Personalized recommendation method and system for boutique courses supported by information technology

Abstract

The invention relates to the technical field of boutique course recommendation, and provides an information technology supported boutique course personalized recommendation method and system, and the method comprises the steps: obtaining the historical consumption record and budget range data of a learner, and calculating the economic bearing capability level; extracting courses matched with the learning target, and generating a preliminary candidate set in combination with payment preference information; querying a preferential activity database for the courses exceeding the economic bearing capacity level, and generating an optimized cost scheme set; obtaining the consumption tendency of the user group similar to the payment preference information, and generating a personalized recommendation combination; obtaining duration and content dimension data of the personalized recommendation combination, and generating a sorted recommendation list; and dynamically adjusting the payment mismatching items in the sorted recommendation list to obtain a final accessible course recommendation result. According to the method, accurate matching of economic ability and learning requirements is realized, the personalized level and economic accessibility of course recommendation are improved, and an efficient and economic learning path is provided for learners.

Description

Technical Field

[0001] This invention relates to the field of high-quality course recommendation technology, and in particular to a personalized recommendation method and system for high-quality courses supported by information technology. Background Technology

[0002] With the rise of online education, the knowledge system for curriculum development has become increasingly rich, and various educational resources have been continuously accumulated. Currently, there are many types of courses on online learning platforms, and the overview of educational courses is mainly classified by simple course tags and names. The course classification is vague, and users cannot find suitable educational courses by simply browsing or searching. Therefore, a high-quality course recommendation system has been developed.

[0003] In systems based on information technology, artificial intelligence, and premium course recommendations, a complex technical challenge exists: how to achieve a dynamic balance between learners' affordability and course recommendations. The system needs to determine learners' affordability levels. Simultaneously, it needs to extract premium courses matching learning goals from the course library and incorporate payment preference information. Furthermore, the system needs to dynamically adjust the course pricing structure, including applying promotional activities and installment payment options, to ensure the accessibility of recommended courses. This involves complex pricing strategies and payment scheme optimization. Even more challenging is the system's need for continuous learning and adaptation, constantly updating the learner's economic information model through feedback data to maintain recommendation accuracy. This requires the system to possess powerful machine learning capabilities, capable of identifying patterns and making intelligent decisions from massive amounts of data. Summary of the Invention

[0004] This invention provides a personalized recommendation method and system for high-quality courses supported by information technology, aiming to solve the problem that existing high-quality course recommendation systems cannot achieve a dynamic balance between learners' economic affordability and course recommendations.

[0005] This invention is implemented as follows: a method and system for personalized recommendation of high-quality courses supported by information technology, wherein the method for personalized recommendation of high-quality courses supported by information technology includes:

[0006] Acquire learners' historical consumption records and budget range data, and analyze them in conjunction with real-time interactive behavior to build learners' economic information models and calculate their economic affordability levels;

[0007] Based on the level of economic affordability, a content recommendation algorithm is used to extract courses that match the learning objectives from the course library, and a preliminary candidate set is generated by combining payment preference information.

[0008] Determine whether the course pricing in the preliminary candidate set exceeds the affordability level; for courses exceeding the affordability level, query the discount activity database and generate an optimized pricing scheme set.

[0009] The collaborative filtering algorithm is used to obtain the consumption tendencies of similar user groups based on the payment preference information, and the matching payment schemes are determined from the optimized payment scheme set and associated with the corresponding courses to generate personalized recommendation combinations;

[0010] Obtain the duration and content dimension data of the personalized recommendation combination, calculate the relevance score with learner needs through multi-dimensional matching, and generate a sorted recommendation list;

[0011] Determine if there are any payment mismatches in the sorted recommendation list. If so, dynamically adjust the installment options or discount combinations in the payment plan to obtain the final available course recommendation results.

[0012] Furthermore, the historical consumption records are course purchase data of learners over multiple time periods, the budget range data is the cost range set by learners, the real-time interactive behavior includes click and browsing data of learners during the course selection process, and the payment preference information includes learners' preference for payment methods.

[0013] Furthermore, the process of acquiring learners' historical consumption records and budget range data, and analyzing them in conjunction with real-time interactive behavior to establish a learner's economic information model and calculate their economic affordability level, specifically includes:

[0014] Extract purchase amount and frequency data from the historical consumption records, and upper and lower limits of the budget range data. Determine the interaction behavior weights based on click and browsing data from the real-time interaction behavior. Combine the purchase amount and frequency data, the upper and lower limits of the budget range data, and the interaction behavior weights to establish a learner economic information model and calculate the economic affordability level.

