Information statistics management platform based on data analysis

Abstract

The invention relates to the technical field of information statistics management, in particular to an information statistics management platform based on data analysis. Comprising a data acquisition module, a server, a data association module, a data recommendation module and a data maintenance module, the data acquisition module is used for acquiring platform information and personnel information and sending the information to the server for storage; the data association module is used for analyzing data stored in the public platform to obtain an association value and carrying out related content display; the data recommendation module analyzes the matched data and browsing habits of the user to obtain a recommendation value, and performs data recommendation according to the recommendation value; the data recommendation module analyzes the matched data and browsing habits of the user to obtain a recommendation value, and performs data recommendation according to the recommendation value; through multi-dimensional matching and feedback, it is ensured that the content recommended to the user is highly related to the keyword input by the user, the recommendation accuracy is improved, and the problem of the user is also responded in time.

Description

Technical Field

[0001] The present invention relates to the technical field of information statistics management, and in particular to an information statistics management platform based on data analysis. Background Art

[0002] Information statistics management platform refers to the integration, processing and management of scattered information resources through various technical means and methods, so that users can easily obtain, use and share information. It usually includes hardware, software and management personnel, and has the ability to store, process, transmit and present information.

[0003] With the continuous development of information technology, the information statistics management platform includes a large amount of data. During use, users will face problems such as slow response and inaccurate search results when searching, and cannot respond to user feedback in a timely manner, affecting the response speed and availability of the information statistics management platform. Summary of the invention

[0004] To this end, the present invention provides an information statistics management platform based on data analysis to overcome the problems mentioned in the above background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides an information statistics management platform based on data analysis, comprising: a data acquisition module, a server, a data association module, a data recommendation module and a data maintenance module;

[0006] The data collection module is used to collect platform information and user information and send them to the server for storage;

[0007] The data association module is used to analyze the data stored in the server to obtain the association value and display the related content; the specific steps are as follows:

[0008] When the user inputs a set of search keywords, the keywords are segmented and the main keywords are extracted; an inverted index is established for all data paragraphs and keywords stored in the server to quickly locate the paragraph where each keyword is located and the data set where it is located; the search keywords entered by the user are matched with the keywords in the data paragraph; the total number of keywords entered by the user is set to n, where n = 1, 2, 3...N, N is a positive integer, N represents the total number of keywords retrieved by the user, and n represents any one of the keywords; the total number of times the keyword appears in the paragraph and the total number of words in the paragraph are obtained, and the total number of times the keyword n ​​appears in the paragraph and the total number of words in the paragraph are substituted into the set formula Calculate the frequency of occurrence of keyword n ​​in the paragraph Fn, where a5 is the set weight factor; obtain the weight of keyword n ​​in the paragraph, using the formula Calculate the weight Wn of keyword n ​​in the paragraph, where M represents the total number of data, dn represents the number of data containing keyword n, and a6 is the set weight factor; obtain the character distance between keyword n ​​and the beginning of the paragraph, obtain the position weight of keyword n ​​in the paragraph, and use the formula Calculate the position weight Pn of keyword n ​​in the paragraph, where a7 is the set weight factor; substitute the values ​​of the keyword frequency Fn in the paragraph, the keyword weight Wn in the paragraph, the keyword position weight Pn in the paragraph and the matching value Gi into the formula Calculate the associated value Sni of the matching paragraph;

[0009] The paragraphs with the highest relevance value and the related data are displayed to the user. The matching degree and related data of each paragraph can be marked through the interface, adding "highly matched" or "related content" labels; allowing users to mark the recommended paragraphs or related data to mark whether they are relevant; when the platform data is updated or added, the server will re-extract the paragraph keywords and update the inverted index to ensure that the data is always up to date;

[0010] The data recommendation module obtains recommendation values ​​by analyzing matching data and user browsing habits, and recommends data based on the recommendation values;

[0011] The data maintenance module maintains the data platform based on user labels and feedback on the data.

