A user attention demand analysis and processing system and method based on big data

By collecting and analyzing the basic and browsing information of new users, combining big data technology, screening users with similar and follow-up sections for comprehensive analysis, calculating the recommendation index and section number threshold, the problem of low efficiency in recommendation of new users' information is solved and efficient Information recommendation service.

CN117473165BActive Publication Date: 2024-11-22CHINA-FUNDED LIANHUITONG (SHANXI) TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311548044.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-20
Publication Date
2024-11-22
Estimated Expiration
2043-11-20

AI Technical Summary

Technical Problem

Existing big data analysis platforms are difficult to effectively predict new users' attention needs and interests, which leads to low efficiency in recommending new users' information and difficulty in quickly obtaining required information.

Method used

By collecting the personal basic information and browsing information of new users, combining big data analysis technology, we push preliminary analysis results and integrate processing browsing information to determine the follow-up recommendation strategy, filter out other users with similar follow-up sections for comprehensive analysis, calculate the recommendation index and The threshold for the number of sections, providing personalized information recommendations.

Benefits of technology

Without a large amount of historical attention information, it can predict the attention needs of new users, improve the efficiency and accuracy of information recommendation, and help new users quickly obtain the required information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117473165B_ABST
    Figure CN117473165B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of big data analysis technology, and discloses a user attention demand analysis and processing system and method based on big data. A user attention demand analysis and processing method based on big data includes: S1, collecting personal basic information of target new users, the personal basic information includes the user's gender and age group; S2, based on big data, preliminary analysis of the personal basic information of the target new user, and according to the results of the preliminary analysis, pushing out the image and text click channels corresponding to the sub-pages of various sections on the main page; S3, collecting the browsing information of the target new user, the browsing information includes the number of clicks of the target new user on each image and text click channel and the browsing time on the corresponding sub-page after the click. The present invention can analyze the historical attention information of other users who have similar attention tendencies as the target new user, and predict the attention needs of the target new user through analysis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a user attention demand analysis and processing system and method based on big data. Background Art

[0002] Big data is a collection of data that is so large that it is beyond the capabilities of traditional database software tools in terms of acquisition, storage, management, and analysis. It has four major characteristics: massive data scale, fast data flow, diverse data types, and low value density. The strategic significance of big data technology lies not in mastering huge amounts of data information, but in professional processing of these meaningful data. In other words, if big data is compared to an industry, then the key to profitability of this industry lies in improving the "processing ability" of data and achieving "value-added" of data through "processing". From a technical point of view, the relationship between big data and cloud computing is as inseparable as the front and back of a coin. Big data cannot be processed by a single computer and must adopt a distributed architecture. Its feature is distributed data mining of massive data. But it must rely on distributed processing, distributed databases, cloud storage, and virtualization technologies of cloud computing.

[0003] With the advent of the cloud era, big data has also attracted more and more attention. The analyst team believes that big data is usually used to describe a large amount of unstructured and semi-structured data created by a company, which takes too much time and money to download to a relational database for analysis. Big data analysis is often associated with cloud computing because real-time analysis of large data sets requires a framework like the same to distribute work to dozens, hundreds or even thousands of computers. With the coordinated development of cloud computing and big data, network platforms that are not based on user relationship information sharing collect and store user-related information through big data, and cooperate with cloud computing to analyze and process various related information data. It can judge the user's preference characteristics based on the user's historical attention information and predict the user's attention needs, thereby providing users with more efficient services. However, for new users of such platforms, big data is difficult to obtain new users' historical attention or browsing information, cannot make good predictions about new users' interests and hobbies, and is difficult to provide information section recommendations based on users' attention needs. For users, it is difficult to quickly and efficiently obtain the information they need on this network platform. Summary of the invention

[0004] The purpose of the present invention is to provide a user attention demand analysis and processing system and method based on big data to solve the above technical problems:

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A method for analyzing and processing user attention needs based on big data, comprising:

[0007] S1. Collect basic personal information of the target new user, including the user's gender and age group;

[0008] S2. Conduct a preliminary analysis of the basic personal information of the target new user based on big data, and push out the image and text click channels corresponding to the sub-pages of various sections on the main page according to the results of the preliminary analysis;

[0009] S3, collecting browsing information of the target new user, wherein the browsing information includes the number of clicks of the target new user on each picture and text click channel and the browsing time on the corresponding sub-page after the click;

[0010] S4. Perform data integration processing on the browsing information of target new users, and establish a focus recommendation strategy based on the results of the data integration processing.