[0015]

[0016] EAL represents the level of economic affordability, and H t Let B represent the historical consumption record for period t, T represent the total number of periods in the historical consumption record, and B represent the budget range data. k ω represents the weight value of the k-th real-time interactive action. k Let α represent the influencing factor of the k-th interaction behavior, K represent the total number of real-time interaction behaviors, and α, β, and γ represent the weight coefficients of historical consumption records, budget range data, and interaction behaviors, respectively.

[0017] Furthermore, the step of determining whether the course pricing in the preliminary candidate set exceeds the affordability level, and querying the discount activity database for courses exceeding the affordability level to generate an optimized pricing scheme set, specifically includes:

[0018] Compare the course pricing in the preliminary candidate set with the level of economic affordability;

[0019] For courses that exceed the stated affordability level, extract available discount or installment payment data from the promotional activity database;

[0020] Adjust course pricing based on extracted discount or installment payment data to generate the optimized pricing scheme set.

[0021] Furthermore, the step of using a collaborative filtering algorithm to obtain the consumption tendencies of similar user groups based on the payment preference information, and determining matching payment schemes from the optimized payment scheme set and associating them with corresponding courses to produce personalized recommendation combinations specifically includes:

[0022] Calculate the payment preference similarity between learners and similar user groups, where similar user groups are those with similar course consumption behaviors. Based on the payment preference similarity, select payment schemes that match the payment preference information from the optimized set of payment schemes, associate the selected payment schemes with the corresponding courses, and generate the personalized recommendation combination.

[0023]

[0024] Among them, S ij Let r represent the similarity between user i and user j, U represent the set of users who have made purchases on both course i and course j, and r represent the similarity between user i and user j. ui This represents user u's payment preference rating for course i, r uj This represents user u's rating of their payment preference for course j. This represents the average payment preference score for user u.

[0025] Furthermore, the step of obtaining the duration and content dimension data of the personalized recommendation combination, calculating the relevance score with learner needs through multi-dimensional matching, and generating a sorted recommendation list specifically includes:

[0026] Extract the duration and content data of the courses in the personalized recommendation combination, and calculate the relevance score based on the matching degree between the duration and content data and the learner's needs:

[0027]

[0028] Where RS represents the relevance score of the course recommendation, M represents the total number of courses in the recommended combination, and ω m D represents the weight coefficient of the m-th course. m T represents the degree of matching between the content dimension of the m-th course and the learning needs. m Let C represent the degree of match between the duration of the m-th course and the demand.m P represents the content quality score of the m-th course. m This represents the optimized cost plan price for the m-th course;

[0029] The personalized recommendation combinations are then sorted according to the relevance scores to generate the sorted recommendation list.

[0030] Furthermore, based on the degree of matching between the aforementioned duration and content dimension data and learner needs, a relevance score is calculated, including:

[0031] Determine the degree of match between the course duration and learner's time preference in the personalized recommendation combination;

[0032] Determine the degree of match between the content dimensions of the courses in the personalized recommendation combination and the learner's learning objectives;

[0033] The relevance score is calculated based on the duration matching degree and the content dimension matching degree.

[0034] Furthermore, the recommendation method also includes:

[0035] The system uses a secure encryption module to obtain and protect user feedback data on the final recommendation results.

[0036] The learner's economic information model is updated using the feedback data to determine the affordability adjustment parameters for the next period in order to maintain the continued accuracy of the recommendations.

[0037] A personalized recommendation system for high-quality courses supported by information technology, comprising:

[0038] The data acquisition module is used to acquire learners' historical consumption records, budget data, real-time interactive behavior data, and payment preference information;

[0039] The economic capacity calculation module is used to calculate the learner's economic affordability level based on the acquired data.

[0040] The candidate course generation module is used to generate a preliminary set of candidate courses based on economic capacity and learning objectives.

[0041] The cost optimization module is used to query the discount database and generate cost optimization plans;

[0042] The collaborative filtering recommendation module is used to generate personalized recommendation combinations based on the consumption preferences of similar user groups;

[0043] The multi-dimensional sorting module is used to calculate and sort relevance scores based on duration and content matching degree.

[0044] The payment adaptation module is used to dynamically adjust the fee scheme and output the final recommendation result.

[0045] Furthermore, the recommendation system also includes:

[0046] A security encryption module is used to acquire and protect user feedback data on the final recommendation results;

[0047] The accuracy maintenance module is used to update the learner's economic information model using the feedback data and determine the affordability adjustment parameters for the next period to maintain the continuous accuracy of the recommendations.