[0012] As a preferred embodiment of the present invention, the specific analysis steps of the matching value are:

[0013] Classify all data in the server by type, match the retrieved text with all data types stored in the server by keywords, select the data type with a high degree of overlap with the retrieved text and match it as related data, and record it as i, where i = 1, 2, 3...I, I is a positive integer, I represents the total number of related data, and i represents any one of the related data; record the data application field of related data i as Li; record the time when related data i is uploaded to the server as Ti; record the number of recommendations of related data i as Ci; record the number of clicks on related data i as Di; substitute the values ​​of the data field Li, upload time Ti, recommendation number Ci and click number Di of the related data into the set formula The matching value Gi of the associated data is calculated, where a1, a2, a3 and a4 are respectively the set weight factors, and λ is the set correction factor.

[0014] As a preferred embodiment of the present invention, the platform information in the data collection module includes: data type, data click times, data upload time, and data recommendation times; the personnel information includes user information and background processing personnel information; the user information includes: user account name, mobile phone number, user online time, and user browsing interests; the background processing personnel information includes: background processing personnel name, age, employment time, and processing and maintenance times;

[0015] As a preferred embodiment of the present invention, the specific analysis steps of the recommended value are:

[0016] Get the start time and end time of each login of the user on the platform, calculate the difference between the start time and the end time of each login to get the browsing time, and sum up all the browsing time to get the total browsing time, and record it as Rj, where j = 1, 2, 3...J, J is a positive integer, J represents the total number of users of the information statistics management platform, and j represents the sequence number of any one of the users; get the total number of times the user logs in on the platform and record it as Zj; calculate the difference between the browsing start time of two consecutive logins of the user and the end time of the last browsing to get the browsing interval time, sum up all the browsing interval time to get the total browsing interval time, and record it as Hj, then the average interval time is Get the total number of recommendations and the number of clicks on the platform and record them as Uj and Vj respectively, then the user click rate is The associated value Sni, the total browsing time of the user Rj, and the average browsing interval time Total number of logins Zj, total number of platform recommendations Uj, number of times users click on recommendations Vj, and user click-through rate Substitute the value of into the formula The user's recommended value Knij is calculated, where b1, b2, b3, b4 and b5 are the set weight factors, and μ is the set correction factor;

[0017] According to the matching value size of the associated data, the top ten data with matching values ​​from large to small are screened out as candidate data, and they are marked as recommended data. At the same time, the recommendation number of the candidate data is increased once and sent to the server for storage; a recommendation value threshold is set, and the user's recommendation value is compared and analyzed with the recommendation threshold; when the user's recommendation value is greater than the set recommendation threshold, ten recommended data are pushed for customer display; when the user's recommendation value is less than or equal to the set recommendation threshold, five recommended data are pushed for customer display.

[0018] As a preferred implementation of the present invention, the specific steps of data platform maintenance are:

[0019] The backstage personnel with the largest maintenance value will be maintained according to the urgency, and the pending status of the backstage personnel will be changed to the processing status. At the same time, the number of processing times of the personnel will be increased by one and sent to the server storage; when the backstage personnel in the processing status completes the maintenance, the backstage personnel will confirm and change the status to the pending status, and re-add the personnel to be processed for assigned maintenance; repeat the above steps until the problem reported by the user is resolved.

[0020] As a preferred embodiment of the present invention, the specific analysis steps of the maintenance value and the urgency are as follows:

[0021] Set up a user feedback form in the data, where users can select the category of the feedback problem: weak data relevance, incomplete data, duplicate data, incorrect data and fill in a detailed description, and set the urgency of the feedback to low, medium and high levels;

[0022] Set the status of the backend processing personnel to pending status and processing status, obtain the time of employment of the backend processing personnel and record it as Yx, where x = 1, 2, 3...X, X is a positive integer, X represents the total number of backend processing personnel, and x represents the sequence number of any one of them; obtain the number of processing times of the backend processing personnel and record it as Ex, substitute the values ​​of the urgency Q, the processing personnel's time of employment Yx and the number of processing times Ex into the formula The maintenance value θ of the background processing personnel is calculated, where β1, β2 and β3 are the set weight factors respectively.