[0011] As a further technical solution, the method further includes:

[0012] S5. Collecting the attention information of the target new user, wherein the attention information includes the types and quantities of the sections that the target new user follows;

[0013] S6. Based on the attention information of the target new user, other users who have the same attention sections as the target new user are obtained, and the research object user is screened out from the other users according to the number of attention sections of the other users.

[0014] S7. Conduct a comprehensive analysis of the attention information of target new users and research object users, and establish a recommendation update strategy based on the results of the comprehensive analysis.

[0015] As a further technical solution, the process of data integration processing of the browsing information of the target new user includes:

[0016] By formula Calculate and obtain the recommendation index R of each section;

[0017] Wherein, k is the preset first adjustment coefficient, and k>e -1 ; n is the total number of times the target new users click on each sub-page under the same section; T i,j Δt is the time that the target new user browses after clicking the jth subpage for the i-th time; j is the preset browsing time standard value of the j-th subpage;

[0018] The recommendation index R exceeds the preset threshold R cap The section is used as a recommended section and corresponding recommendation information is sent to the target new users.

[0019] As a further technical solution, the process of screening out the research object users from the other users according to the number of the follow-up sections of the other users includes:

[0020] Get the set of other users who have the same follow-up section as the target new user I = {A 1 , A 2 , A 3 …};

[0021] Filter out the N 0 The users corresponding to the set of follow-up sections with <|I|≤ΔN are taken as the research object users;

[0022] Where |I| is the cardinality of set I; N 0 is the number of forums that the target new user has followed; ΔN is the threshold of the number of forums.

[0023] As a further technical solution, the process of obtaining the section quantity threshold ΔN includes:

[0024] By formula Calculate and obtain the preset threshold value ΔN;

[0025] Wherein, l is the preset second adjustment coefficient, and 0<k<e -1 ; δ is the preset proportionality coefficient, and δ>1; N S is the total number of sections on the homepage; [] is the rounding function.

[0026] As a further technical solution, the process of comprehensively analyzing the attention information of target new users and research object users includes:

[0027] By formula Calculate the set I sum ;

[0028] Based on the frequency function calculation of the Collections class in Java programming technology, the collection I is obtained sum The number of occurrences of each element in f;

[0029] The number of occurrences f and the preset threshold f θ For comparison:

[0030] will satisfy the number of occurrences f ≥ f θ The section corresponding to the element is recommended to the target new users as a recommended section;

[0031] If the set I sum There is no such condition that the occurrence number f ≥ f θ If there is an element, no new recommendation information will be sent to the target new user.

[0032] As a further technical solution, the user attention demand analysis and processing method based on big data also includes:

[0033] S8. Count the number of times the same section is recommended to target new users within a preset time period, mark sections whose recommendation times exceed a preset recommendation times threshold, and do not recommend the marked sections during the recommendation update process.

[0034] A user attention demand analysis and processing system based on big data, comprising:

[0035] Information collection module, including personal information input terminal and web page information recording terminal;

[0036] The personal information input terminal is used to collect the personal information of the target new user, and the web page information recording terminal is used to collect the browsing information and attention information of the target new user and other users;

[0037] A processing module is used to process and analyze the collected browsing information and attention information of target new users and other users, and establish attention recommendation strategies and recommendation update strategies based on the results of the processing and analysis;

[0038] Push module, used to execute recommendation strategy and recommendation update strategy.

[0039] As a further technical solution, the processing module includes an integrated processing unit and a comprehensive analysis unit;

[0040] The integration processing unit is used to perform data integration processing on the browsing information of the target new user, and establish a focus recommendation strategy according to the result of the data integration processing;

[0041] The comprehensive analysis unit is used to conduct a comprehensive analysis on the attention information of the target new users and the research object users, and establish a recommendation update strategy based on the results of the comprehensive analysis.

[0042] Beneficial effects of the present invention:

[0043] Without the need to obtain a large amount of historical attention information of the target new user, the present invention can also analyze the historical attention information of other users who have similar attention tendencies as the target new user, predict the attention needs of the target new user through analysis, and provide information section recommendations according to the user's attention needs. Therefore, the platform can provide more efficient information recommendation services for new users, and users can also obtain the information they need on the platform more quickly. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described below in conjunction with the accompanying drawings.

