Teaching course recommendation processing method and system and storage medium

Abstract

The invention provides a teaching course recommendation processing method and system and a storage medium, and belongs to the technical field of recommendation management, and the method specifically comprises the following steps: based on historical retrieval data of a retrieval user under an associated user portrait of an optimized target course, when it is determined that retrieval data of retrieval users under other user portraits need to be considered, determining that the retrieval data of retrieval users under other user portraits need to be considered; determining an updating processing mode of the reference keyword of the optimized target course in the user portrait by utilizing a matching condition with other optimized target courses under the reference keyword and an associated user portrait of other optimized target courses, and updating the optimized target course on the basis of the updating processing mode of the reference keyword. And determining the recommendation processing method of the updated teaching course in the retrieval user under the user portrait, thereby improving the exposure of the teaching course with fewer keywords.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of recommendation management, and particularly relates to a recommended processing method and system for investment education courses and a storage medium. BACKGROUND

[0002] In order to realize the personalized recommendation processing of investment education courses to investors, that is, the personalized recommendation processing of investor education courses, the existing technical solutions often use the browsing data of users for personalized recommendation processing. The specific invention patent applications CN202510653729.7 "Course automatic recommendation management system and method based on artificial intelligence" and CN202510601679.8 "Online course recommendation method and system based on a large language model" are used for the recommendation processing of courses. However, the above technical solutions have the following technical defects: For the newly updated investment education courses, especially in the case that the number of keywords is small and the matching degree of user search is not high, the user portrait angle often cannot accurately realize the accurate recommendation processing of the investment education courses. Therefore, how to update the keywords of the investment education courses according to the search data of the user and the association of the keywords of other newly updated investment education courses, determine the differentiated recommendation processing strategy according to the similarity of the updated keywords and other newly updated investment education courses, and reduce the influence of the recommendation frequency and exposure of other newly updated investment education courses as much as possible, becomes a technical problem to be solved.

[0003] To solve the above technical problems, the application provides a recommended processing method and system for investment education courses and a storage medium. SUMMARY

[0004] To achieve the purpose of the application, the application adopts the following technical solutions: Specifically, the application provides a recommended processing method for investment education courses, which specifically includes: S1, based on the search data of the updated investment education courses, determining the matching data of the keywords when the updated investment education courses are used as search targets, and combining the number of keywords to determine the optimization target course in the updated investment education courses; S2, determining the reference keywords of the optimization target course according to the search data, determining the associated user portrait of the optimization target course according to the matching result of the reference keywords and the user portrait, and determining the search data of the search user under other user portraits when the search data of the search user under the associated user portrait of the optimization target course needs to be considered, entering the next step; S3 determines the updating processing mode of the reference keyword of the optimization target course in the user portrait based on the matching condition of the reference keyword with other optimization target courses and the associated user portrait of other optimization target courses. S4 determines the recommendation processing method of the updated teaching course in the search user under the user portrait based on the updating processing mode of the reference keyword.

[0005] The present application has the following advantages: The updating processing mode of the reference keyword of the optimization target course in the user portrait is determined based on the matching condition of the reference keyword with other optimization target courses and the associated user portrait of other optimization target courses, thereby avoiding the technical problem that the updating processing of the reference keyword in some user portraits may cause the recommendation processing frequency and exposure of the optimization target course with a high degree of reference keyword overlap to decrease, reducing the impact on the recommendation processing frequency of other optimization target courses in the associated user portrait, and ensuring the real-time and reliability of the updating processing of the reference keyword of the optimization target course.

[0006] The recommendation processing method of the updated teaching course in the search user under the user portrait is determined based on the updating processing mode of the reference keyword, taking into account the difference in the influence degree of the recommendation processing of different optimization target courses under different user portraits due to the difference in the updating processing mode of the reference keyword, and achieving the reliability of the recommendation processing based on the influence degree of the recommendation processing of other optimization target courses and the exposure processing demand of the self, thereby avoiding the technical problem that the browsing of the updated teaching course does not meet the requirements due to the small number of keywords or low retrieval matching degree.

[0007] The further technical solution is that the updated teaching course is the teaching course updated in the recent preset time period, and in one possible embodiment, the updated teaching course in the last week is taken as the updated teaching course.

[0008] It can be understood that the keyword is the keyword of the updated teaching course, and is specifically determined by the extraction result of the keyword in the title of the updated teaching course.

