Data Processing Method Applied to a Feedback Platform

Abstract

The present invention discloses a data processing method applied to a feedback platform, including: extracting key content from the problem information feedback by users, performing weighted algorithm processing on the extracted information, and classifying common problems; defining labels for the members of the observation group; intelligently matching the common problems with the labels of the members of the observation group, and having the matched members of the observation group reply to and solve the problems; converting the online comments after the common problems are solved into quantifiable satisfaction degrees. The technical effects of the present invention: overcome the technical problems of low processing efficiency and poor pertinence of the traditional method, and greatly improve the efficiency, accuracy and scientificity of feedback problem processing.

Description

Technical Field

[0001] The present invention relates to the technical field of problem processing platforms, and particularly to a data processing method applied to a feedback platform. Background Art

[0002] This project is an online platform for network-based political participation in the media industry. Users can provide problem feedback and expose issues through the platform. The platform forwards the problems to government functional departments, and the functional departments handle them with online responses. Finally, users can evaluate the satisfaction based on the response results of the functional departments. Generally, the evaluation results are: satisfied, average, and dissatisfied.

[0003] The existing solution provides an online platform for network-based political participation, lacking intelligent analysis of the problems feedback by users. The problems reported by netizens vary in size, are numerous and miscellaneous. The platform fails to extract the commonalities of the problems well, that is, it cannot extract and summarize the key content of the problem information feedback by users. In this way, in-depth analysis, rapid positioning, and professional tracking and processing of the feedback problems cannot be carried out. The traditional method of the existing online platform for network-based political participation has low processing efficiency, poor pertinence, and low efficiency and accuracy in problem handling. Summary of the Invention

[0004] The purpose of the present invention is to provide a data processing method applied to a feedback platform to solve the above technical problems. The specific technical solutions are as follows:

[0005] A data processing method applied to a feedback platform includes the following steps:

[0006] Extract the key content of the problem information feedback by users, and perform weighted algorithm processing on the extracted information to classify the common problems;

[0007] Define labels for the members of the observation group;

[0008] Intelligently match the problems with commonalities with the labels of the members of the observation group, and have the matched members of the observation group reply and solve the problems;

[0009] Convert the online comments after the problems with commonalities are solved into quantifiable satisfaction degrees;

[0010] The method for extracting the key content of the problem information feedback by users includes:

[0011] Establish a database for the feedback platform. The database collects the feedback problem information of users, including: picture information and text information;

[0012] Obtain a list of key information;

[0013] