: The system comprises: An information volume calculation module, used to obtain the browsing data containing browsing parameters of the user based on the preset authority, identify the browsing data containing browsing parameters, and determine the information volume of each browsing data; A compatibility calculation module, used to obtain the user's personal information and determine the compatibility of each browsing data according to the personal information; A course library construction module, used to select browsing data as reference data according to the degree of fit and the amount of information, select courses from a preset course library based on the reference data, and construct a course library; The selection and updating module is used to obtain the usage parameters pointing to each course in the course library in real time and adjust the course selection process according to the usage parameters.

8. The customized course system construction system according to claim 7, characterized in that: The information volume calculation module includes: The permission acquisition unit is used to send a browsing data access request to the user and receive the access permission granted by the user; A search execution unit, used for acquiring browsing data containing browsing parameters of the user based on the search authority; the browsing parameters include browsing duration and a browsing time point set, and the browsing time point in the browsing time point set is a time point for starting browsing; A parameter identification unit, used to identify the browsing parameter and determine the adjustment coefficient; A data identification unit, used to identify the browsing data, determine the amount of information, and adjust the amount of information according to the adjustment coefficient; The process of determining the adjustment coefficient is as follows: Wherein, x is the adjustment coefficient, α is the preset adjustment coefficient, T is the browsing time, and N is the total number of time points in the browsing time point concentration.

9. The customized course system construction system according to claim 7, characterized in that: The fit calculation module includes: A tag query unit, used to obtain professional tags and interest tags of users; A keyword extraction unit, used to extract keywords for each browsing data based on an AI model; The comparison unit is used to compare the user's professional tags and interest tags as well as the keywords of each browsing data, and determine the degree of fit based on the comparison results.

10. The customized course system construction system according to claim 9, characterized in that: The course library building module includes: An evaluation value calculation unit, used to calculate the evaluation value by taking the fit degree and the amount of information as two dependent variables, and used to characterize the importance of the browsing data; A selection unit, used to select browsing data whose evaluation value reaches a preset threshold as reference data; The matching unit is used to read the keywords of the parameter data, match and select courses in the preset course library, and build a course library.

Images