[0009] The further technical solution is that the determination method of the optimization target course in the updated teaching course is: The number of keywords of the updated teaching course is obtained, and the matching retrieval times of different keywords when the updated teaching course is taken as a retrieval target are determined based on the historical retrieval data of the keywords. The matching retrieval keyword in the keyword is determined based on the matching retrieval times. The number of the matching search keywords is determined, and whether the updated investment and education course is an optimization target course is determined.

[0010] Further technical solutions are that the matching search keywords are keywords whose matching search times meet the requirements, and in a possible embodiment, keywords whose matching search times corresponding to the keywords account for more than 0.2 in all matching search times are taken as the matching search keywords.

[0011] Further technical solutions are that the method for determining the recommendation processing method of the updated investment and education course in the search user under the user portrait is: Based on the reference keyword update processing mode, a user portrait for which the recommendation processing is performed based on the reference keyword and the keyword is determined as an updated user portrait; According to the number of coincident target courses in different updated user portraits, the number of coincidences of the updated user portrait with different coincident target courses is determined. Based on the number of coincidences of the updated user portrait with different coincident target courses, the recommendation processing method of the updated investment and education course in the search user under different user portraits is determined.

[0012] Optionally, in the above steps, if the number of coincidences of the updated user portrait with different coincident target courses all meet the requirements, that is, the number of coincidences of the updated user portrait with different coincident target courses is less than a preset coincidence number threshold, then the recommendation processing according to the first preset strategy does not have a great impact on other coincident target courses at this time, and therefore the first preset strategy is used for determining the recommendation processing method of the search user in different updated user portraits, that is, only when the search keyword of the search user matches at least one of the keywords of the optimization target course and the reference keyword, the recommendation processing is needed.

[0013] In a second aspect, the present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the investment and education course recommendation processing method described above.

[0014] In a third aspect, the present application provides a computer storage medium having a computer program stored thereon, wherein when the computer program is executed in a computer, the computer is caused to perform the investment and education course recommendation processing method described above.

[0015] Other features and advantages will be set forth in the following description of the application, and will be apparent from the description and the drawings. The objects and other advantages of the present application will be realized and achieved by the structure particularly pointed out in the description and the drawings.

[0016] In order to make the above objectives, characteristics and advantages of the present application more apparent, more comprehensible, the following preferred embodiments are specifically described in detail below, together with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] The above and other features and advantages of the present application will become more apparent by describing in detail example embodiments thereof with reference to the attached drawings.

[0018] Figure 1 is a flowchart of a method for determining an updating processing method of an optimization target course in a teaching course; Figure 2 is a flowchart of a method for determining an updating processing method of an optimization target course in a teaching course; Figure 3 is a flowchart of a method for determining an updating processing method of an optimization target course in a teaching course; Figure 4 is a flowchart of a method for determining an updating processing method of an optimization target course in a teaching course; Figure 5 is a framework diagram of a computer system. DETAILED DESCRIPTION

[0019] In order to make the above objectives, characteristics and advantages of the present application more apparent, more comprehensible, the following preferred embodiments are specifically described in detail below, together with the accompanying drawings.

[0020] In the present application, for the optimization target course with less keywords or low matching degree of keyword search, the self-adaptive updating processing of keywords is performed in combination with the user's search data, and the determination of the differentiated recommendation processing method is realized in different user portraits according to the coincidence with other optimization target courses in different user portraits, thereby improving the matching degree between the newly updated teaching course and the user's search demand.

[0021] Embodiment 1 As shown in Figure 1 The present application provides a teaching course recommendation processing method, which specifically comprises: S1, based on the search data of the updated teaching course, determining the matching data of the keywords when the updated teaching course is used as a search target, and in combination with the number of keywords, determining the optimization target course in the updated teaching course; Further, the updated teaching course is a teaching course updated in a preset time period, and in an embodiment, the updated teaching course in the last week is taken as the updated teaching course.

[0022] It can be understood that the keyword is a keyword of the updated teaching course, and specifically, the keyword is determined by an extraction result of a keyword in a title of the updated teaching course.

[0023] Specifically, as shown in Figure 2 The method for determining the optimization target course in the updated teaching course is as follows: The number of keywords of the updated teaching course is obtained, and based on historical search data of the keywords, a matching search frequency of different keywords when the updated teaching course is taken as a search target is determined. Based on the matching search frequency, a matching search keyword in the keyword is determined. Based on the number of the matching search keyword, it is determined whether the updated teaching course is an optimization target course.

[0024] Further, the matching search keyword is a keyword whose matching search frequency meets a requirement, and in an embodiment, a keyword whose matching search frequency accounts for more than 0.2 in all matching search frequencies is taken as the matching search keyword.