[0023] Beneficial effects of the present invention:

[0024] 1. By classifying the data in the server by type and using keyword matching, the data type related to the user's search term can be quickly located; through matching degree calculation and multi-dimensional matching, it can ensure that the content recommended to the user is highly relevant to the keyword they enter, thereby improving the accuracy of the recommendation; the recommendation results are generated based on the matching value of the associated data. The higher the recommendation value, the more relevant the data is to the user's needs, and it can also reflect the timeliness and popularity of the data; the dynamic associated display method helps to prioritize the most valuable data and optimize the user's search experience; by extracting the search keyword and establishing an inverted index with the data paragraph, the paragraph where the keyword is located can be quickly located, reducing the time consumption of the global search. The inverted index ensures that when new data is updated, the associated display results can be updated in time and kept in real time, thereby improving the data processing efficiency of the platform; the paragraph matching mechanism based on keyword distribution makes the display results closer to the actual needs of users according to the existence of keywords and their importance in the paragraph.

[0025] 2. By determining the relevance of data to user search content, the higher the correlation, the more in line with user needs the recommended content is, thereby improving the accuracy of recommendations; users with longer browsing time and more logins are considered active users, so more recommended content will be pushed to active users first, improving user experience and platform stickiness; users who log in frequently and users who respond positively to recommended content will receive higher recommendation values, dynamically adapting to their needs and avoiding duplicate and inefficient recommendations; by analyzing click-through rates, users who are interested in recommended content can be identified and their recommendation values ​​increased, thereby improving users' attention and participation in recommended content; combining user behavior data and content matching, and formulating recommendation results through multi-dimensional analysis can improve the accuracy and personalization of recommendations.

[0026] 3. By classifying the urgency level, urgent or high-impact issues can be dealt with first, ensuring that critical issues are responded to quickly; through multi-dimensional evaluation, the most suitable personnel are assigned to handle the issues, ensuring that experienced personnel handle high-priority issues and avoiding backlogs of tasks for novices; the task status of backstage personnel is updated in the system at any time to ensure that tasks are reallocated immediately after completion, avoiding redundant task backlogs and achieving efficient task flow; the feedback mechanism can not only respond to user issues in a timely manner, but also ensure that the data quality of the platform is always at a high level by continuously updating the processing status and task assignments. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of system module connection of the present invention. DETAILED DESCRIPTION

[0028] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0029] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0030] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0031] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0032] See also Figure 1 As shown, the present invention is an information statistics management platform based on data analysis, including: a data acquisition module, a server, a data association module, a data recommendation module and a data maintenance module;

[0033] The data collection module is used to collect platform information and personnel information and send them to the server for storage; the platform information includes: data type, data click times, data upload time and data recommendation times; the personnel information includes user information and backend processing personnel information; user information includes: user account name, mobile phone number, user online time and user browsing interests; backend processing personnel information includes: backend processing personnel name, age, employment time and processing maintenance times;

[0034] The data association module is used to analyze the data stored in the server to obtain the association value and display the related content; the specific steps are as follows:

[0035] Classify all data in the server by type, match the retrieved text with all data types stored in the server by keywords, select the data type with a high degree of overlap with the retrieved text and match it as related data, and record it as i, where i = 1, 2, 3...I, I is a positive integer, I represents the total number of related data, and i represents any one of the related data; record the data application field of related data i as Li; record the time when related data i is uploaded to the server as Ti; record the number of recommendations of related data i as Ci; record the number of clicks on related data i as Di; substitute the values ​​of the data field Li, upload time Ti, recommendation number Ci and click number Di of the related data into the set formula The matching value Gi of the associated data is calculated, where a1, a2, a3 and a4 are respectively the set weight factors, and λ is the set correction factor. It can be obtained from the formula that the fewer the applicable fields of the associated data, the higher the accuracy of the associated data, and the greater the matching value; the smaller the upload server time of the associated data, the greater the reference of the associated data, and the greater the matching value; the more times the recommendation is, the greater the matching value; the more times the user clicks, the greater the matching value;