[0045] Figure 1It is a flow chart of the main steps of the method for analyzing and processing user attention needs based on big data in the present invention;

[0046] Figure 2 This is a block diagram of the contents of the user attention demand analysis and processing system based on big data in the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 As shown, the present invention is a method for analyzing and processing user attention needs based on big data, comprising:

[0049] S1. Collect basic personal information of the target new user, including the user's gender and age group;

[0050] S2. Conduct a preliminary analysis of the basic personal information of the target new user based on big data, and push out the image and text click channels corresponding to the sub-pages of various sections on the main page according to the results of the preliminary analysis;

[0051] S3, collecting browsing information of the target new user, wherein the browsing information includes the number of clicks of the target new user on each picture and text click channel and the browsing time on the corresponding sub-page after the click;

[0052] S4. Perform data integration processing on the browsing information of target new users, and establish a focus recommendation strategy based on the results of the data integration processing.

[0053] S5. Collecting the attention information of the target new user, wherein the attention information includes the types and quantities of the sections that the target new user follows;

[0054] S6. Based on the attention information of the target new user, other users who have the same attention sections as the target new user are obtained, and the research object user is screened out from the other users according to the number of attention sections of the other users.

[0055] S7. Conduct a comprehensive analysis of the attention information of target new users and research object users, and establish a recommendation update strategy based on the results of the comprehensive analysis.

[0056] Through the above technical scheme, this embodiment provides a user attention demand analysis and processing method based on big data. Specifically, first, the personal basic information of the target new user is collected, and the personal basic information of the target new user is preliminarily analyzed based on the big data analysis technology. The section that the user may be interested in can be preliminarily judged according to the age and gender of the target new user and the historical information of other users. According to the results of the preliminary analysis, the picture and text click channels corresponding to the sub-pages of various sections are pushed out on the main page. Then, after the target new user clicks on the picture and text click channel by himself and browses for a period of time, the browsing information of the target new user is collected. The browsing information includes the number of clicks of the target new user on each picture and text click channel and the browsing time on the corresponding sub-page after clicking. The browsing information of the target new user is processed by data integration, and the attention recommendation strategy is established according to the result of the data integration processing. When the target new user pays attention to a section according to the attention recommendation, the attention information of the target new user can be collected. The attention information includes the type and number of the sections that the target new user pays attention to. Based on the attention information of the target new user, since people who pay attention to similar types of sections usually have a greater possibility of common interests and hobbies, other users who have the same attention section as the target new user can be obtained, and the research object user can be screened out from the other users according to the number of the sections that the other users pay attention to. Finally, a comprehensive analysis is conducted on the attention information of the target new users and the research object users, and a recommendation update strategy is established based on the results of the comprehensive analysis. Without the need to obtain a large amount of historical attention information of the target new users, the historical attention information of other users with similar attention tendencies as the target new users can also be analyzed to predict the attention needs of the target new users through analysis, and information section recommendations are provided according to the user's attention needs. Therefore, the platform can provide efficient services for new users, and users can also obtain the information they need on the platform more quickly.

[0057] The process of data integration and processing of the browsing information of target new users includes:

[0058] By formula Calculate and obtain the recommendation index R of each section;

[0059] Wherein, k is the preset first adjustment coefficient, and k>e -1 ; n is the total number of times the target new users click on each sub-page under the same section; T i,j Δt is the time that the target new user browses after clicking the jth subpage for the i-th time; j is the preset browsing time standard value of the j-th subpage;

[0060] The recommendation index R exceeds the preset threshold R cap The section is used as a recommended section and corresponding recommendation information is sent to the target new users.

[0061] Through the above technical solution, this embodiment provides a process for data integration processing of the browsing information of the target new user. Specifically, through the formula Calculate and obtain the recommendation index R of each section. The larger the recommendation index R, the more likely the user is to be interested in this section. Therefore, the recommendation index R exceeds the preset threshold R. cap The section is used as a recommended section and the corresponding recommendation information is sent to the target new user. It should be noted that k is a preset first adjustment coefficient, which can be obtained by fitting experimental data and will not be described in detail here. Δt j is the preset standard browsing time of the jth sub-page, which is related to the amount of information on the page.