[0025] It can be understood that when the number of matching search keywords is less than a preset matching keyword number threshold, that is, the number of keywords with a high matching degree is small, and in an embodiment, the number is less than 4, it is determined that the updated teaching course is an optimization target course, and the keyword of the updated teaching course needs to be optimized, so as to improve the efficiency of the recommendation process when the updated teaching course is taken as a search target.

[0026] Optionally, the method for determining the optimization target course in the updated teaching course is as follows: The number of keywords of the updated teaching course is obtained. Based on historical search data of the keywords, a historical search frequency when the updated teaching course is taken as a search target is determined. Based on the historical search frequency and the number of keywords, it is determined whether the updated teaching course is an optimization target course.

[0027] It should be noted that when the historical search frequency is less than a preset search frequency threshold and the number of keywords is less than a preset keyword number threshold, it is determined that the number of times when the updated teaching course is taken as a search target is small and the number of keywords is small, and therefore, in order to improve the browsing data, the teaching course is determined as an optimization target course.

[0028] S2 determines the reference keyword of the optimization target course according to the search data, determines the associated user portrait of the optimization target course according to the matching result of the user portrait under the reference keyword, and determines whether the search data of the search user under other user portraits needs to be considered based on the historical search data of the search user under the associated user portrait of the optimization target course. It can be understood that the reference keyword is determined according to the keyword adjustment process in the keyword adjustment process of the optimization target course as the search target, and the search user finally obtains the optimization target course through the adjustment of the search keyword. Different keywords in the adjustment process are associated with the adjustment process of the search target as the adjustment process for extracting the reference keyword. It can be understood that if the search user searches three times in the last three minutes, the keywords of different search times are finance, bank, and bank in Zhejiang, and the search target is the stock of Ningbo Bank, then finance, bank, and bank in Zhejiang are used as the reference keyword of Ningbo Bank.

[0029] Specifically, when the search user performs the search process of the optimization target course, the search target is searched by adjusting the search keyword form within a certain time period because the search user does not know the keyword of the optimization target course.

[0030] Specifically, the associated user portrait of the optimization target course is a user portrait whose number of coinciding keywords and reference keywords meets the requirement. In one possible embodiment, if the user portrait is a bank stock investment user portrait, the keywords thereof include the names of different banks, bank, finance, interest, etc. When the number of coinciding keywords accounts for more than 0.6 in the number of keywords in the user portrait, the user portrait is determined to be the associated user portrait.

[0031] Specifically, as shown in Figure 3 The search data of the search user under other user portraits needs to be considered, specifically including: The search times of the search target as the optimization target course are used as the matching search times, and the search user with the matching search times is determined as the matching search user based on the historical search data of the search user under the associated user portrait of the optimization target course. The proportion of the matching search times belonging to the associated user portrait in different dates is determined as the associated proportion based on the constituent data of the matching search user under different associated user portraits. Based on the associated proportion in different dates, it is determined whether the search data of the search user under other user portraits needs to be considered.

[0032] Specifically, the correlation proportion is determined by a ratio of a number of matching searches in the date under the correlation user portrait to a number of matching searches in the date.

[0033] It can be understood that when the average value of the correlation proportions of different dates is greater than the preset correlation proportion threshold, in a possible embodiment, greater than 0.6, it is determined that the search data of the search users under other user portraits does not need to be considered.

[0034] It should be noted that when the search data of the search users under other user portraits does not need to be considered, only the search target under the correlation user portrait needs to be considered for the reference keyword adjustment process of the keyword adjustment process of the optimization target course, and only when the search keyword of the search user under the correlation user portrait matches the reference keyword and the keyword at least once, the recommendation processing of the optimization target course is performed, and under other user portraits, only when the keyword matches the keyword of the optimization target course at least once, the recommendation processing needs to be performed, thereby ensuring the exposure amount, and also reducing the technical problems of the exposure amount of other investment courses being low and the construction processing difficulty of the reference keyword being high caused by considering the reference keyword in all user portraits.

[0035] S3 determines the update processing mode of the reference keyword of the optimization target course in the user portrait by using the matching of the reference keyword with other optimization target courses, and the correlation user portraits of other optimization target courses; Specifically, as shown in Figure 4 The method for determining the update processing mode of the reference keyword of the optimization target course in the user portrait is: determining the number of coincidences of the reference keyword with different other optimization target courses based on the matching of the reference keyword with other optimization target courses, determining the coincident target courses in the optimization target course based on the number of coincidences; determining the number of coincident target courses in different user portraits according to different correlation user portraits of the coincident target courses, and taking the number as the number of coincident courses; determining the update processing mode of the reference keyword of the optimization target course based on the number of coincident courses in different user portraits.