[0036] When the user inputs a set of search keywords, the keywords are segmented and the main keywords are extracted; (the keywords in a set of search keywords that are the same as several preset target keywords are the main keywords) an inverted index is established for all data paragraphs and keywords stored in the server to quickly locate the paragraph where each keyword is located and the data set where it is located; the search keywords input by the user are matched with the keywords in the data paragraph; the total number of keywords input by the user is set to n, where n = 1, 2, 3...N, N is a positive integer, N represents the total number of keywords retrieved by the user, and n represents any one of the keywords; the total number of times keyword n ​​appears in the paragraph and the total number of words in the paragraph are obtained, and the total number of times keyword n ​​appears in the paragraph and the total number of words in the paragraph are substituted into the set formula Calculate the frequency of occurrence of keyword n ​​in the paragraph Fn, where a5 is the set weight factor; obtain the weight of keyword n ​​in the paragraph, using the formula Calculate the weight Wn of keyword n ​​in the paragraph, where M represents the total number of data, dn represents the number of data containing keyword n, and a6 is the set weight factor; obtain the character distance between keyword n ​​and the beginning of the paragraph, obtain the position weight of keyword n ​​in the paragraph, and use the formula Calculate the position weight Pn of keyword n ​​in the paragraph, where a7 is the set weight factor; substitute the values ​​of the occurrence frequency Fn of keyword n ​​in the paragraph, the weight Wn of keyword n ​​in the paragraph, the position weight Pn of keyword n ​​in the paragraph and the matching value Gi into the set formula The correlation value Sni of the matching paragraph is calculated; from the formula, the more frequently the keyword appears in the paragraph, the higher the correlation between the paragraph and the keyword, and the higher the correlation value; the higher the keyword weight, the higher the correlation value; the keyword appears in an important position in the paragraph, which means that the paragraph is more correlated with the search term input by the user, and the higher the correlation value; the higher the matching value of the associated data, the higher the correlation value;

[0037] The paragraphs with the highest relevance value and the related data are displayed to the user. The matching degree and related data of each paragraph can be marked through the interface, adding "highly matched" or "related content" labels; allowing users to mark the recommended paragraphs or related data to mark whether they are relevant; when the platform data is updated or added, the server will re-extract the paragraph keywords and update the inverted index to ensure that the data is always up to date;

[0038] By classifying the data in the server by type and using keyword matching, the data type related to the user's search term can be quickly located; by matching degree calculation and multi-dimensional matching, it can ensure that the content recommended to the user is highly relevant to the keyword they input, thereby improving the accuracy of the recommendation; the recommendation results are generated based on the matching value of the associated data. The higher the recommendation value, the more relevant the data is to the user's needs, and it can also reflect the timeliness and popularity of the data; the dynamic association display method helps to prioritize the most valuable data and optimize the user's search experience; by extracting the search keyword and establishing an inverted index with the data paragraph, the paragraph where the keyword is located can be quickly located, reducing the time consumption of the global search. The inverted index ensures that when new data is updated, the associated display results can be updated in time and kept in real time, thereby improving the data processing efficiency of the platform; the paragraph matching mechanism based on keyword distribution makes the display results closer to the actual needs of users according to the existence of keywords and their importance in the paragraph;

[0039] The data recommendation module obtains the recommendation value by analyzing the matching data and the user's browsing habits, and recommends data based on the recommendation value; the specific steps are as follows:

[0040] Get the start time and end time of each login of the user on the platform, calculate the difference between the start time and the end time of each login to get the browsing time, and sum up all the browsing time to get the total browsing time, and record it as Rj, where j = 1, 2, 3...J, J is a positive integer, J represents the total number of users of the information statistics management platform, and j represents the sequence number of any one of the users; get the total number of times the user logs in on the platform and record it as Zj; calculate the difference between the browsing start time of two consecutive logins of the user and the end time of the last browsing to get the browsing interval time, sum up all the browsing interval time to get the total browsing interval time, and record it as Hj, then the average browsing interval time is Get the total number of recommendations and the number of clicks on the platform and record them as Uj and Vj respectively, then the user click rate is The associated value Sni, the total browsing time of the user Rj, and the average browsing interval time Total number of logins Zj, total number of platform recommendations Uj, number of times users click on recommendations Vj, and user click-through rate Substitute the value of into the formula The user's recommendation value Knij is calculated, where b1, b2, b3, b4 and b5 are the set weight factors, and μ is the set correction factor. It can be seen from the formula that the higher the degree of fit, the stronger the correlation between the data and the user's search content, and the greater the recommendation value; the longer the total browsing time, the more content will be pushed to highly active users, and the greater the recommendation value; the better the user's response to the recommended content, the higher the click-through rate, and the greater the recommendation value; the higher the activity, the greater the recommendation value; the shorter the browsing interval, the more frequent the user visits the platform, and the greater the recommendation value;