[0048] Compared with the prior art, the beneficial effects of the present invention are:

[0049] This invention addresses the problem of insufficient matching between economic capacity and learning goals in traditional course recommendations. By integrating historical consumption records, budget ranges, and real-time interactive behavior, it dynamically analyzes learners' affordability levels. Based on this analysis, and combining content recommendation algorithms and collaborative filtering algorithms, it accurately selects high-quality courses from the course library that match learning goals, while simultaneously optimizing pricing schemes. Through information technology-supported system integration interfaces and automated decision-making systems, this invention deeply integrates course data and payment preferences to generate an initial candidate set. It then dynamically adjusts discounts or installment payment options based on affordability, forming personalized recommendation combinations. This invention utilizes multi-dimensional matching to calculate relevance scores, prioritizes the recommendation list, and protects feedback data with a secure encryption module. It also combines pattern recognition to update the learner's economic information model, continuously optimizing recommendation accuracy. This invention achieves precise matching between economic capacity and learning needs, improving the personalization and economic accessibility of course recommendations, and providing learners with an efficient and economical learning path. Attached Figure Description

[0050] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is an overall flowchart of Embodiment 1 of the present invention;

[0052] Figure 2 This is a system block diagram of Embodiment 2 of the present invention; Detailed Implementation

[0053] To better understand the technical content of this invention, the technical solutions of this invention are further described and explained below with reference to specific embodiments, but are not limited thereto. The technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0054] Example 1

[0055] refer to Figure 1 A personalized recommendation method for high-quality courses supported by information technology includes:

[0056] S101: Obtain learners' historical spending records and budget range data, and analyze them in conjunction with real-time interactive behavior to calculate their affordability level. The historical spending records are course purchase data of learners over multiple time periods, the budget range data is the cost range set by the learners, and the real-time interactive behavior includes the click and browsing data of learners during the course selection process.

[0057] Specifically, this involves: extracting purchase amount and frequency data from the historical consumption records, and the upper and lower limits of the budget range data; determining the interaction behavior weights based on the click and browsing data of the real-time interactive behavior; and establishing a learner economic information model by combining the purchase amount and frequency data, the upper and lower limits of the budget range data, and the interaction behavior weights to calculate the economic affordability level.

[0058]

[0059] EAL represents the level of economic affordability, and H t Let B represent the historical consumption record for period t, T represent the total number of periods in the historical consumption record, and B represent the budget range data. k ω represents the weight value of the k-th real-time interactive action. k Let α represent the influencing factor of the k-th interaction behavior, K represent the total number of real-time interaction behaviors, and α, β, and γ represent the weight coefficients of historical consumption records, budget range data, and interaction behaviors, respectively.

[0060] S102: Based on the economic affordability level, a content recommendation algorithm is used to extract courses that match the learning objectives from the course library, and a preliminary candidate set is generated by combining the payment preference information, which includes the learner's preference for payment methods.

[0061] S103: Determine whether the course pricing in the preliminary candidate set exceeds the economic affordability level. For courses that exceed the economic affordability level, query the discount activity database and generate an optimized cost plan set.

[0062] Compare the course pricing in the preliminary candidate set with the level of economic affordability;

[0063] For courses that exceed the stated affordability level, extract available discount or installment payment data from the promotional activity database;

[0064] Adjust course pricing based on extracted discount or installment payment data to generate the optimized pricing scheme set.

[0065] S104: Use a collaborative filtering algorithm to obtain the consumption tendencies of similar user groups based on the payment preference information, and determine the matching payment scheme from the optimized payment scheme set and associate it with the corresponding course to generate a personalized recommendation combination.

[0066] Specifically, the process involves: calculating the payment preference similarity between learners and similar user groups, where similar user groups are those with similar course consumption behaviors; selecting payment options that match the payment preference information from the optimized set of payment options based on the payment preference similarity; associating the selected payment options with corresponding courses; and generating the personalized recommendation combination.

[0067]

[0068] Among them, S ij Let r represent the similarity between user i and user j, U represent the set of users who have made purchases on both course i and course j, and r represent the similarity between user i and user j. ui This represents user u's payment preference rating for course i, r uj This represents user u's rating of their payment preference for course j. This represents the average payment preference score for user u.

[0069] S105: Obtain the duration and content dimension data of the personalized recommendation combination, calculate the relevance score with learner needs through multi-dimensional matching, and generate a sorted recommendation list.

[0070] Specifically, this involves: extracting the duration and content data of courses from the personalized recommendation combinations, and calculating a relevance score based on the matching degree between the duration and content data and the learner's needs.