[0062] The process of selecting the research object user from the other users according to the number of the follow-up sections of the other users includes:

[0063] Get the set of other users who have the same follow-up section as the target new user I = {A 1 , A 2 , A 3 …};

[0064] Filter out the N 0 The users corresponding to the set of follow-up sections with <|I|≤ΔN are taken as the research object users;

[0065] Where |I| is the cardinality of set I; N 0 is the number of forums that the target new user has followed; ΔN is the threshold of the number of forums.

[0066] The process of obtaining the section quantity threshold ΔN includes:

[0067] By formula Calculate and obtain the preset threshold value ΔN;

[0068] Wherein, l is the preset second adjustment coefficient, and 0<k<e -1 ; δ is the preset proportionality coefficient, and δ>1 (used to ensure ΔN>N 0 );N S is the total number of sections on the homepage; [] is the rounding function.

[0069] Through the above technical solution, this embodiment obtains the set of other users' concerned forums that have the same concerned forum as the target new user I = {A 1 , A 2 , A 3 …}, and select the ones that satisfy N 0The users corresponding to the set of follow-up sections with <|I|≤ΔN are taken as the research object users; the restriction of |I|≤ΔN is based on the consideration that users with too many followers usually use the platform for a long time, which also indirectly reflects that their interests and hobbies are likely to change in such a long time. Therefore, the reference value of the follow-up information of this type of users is relatively low, so they are excluded through the restriction of |I|≤ΔN.

[0070] The process of comprehensive analysis of the attention information of target new users and research object users includes:

[0071] By formula Calculate the set I sum ;

[0072] Based on the frequency function calculation of the Collections class in Java programming technology, the collection I is obtained sum The number of occurrences of each element in f;

[0073] The number of occurrences f and the preset threshold f θ Make a comparison:

[0074] will satisfy the number of occurrences f ≥ f θ The section corresponding to the element is recommended to the target new users as a recommended section;

[0075] If the set I sum There is no such condition that the occurrence number f ≥ f θ If there is an element, no new recommendation information will be sent to the target new user.

[0076] Through the above technical solution, this embodiment provides a process for comprehensively analyzing the attention information of target new users and research object users. Specifically, firstly, the formula Calculate the set I sum , based on the frequency function calculation of the Collections class in Java programming technology to obtain the collection I sum The number of occurrences of each element in f; compare the number of occurrences f with the preset threshold f θ For comparison: If f≥f θ , then it means that the set I sum There are more users who follow this section, and the possibility that this section can meet the attention needs of the target new users is high, so the number of occurrences f ≥ f θ The section corresponding to the elements of is recommended as the recommended section to the target new user; if the set I sum There is no such condition that the occurrence number f ≥ f θ Elements of the description set I sumThe user-focused sections in the target new user have little reference value for predicting the focus needs of the target new user, so no new recommendation information is sent to the target new user. It should be noted that the above recommendation method does not recommend the sections that the new user has focused on to the target new user by default.

[0077] The user attention demand analysis and processing method based on big data also includes:

[0078] S8. Count the number of times the same section is recommended to target new users within a preset time period, mark sections whose recommendation times exceed a preset recommendation times threshold, and do not recommend the marked sections during the recommendation update process.

[0079] Through the above technical solution, this embodiment provides a process for reasonably restricting the section recommendation process. Specifically, the number of times the same section is recommended to the target new user can be counted within a week. The more times the same section is recommended, the less interested the target new user is in this section. Therefore, the section whose recommendation times exceed the preset recommendation times threshold is marked, and the marked section is not recommended during the recommendation update process.

[0080] See also Figure 2 As shown, a user attention demand analysis and processing system based on big data includes:

[0081] Information collection module, including personal information input terminal and web page information recording terminal;

[0082] The personal information input terminal is used to collect the personal information of the target new user, and the web page information recording terminal is used to collect the browsing information and attention information of the target new user and other users;

[0083] A processing module is used to process and analyze the collected browsing information and attention information of target new users and other users, and establish attention recommendation strategies and recommendation update strategies based on the results of the processing and analysis;

[0084] Push module, used to execute recommendation strategy and recommendation update strategy.

[0085] The processing module includes an integrated processing unit and a comprehensive analysis unit;

[0086] The integration processing unit is used to perform data integration processing on the browsing information of the target new user, and establish a focus recommendation strategy according to the result of the data integration processing;

[0087] The comprehensive analysis unit is used to conduct a comprehensive analysis on the attention information of the target new users and the research object users, and establish a recommendation update strategy based on the results of the comprehensive analysis.