[0041] According to the matching value size of the associated data, the top ten data with matching values ​​from large to small are screened out as candidate data, and they are marked as recommended data. At the same time, the recommendation number of the candidate data is increased once and sent to the server for storage; a recommendation value threshold is set, and the user's recommendation value is compared and analyzed with the recommendation threshold; when the user's recommendation value is greater than the set recommendation threshold, ten recommended data are pushed for customer display; when the user's recommendation value is less than or equal to the set recommendation threshold, five recommended data are pushed for customer display.

[0042] By determining the relevance of data to user search content, the higher the relevance, the more in line with user needs the recommended content is, thus improving the accuracy of recommendations; users with longer browsing time and more logins are considered active users, so more recommended content is pushed to active users first, improving user experience and platform stickiness; users who log in frequently and those who respond positively to recommended content will receive higher recommendation values, dynamically adapting to their needs and avoiding duplicate and inefficient recommendations; by analyzing click-through rates, users who are interested in recommended content can be identified and their recommendation values ​​increased, thus improving users' attention and participation in recommended content; combining user behavior data and content matching, formulating recommendation results through multi-dimensional analysis can improve the accuracy and personalization of recommendations;

[0043] The data maintenance module maintains the data platform based on the user's tags and feedback on the data; the specific steps are as follows:

[0044] Step 1: Set up a user feedback form in the data. Users can choose the category of the feedback problem: weak data relevance, incomplete data, duplicate data, incorrect data and fill in a detailed description. The urgency of the feedback is set as Q1, Q2 and Q3, where Q1 is low urgency, Q2 is medium urgency, and Q3 is high urgency;

[0045] Step 2: Set the status of the backend processing personnel to pending status and processing status, obtain the time of employment of the backend processing personnel and record it as Yx, where x = 1, 2, 3...X, X is a positive integer, X represents the total number of backend processing personnel, and x represents the sequence number of any one of them; obtain the number of processing times of the backend processing personnel and record it as Ex, substitute the values ​​of the urgency Q, the processing personnel's time of employment Yx and the number of processing times Ex into the set formula The maintenance value θ of the backend processing personnel is calculated, where β1, β2 and β3 are respectively the set weight factors; the larger the maintenance value θ of the backend processing personnel is, the higher the priority the backend processing personnel has in maintaining the backend feedback issues;

[0046] Step 3: Prioritize the backstage personnel with the largest maintenance value to be processed Q3 for maintenance, and change the pending status of the backstage personnel to the processing status. At the same time, the number of processing times of the processing personnel is increased and sent to the server for storage; when the backstage processing personnel in the processing status completes the maintenance, the backstage processing personnel confirms and changes the status to pending, and re-adds the pending personnel for allocation maintenance; repeat the above steps until the problem reported by the user is resolved;

[0047] By classifying the level of urgency, urgent or high-impact issues can be dealt with first, ensuring that critical issues receive a quick response; through multi-dimensional evaluation, the most suitable personnel are assigned to handle the issues, ensuring that experienced personnel handle high-priority issues while avoiding a backlog of tasks for novices; the task status of backstage personnel is updated at any time in the system to ensure that tasks are reallocated immediately after completion, avoiding a backlog of redundant tasks and achieving efficient task flow; the feedback mechanism can not only respond to user issues in a timely manner, but also ensure that the data quality of the platform is always at a high level by continuously updating the processing status and task assignments.