[0036] It can be understood that the coincident target course is an optimization target course in which the proportion of the number of coincidences of the reference keyword in the number of reference keywords in the optimization target course is greater than a preset reference keyword proportion threshold, and in a possible embodiment, the optimization target course greater than 0.3 is taken as the coincident target course.

[0037] It should be noted that when the number of coincident courses in the user portrait is greater than the preset coincident course number threshold, in one possible embodiment, when it is greater than 5, the reference keyword updating process is not performed in the user portrait, that is, the recommendation process is performed based on the keyword, and when the number of coincident courses in the user portrait is not greater than 5, the reference keyword updating process is performed in the user portrait, and the recommendation process is performed based on the reference keyword and the keyword.

[0038] S4 determines the recommendation processing method of the updated training course in the search user under the user portrait based on the reference keyword updating mode.

[0039] Specifically, the method for determining the recommendation processing method of the updated training course in the search user under the user portrait is: Based on the reference keyword updating mode, determine the user portrait based on the reference keyword and the keyword for recommendation processing, and take it as an updated user portrait; According to the number of coincident target courses in different updated user portraits, determine the number of coincident target courses in different updated user portraits. Based on the number of coincident target courses in different updated user portraits, determine the recommendation processing method of the updated training course in the search user under different user portraits.

[0040] Optionally, in the above steps, if the number of coincident target courses in different updated user portraits meets the requirement, that is, the number of coincident target courses in different updated user portraits is less than the preset coincident number threshold, in one possible embodiment, when it is less than 3, at this time, the recommendation processing according to the first preset strategy will not cause excessive influence on other coincident target courses, so the first preset strategy is adopted in different updated user portraits to determine the recommendation processing method of the search user, that is, only when the search keyword of the search user matches the keyword and the reference keyword of the optimization target course at least one, the recommendation processing is needed.

[0041] In addition, it should be noted that when it is not in the updated user portrait, the second preset strategy is adopted to determine the recommendation processing of the search user, that is, only when the search keyword of the search user matches the keyword of the optimization target course at least one, the recommendation processing is needed.

[0042] In addition, it can be understood that if there is a coincident target course whose coincident number of the updated user portrait does not meet the requirement, the coincident target course whose coincident number of the updated user portrait does not meet the requirement is taken as an impact target course, and when the number of the impact target courses in the updated user portrait does not meet the requirement, i.e., more than 2, a third preset strategy is used for the recommendation processing of the search user, i.e., only when the search keyword of the search user matches the keyword and the reference keyword of the optimization target course by at least a preset number, the recommendation processing is needed. In one possible embodiment, the preset number is more than 3.

[0043] When the number of the impact target courses in the updated user portrait meets the requirement, i.e., not more than 2, a first preset strategy is used for the determination of the recommendation processing method of the search user.

[0044] In another embodiment, when the coincident number of the updated user portrait of different coincident target courses is less than 2, the first preset strategy is used for the recommendation processing at this time, which does not cause excessive impact on other coincident target courses. Therefore, the first preset strategy is used for the determination of the recommendation processing method of the search user in different updated user portraits, i.e., only when the search keyword of the search user matches the keyword and the reference keyword of the optimization target course by at least one, the recommendation processing is needed.

[0045] When the coincident number is not less than 2, the third preset strategy is used for the recommendation processing of the search user in the updated user portrait which is not less than 2, i.e., only when the search keyword of the search user matches the keyword and the reference keyword of the optimization target course by at least a preset number, the recommendation processing is needed, and the first preset strategy is used for the determination of the recommendation processing method of the search user.

[0046] Optionally, the determination of the recommendation processing method of the search user in the updated teaching course under the user portrait includes the following steps. Based on the reference keyword update processing mode, the user portrait based on the reference keyword and the keyword for the recommendation processing is determined as an updated user portrait, the number of the updated user portrait and the number of the updated user portrait of the coincident target course are determined; It should be noted that in the above steps, if the number of the updated user portrait is less than a preset updated user portrait number threshold, the first preset strategy is used for the determination of the recommendation processing method of the search user at this time in order to improve the exposure. Further, in the above step, if the number of updated user profiles is not less than the preset threshold of the number of updated user profiles, the number of updated user profiles without the overlapping target course is obtained. When the number of updated user profiles without the overlapping target course is large, i.e., greater than the preset threshold of the number of user profiles, only the first preset strategy is used to determine the recommendation processing method of the search user in the updated user profiles without the overlapping target course, i.e., the first preset strategy is used to recommend the search user in the updated user profiles without the overlapping target course, and the third preset strategy is used to recommend the search user in other updated user profiles.