[0071] Determine the degree of match between the course duration and learner's time preference in the personalized recommendation combination;

[0072] Determine the degree of match between the content dimensions of the courses in the personalized recommendation combination and the learner's learning objectives;

[0073] The relevance score is calculated based on the duration matching degree and the content dimension matching degree;

[0074]

[0075] Where RS represents the relevance score of the course recommendation, M represents the total number of courses in the recommended combination, and ω m D represents the weight coefficient of the m-th course. m T represents the degree of matching between the content dimension of the m-th course and the learning needs. m Let C represent the degree of match between the duration of the m-th course and the demand. m P represents the content quality score of the m-th course. m This represents the optimized cost plan price for the m-th course;

[0076] The personalized recommendation combinations are then sorted according to the relevance scores to generate the sorted recommendation list.

[0077] S106: Determine if there are any payment mismatches in the sorted recommendation list. If so, dynamically adjust the installment options or discount combinations in the payment plan to obtain the final accessible course recommendation results.

[0078] S107: Obtain and protect user feedback data on the final recommendation results through a secure encryption module.

[0079] S108: Update the learner's economic information model using the feedback data to determine the affordability adjustment parameters for the next period in order to maintain the continued accuracy of the recommendations.

[0080] Example 2

[0081] refer to Figure 2 A personalized recommendation system for high-quality courses supported by information technology, comprising:

[0082] The data acquisition module is used to acquire learners' historical consumption records, budget data, real-time interactive behavior data, and payment preference information;

[0083] The economic capacity calculation module is used to calculate the learner's economic affordability level based on the acquired data.

[0084] The candidate course generation module is used to generate a preliminary set of candidate courses based on economic capacity and learning objectives.

[0085] The cost optimization module is used to query the discount database and generate cost optimization plans;

[0086] The collaborative filtering recommendation module is used to generate personalized recommendation combinations based on the consumption preferences of similar user groups;

[0087] The multi-dimensional sorting module is used to calculate and sort relevance scores based on duration and content matching degree.

[0088] The payment adaptation module is used to dynamically adjust the fee scheme and output the final recommendation result;

[0089] A security encryption module is used to acquire and protect user feedback data on the final recommendation results;

[0090] The accuracy maintenance module is used to update the learner's economic information model using the feedback data and determine the affordability adjustment parameters for the next period to maintain the continuous accuracy of the recommendations.

[0091] The above-described embodiments are only some embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the technical scope disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A personalized recommendation method for high-quality courses supported by information technology, characterized in that, The recommended approach includes: Acquire learners' historical consumption records and budget range data, and analyze them in conjunction with real-time interactive behavior to build learners' economic information models and calculate their economic affordability levels; Based on the level of economic affordability, a content recommendation algorithm is used to extract courses that match the learning objectives from the course library, and a preliminary candidate set is generated by combining payment preference information. Determine whether the course pricing in the preliminary candidate set exceeds the affordability level; for courses exceeding the affordability level, query the discount activity database and generate an optimized pricing scheme set. The collaborative filtering algorithm is used to obtain the consumption tendencies of similar user groups based on the payment preference information, and the matching payment schemes are determined from the optimized payment scheme set and associated with the corresponding courses to generate personalized recommendation combinations; Obtain the duration and content dimension data of the personalized recommendation combination, calculate the relevance score with learner needs through multi-dimensional matching, and generate a sorted recommendation list; Determine if there are any payment mismatches in the sorted recommendation list. If so, dynamically adjust the installment options or discount combinations in the payment plan to obtain the final available course recommendation results.

2. The personalized recommendation method for high-quality courses supported by information technology as described in claim 1, characterized in that, The historical consumption records are course purchase data of learners over multiple time periods; the budget range data is the cost range set by learners; the real-time interactive behavior includes click and browsing data of learners during the course selection process; and the payment preference information includes learners' preference for payment methods.

3. The personalized recommendation method for high-quality courses supported by information technology as described in claim 1, characterized in that, The process of acquiring learners' historical consumption records and budget range data, and analyzing them in conjunction with real-time interactive behavior to establish a learner's economic information model and calculate their economic affordability level, specifically includes: Extract purchase amount and frequency data from the historical consumption records, and upper and lower limits of the budget range data. Determine the interaction behavior weights based on click and browsing data from the real-time interaction behavior. Combine the purchase amount and frequency data, the upper and lower limits of the budget range data, and the interaction behavior weights to establish a learner economic information model and calculate the economic affordability level. EAL represents the level of economic affordability, and H t Let B represent the historical consumption record for period t, T represent the total number of periods in the historical consumption record, and B represent the budget range data. k ω represents the weight value of the k-th real-time interactive action. k Let α represent the influencing factor of the k-th interaction behavior, K represent the total number of real-time interaction behaviors, and α, β, and γ represent the weight coefficients of historical consumption records, budget range data, and interaction behaviors, respectively.