[0048] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Information statistics management platform based on data analysis, including: Data collection module, server and data association module; The data collection module is used to collect platform information and personnel information and send them to the server for storage; it is characterized in that the data association module is used to analyze the data stored in the server to obtain the association value and display the related content; the specific steps are as follows: When the user inputs a set of search keywords, the keywords are segmented and the keywords are extracted; an inverted index is established for all data paragraphs and keywords stored in the server to quickly locate the paragraph where each keyword is located and the data set where it is located; the search keywords entered by the user are matched with the keywords in the data paragraph; the total number of times the keyword appears in the paragraph and the total number of words in the paragraph are obtained, and the frequency of occurrence of the keyword in the paragraph is calculated; the number of keywords in the paragraph, the total number of data, and the number of data containing the keyword are normalized to obtain the weight of the keyword in the paragraph; the normalization is performed according to the character distance between the keyword and the beginning of the paragraph to obtain the position weight of the keyword in the paragraph; the frequency of the keyword in the paragraph, the weight of the keyword in the paragraph, the position weight of the keyword in the paragraph, and the numerical value of the matching value are normalized to obtain the association value of the matching paragraph; The paragraphs with the highest correlation value and related associated data are displayed to the user. The matching degree and related data of each paragraph are marked through the interface, and the labels of "highly matched" or "related content" are added; the user is allowed to mark the recommended paragraphs or related data to indicate whether they are relevant; when the platform data is updated or added, the server re-extracts the paragraph keywords and updates the inverted index.

2. The information statistics management platform based on data analysis according to claim 1 is characterized in that: The specific analysis process of the matching value is as follows: Classify all data in the server by type, match the retrieved text with all data types stored in the server by keywords, select the data type with a high degree of overlap with the retrieved text and match it as related data; obtain the data application field of the related data; obtain the time when the related data was uploaded to the server; obtain the number of recommendations for the related data; The number of clicks of the associated data is obtained; the data field, upload time, recommendation number and click number of the associated data are normalized to obtain the matching value of the associated data.

3. The information statistics management platform based on data analysis according to claim 1 is characterized in that: The platform information collected by the data collection module includes: data type, number of data clicks, data upload time, and data recommendation times; personnel information includes user information and backend processing personnel information; user information includes: user account name, mobile phone number, user online time, and user browsing interests; backend processing personnel information includes: backend processing personnel's name, age, time of employment, and number of processing and maintenance times.

4. The information statistics management platform based on data analysis according to claim 1 is characterized in that: It also includes a data recommendation module, which obtains a recommendation value by analyzing matching data and user browsing habits, and recommends data based on the recommendation value; The specific analysis steps for the recommended values ​​are: Obtain the start time and end time of each login of the user on the platform, calculate the difference between the start time and end time of each login to obtain the browsing time, and sum up all browsing times to obtain the total browsing time; obtain the total number of times the user logs in to the platform; calculate the difference between the browsing start time of two consecutive logins of the user and the end time of the previous browsing to obtain the browsing interval time, sum up all browsing interval time to obtain the total browsing interval time, and calculate the average interval time based on the total number of times the user logs in to the platform; Obtain the total number of recommendations and clicks on the platform, and calculate the user click-through rate based on the total number of recommendations and clicks on the platform; The association value, total browsing time of users, average browsing interval time, total login times, total platform recommendations, number of times users click on recommendations and user click-through rate are normalized to obtain the recommendation value; the user's recommendation value is compared and analyzed with the recommendation threshold. When the user's recommendation value is greater than the set recommendation threshold, ten recommendation data are pushed for customer display; when the user's recommendation value is less than or equal to the set recommendation threshold, five recommendation data are pushed for customer display.

5. The information statistics management platform based on data analysis according to claim 1 is characterized in that: It also includes a data maintenance module, which maintains the data platform based on user labels and feedback on the data, specifically: The backstage personnel with the largest maintenance value will be maintained according to the urgency, and the pending status of the backstage personnel will be changed to the processing status. At the same time, the number of processing times of the personnel will be increased by one and sent to the server storage; when the backstage personnel in the processing status completes the maintenance, the backstage personnel will confirm and change the status to the pending status, and re-add the personnel to be processed for assigned maintenance; until the problem reported by the user is resolved.

6. The information statistics management platform based on data analysis according to claim 5 is characterized in that: The specific analysis steps for maintenance value and urgency are as follows: Set up a user feedback form in the data, and the user selects the category of the feedback problem: data relevance is not strong, data is incomplete, data is repeated, data is incorrect, and fills in a detailed description, and sets the low urgency, medium urgency, and high urgency according to the urgency of the feedback; Set the status of the backend processing personnel to pending status and being processed status, and obtain the employment time of the backend pending personnel; The values ​​of urgency, length of time the processing personnel have been on the job, and number of processing times are normalized to obtain the maintenance value of the background processing personnel.

Images