[0088] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for analyzing and processing user attention needs based on big data, characterized in that: The method comprises: S1. Collect basic personal information of the target new user, including the user's gender and age group; S2. Conduct a preliminary analysis of the basic personal information of the target new user based on big data, and push out the image and text click channels corresponding to the sub-pages of various sections on the main page according to the results of the preliminary analysis; S3, collecting browsing information of the target new user, wherein the browsing information includes the number of clicks of the target new user on each picture and text click channel and the browsing time on the corresponding sub-page after the click; S4, performing data integration processing on the browsing information of the target new users, and establishing a focus recommendation strategy based on the results of the data integration processing; The method further comprises: S5. Collecting the attention information of the target new user, wherein the attention information includes the types and quantities of the sections that the target new user follows; S6. Based on the attention information of the target new user, other users who have the same attention section as the target new user are obtained, and the research object user is screened out from the other users according to the number of attention sections of the other users; S7. Comprehensively analyze the attention information of target new users and research object users, and establish a recommendation update strategy based on the results of the comprehensive analysis; The process of data integration and processing of the browsing information of target new users includes: By formula Calculate and obtain the recommendation index R of each section; Wherein, k is the preset first adjustment coefficient, and k>e -1 ; n is the total number of times the target new users click on each sub-page under the same section; T i,j Δt is the time that the target new user browses after clicking the jth subpage for the i-th time; j is the preset browsing time standard value of the j-th subpage; The recommendation index R exceeds the preset threshold R cap The section is used as a recommended section and corresponding recommendation information is sent to target new users; The process of selecting the research object user from the other users according to the number of the follow-up sections of the other users includes: Get the set of follow-up boards of other users who have the same follow-up boards as the target new user I = {A1, A2, A3...}; Filter out users corresponding to the set of follow-up sections that satisfy N0<|I|≤ΔN and use them as research object users; Where |I| is the cardinality of set I; N0 is the number of forums that the target new user has followed; ΔN is the threshold of the number of forums; The process of obtaining the section quantity threshold ΔN includes: By formula Calculate and obtain the preset threshold value ΔN; Wherein, l is the preset second adjustment coefficient, and 0 <k<e -1 ; δ is the preset proportionality coefficient, and δ>1; N S The total number of sections on the homepage; The process of comprehensive analysis of the attention information of target new users and research object users includes: By formula Calculate the set I sum ; Based on the frequency function calculation of the Collections class in Java programming technology, the collection I is obtained sum The number of occurrences of each element in f; The number of occurrences f and the preset threshold f θ For comparison: will satisfy the number of occurrences f ≥ f θ The section corresponding to the element is recommended to the target new users as a recommended section; If the set I sum There is no such condition that the occurrence number f ≥ f θ If there is an element, no new recommendation information will be sent to the target new user.

2. According to the method for analyzing and processing user attention needs based on big data in claim 1, it is characterized in that: The method further comprises: S8. Count the number of times the same section is recommended to target new users within a preset time period, mark sections whose recommendation times exceed a preset recommendation times threshold, and do not recommend the marked sections during the recommendation update process.

3. A user attention demand analysis and processing system based on big data, characterized in that: The system is used to execute the user attention demand analysis and processing method based on big data according to any one of claims 1 to 2, and the system includes: Information collection module, including personal information input terminal and web page information recording terminal; The personal information input terminal is used to collect the personal information of the target new user, and the web page information recording terminal is used to collect the browsing information and attention information of the target new user and other users; A processing module is used to process and analyze the collected browsing information and attention information of target new users and other users, and establish attention recommendation strategies and recommendation update strategies based on the results of the processing and analysis; Push module, used to execute recommendation strategy and recommendation update strategy.

4. According to the user attention demand analysis and processing system based on big data as described in claim 3, it is characterized in that: The processing module includes an integrated processing unit and a comprehensive analysis unit; The integration processing unit is used to perform data integration processing on the browsing information of the target new user, and establish a focus recommendation strategy according to the result of the data integration processing; The comprehensive analysis unit is used to conduct a comprehensive analysis on the attention information of the target new users and the research object users, and establish a recommendation update strategy based on the results of the comprehensive analysis.