[0047] It should be noted that if the number of updated user profiles without the overlapping target course is not large, the first preset strategy is used to determine the recommendation processing method of the search user in the updated user profiles without the overlapping target course, and the next step is entered.

[0048] According to the overlapping target courses in different updated user profiles, the number of updated user profiles overlapping with different target courses is determined, and the interference factor of different overlapping target courses is determined in combination with the number of updated user profiles overlapping with the target courses. In one possible embodiment, the interference factor is determined according to the ratio of the number of updated user profiles overlapping with the target courses and the number of updated user profiles overlapping with the target courses.

[0049] It can be understood that in the above step, if the interference factors of different overlapping target courses all meet the requirements, i.e., the interference factors of different overlapping target courses are all less than the preset threshold of the interference factor, then the recommendation processing according to the first preset strategy will not have a great impact on other overlapping target courses, and therefore the first preset strategy is used to determine the recommendation processing method of the search user in different updated user profiles, i.e., only when the search keyword of the search user matches at least one of the keywords of the optimization target course and the reference keyword, the recommendation processing is needed.

[0050] In addition, it can be understood that if there is an overlapping target course of the updated user profile whose interference factor does not meet the requirements, the overlapping target course of the updated user profile whose interference factor does not meet the requirements is taken as the influence target course. When the number of influence target courses in the updated user profile does not meet the requirements, i.e., greater than 2, the third preset strategy is used to recommend the search user, i.e., only when the search keyword of the search user matches a preset number of keywords of the optimization target course and the reference keyword, the recommendation processing is needed. In one possible embodiment, the preset number is greater than 3.

[0051] When the number of influence target courses in the updated user portrait meets the requirement, the process proceeds to the next step.

[0052] Based on the interference factors of the coinciding target courses under different updated user portraits, a recommendation processing method of the updated investment and education courses for the search users under different user portraits is determined.

[0053] It should be noted that in the above steps, the interference influence value under different updated user portraits is determined based on the sum of the interference factors of the coinciding target courses under the updated user portrait. When the interference influence value under the updated user portrait is greater than a preset influence threshold, a third preset strategy is used for the recommendation processing of the search users, and otherwise, a first preset strategy is used for the recommendation processing of the search users.

[0054] In one possible embodiment: The matching search times of different keywords when the updated investment and education course is the search target. The keywords corresponding to the matching search times account for more than 0.2 in all matching search times are taken as matching search keywords. When the number of matching search keywords is less than a preset matching keyword number threshold, that is, the number of search words with high matching degree is small, it is determined that the updated investment and education course is the optimization target course.

[0055] The search times of the search target as the optimization target course are taken as the matching search times, and the search users with the matching search times are taken as the matching search users. The proportion of the matching search times belonging to the associated user portrait in different dates is determined based on the constituent data of the matching search users under different associated user portraits, and is taken as the association proportion. When the average value of the association proportions in different dates is greater than a preset association proportion threshold, which is greater than 0.6 in one possible embodiment, it is determined that the search data of the search users under other user portraits does not need to be considered.

[0056] The number of coinciding target courses in the optimization target course is determined based on the number of coinciding reference keywords with different other optimization target courses, and the number of coinciding target courses belonging to the associated user portrait in different user portraits is determined and taken as the coinciding course number. When the number of coinciding courses in the user portrait is greater than a preset coinciding course number threshold, which is greater than 5 in one possible embodiment, the reference keyword updating process is not performed in the user portrait, that is, the recommendation processing is performed based on the keywords. When the number of coinciding courses in the user portrait is not greater than 5, the reference keyword updating process is performed in the user portrait, and the recommendation processing is performed based on the reference keywords and the keywords.