4. The personalized recommendation method for high-quality courses supported by information technology as described in claim 1, characterized in that, The step of determining whether the course pricing in the preliminary candidate set exceeds the affordability level, and querying the discount activity database for courses exceeding the affordability level to generate an optimized pricing scheme set, specifically includes: Compare the course pricing in the preliminary candidate set with the level of economic affordability; For courses that exceed the stated affordability level, extract available discount or installment payment data from the promotional activity database; Adjust course pricing based on extracted discount or installment payment data to generate the optimized pricing scheme set.

5. The personalized recommendation method for high-quality courses supported by information technology as described in claim 1, characterized in that, The process of using a collaborative filtering algorithm to obtain the consumption tendencies of similar user groups based on payment preference information, and determining matching payment schemes from the optimized payment scheme set and associating them with corresponding courses to generate personalized recommendation combinations specifically includes: Calculate the payment preference similarity between learners and similar user groups, where similar user groups are those with similar course consumption behaviors. Based on the payment preference similarity, select payment schemes that match the payment preference information from the optimized set of payment schemes, associate the selected payment schemes with the corresponding courses, and generate the personalized recommendation combination. Among them, S ij Let r represent the similarity between user i and user j, U represent the set of users who have made purchases on both course i and course j, and r represent the similarity between user i and user j. ui This represents user u's payment preference rating for course i, r uj This represents user u's rating of their payment preference for course j. This represents the average payment preference score for user u.

6. The personalized recommendation method for high-quality courses supported by information technology as described in claim 1, characterized in that, The process of obtaining the duration and content dimension data of the personalized recommendation combination, calculating the relevance score to learner needs through multi-dimensional matching, and generating a sorted recommendation list specifically includes: Extract the duration and content data of the courses in the personalized recommendation combination, and calculate the relevance score based on the matching degree between the duration and content data and the learner's needs: Where RS represents the relevance score of the course recommendation, M represents the total number of courses in the recommended combination, and ω m D represents the weight coefficient of the m-th course. m T represents the degree of matching between the content dimension of the m-th course and the learning needs. m Let C represent the degree of match between the duration of the m-th course and the demand. m P represents the content quality score of the m-th course. m This represents the optimized cost plan price for the m-th course; The personalized recommendation combinations are then sorted according to the relevance scores to generate the sorted recommendation list.

7. The personalized recommendation method for high-quality courses supported by information technology as described in claim 6, characterized in that, Based on the degree of matching between the aforementioned duration and content dimension data and learner needs, a relevance score is calculated, including: Determine the degree of match between the course duration and learner's time preference in the personalized recommendation combination; Determine the degree of match between the content dimensions of the courses in the personalized recommendation combination and the learner's learning objectives; The relevance score is calculated based on the duration matching degree and the content dimension matching degree.

8. The personalized recommendation method for high-quality courses supported by information technology as described in claim 1, characterized in that, The recommendation method also includes: The feedback data of the final recommendation results is protected by a security encryption module supported by information technology, and the data is processed by an artificial intelligence pattern recognition unit to obtain updated learner economic information model parameters. The learner's economic information model is updated using feedback data from the final recommendation results, and the affordability adjustment parameters for the next cycle are determined to maintain the continued accuracy of the recommendations.

9. A personalized recommendation system for high-quality courses supported by information technology, characterized in that: The method for personalized recommendation of high-quality courses supported by information technology as described in any one of claims 1-8 includes: The data acquisition module is used to acquire learners' historical consumption records, budget data, real-time interactive behavior data, and payment preference information; The economic capacity calculation module is used to calculate the learner's economic affordability level based on the acquired data. The candidate course generation module is used to generate a preliminary set of candidate courses based on economic capacity and learning objectives. The cost optimization module is used to query the discount database and generate cost optimization plans; The collaborative filtering recommendation module is used to generate personalized recommendation combinations based on the consumption preferences of similar user groups; The multi-dimensional sorting module is used to calculate and sort relevance scores based on duration and content matching degree. The payment adaptation module is used to dynamically adjust the fee scheme and output the final recommendation result.

10. The personalized recommendation method for high-quality courses supported by information technology as described in claim 9, characterized in that, The recommendation system also includes: A security encryption module is used to acquire and protect user feedback data on the final recommendation results; The accuracy maintenance module is used to update the learner's economic information model using the feedback data and determine the affordability adjustment parameters for the next period to maintain the continuous accuracy of the recommendations.

Images