[0057] The user portrait based on the recommendation processing of the reference keyword and the keyword is updated as the updated user portrait, and if the coincidence number of the updated user portrait of the different coincident target courses all meet the requirement, that is, the coincidence number of the updated user portrait of the different coincident target courses is all less than the preset coincidence number threshold, then at this time, the recommendation processing according to the first preset strategy will not cause excessive influence on other coincident target courses, so the determination of the recommendation processing method of the search user in the different updated user portraits is that only when the search keyword of the search user matches at least one of the keywords and the reference keyword of the optimization target course, the recommendation processing is needed

[0058] Embodiment 2 In a second aspect, as shown in the figure, the present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the above-mentioned course recommendation processing method. Figure 5

[0059] Embodiment 3 In a third aspect, the present application provides a computer storage medium having a computer program stored thereon, when the computer program is executed in a computer, the computer program causes the computer to execute the above-mentioned course recommendation processing method.

[0060] Each of the embodiments in the specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment mainly describes the difference from other embodiments. Especially, for the device, equipment and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the related parts can be referred to the part of the method embodiment.

[0061] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order other than that described in the embodiments and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or possible.

[0062] ​The above merely provides one or more embodiments of the present specification and is not intended to limit the present specification. One of ordinary skill in the art can make various modifications and changes to one or more embodiments of the present specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of claims of the present specification.

Claims

1. A method for recommending student education courses, characterized in that, Specifically, it includes: Based on the search data of updated investor education courses, the matching data of keywords when the updated investor education courses are used as search targets are determined, and the optimized target courses in the updated investor education courses are determined in combination with the number of keywords. Based on the search data, reference keywords for the target course to be optimized are determined. The matching results of the reference keywords with the user profile are used to determine the associated user profile of the target course to be optimized. Based on the historical search data of the search users under the associated user profile of the target course to optimize, when it is determined that the search data of the search users under other user profiles need to be considered, the next step is taken. By utilizing the matching results of the reference keywords with other optimization target courses and the associated user profiles of other optimization target courses, the update processing method of the reference keywords of the optimization target courses in the user profile is determined. Based on the update processing method of the reference keywords, the recommendation processing method for the updated investor education course among the search users under the user profile is determined.

2. The flue gas online monitoring equipment management and analysis method as described in claim 1, characterized in that, The updated investor education courses are those updated within the most recent preset time period.

3. The flue gas online monitoring equipment management and analysis method as described in claim 1, characterized in that, The method for determining the optimized target courses in the updated investor education courses is as follows: Obtain the number of keywords for the updated investor education course, and based on the historical retrieval data of the keywords, determine the number of matching searches for different keywords when the updated investor education course is used as the retrieval target; The matching search keywords in the keywords are determined based on the number of matching searches. The number of matching search keywords determines whether the updated investor education course is the target course for optimization.

4. The flue gas online monitoring equipment management and analysis method as described in claim 3, characterized in that, The matching search keywords are those keywords that meet the required number of matching searches.

5. The flue gas online monitoring equipment management and analysis method as described in claim 1, characterized in that, The user profile associated with the optimized target course is the user profile whose corresponding keywords and reference keywords overlap in a certain number of times.

6. The flue gas online monitoring equipment management and analysis method as described in claim 1, characterized in that, The method for determining the update processing method of the reference keywords of the optimized target course in the user profile is as follows: Based on the matching results with other optimization target courses under different reference keywords, determine the number of overlaps with reference keywords of different other optimization target courses, and determine the overlapping target courses in the optimization target courses based on the number of overlaps. Based on the associated user profiles of different overlapping target courses, determine the number of overlapping target courses belonging to the associated user profiles in different user profiles, and use this as the number of overlapping courses. Based on the number of overlapping courses in different user profiles, the update processing method for the reference keywords of the optimization target course is determined.

7. The flue gas online monitoring equipment management and analysis method as described in claim 6, characterized in that, The overlapping target courses are those whose number of overlapping reference keywords is greater than the percentage of reference keywords in the optimized target courses.

8. The flue gas online monitoring equipment management and analysis method as described in claim 1, characterized in that, The method for determining the recommendation processing method for updating the investor education course among users retrieved under the user profile is as follows: Based on the update processing method of the reference keywords, a user profile is determined based on the reference keywords and keywords for recommendation processing, and this profile is used as the updated user profile. Based on the overlapping target courses in different updated user profiles, determine the number of overlaps with the updated user profiles of different overlapping target courses. Based on the number of overlaps with updated user profiles of different overlapping target courses, a recommendation processing method for retrieving users of the updated investor education courses under different user profiles is determined.

9. A computer system, comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a method for recommending student education courses as described in any one of claims 1-8.

10. A computer storage medium storing a computer program thereon, wherein when the computer program is executed in a computer, the computer executes a method for recommending student education courses as described in any one of claims 1-8.

Images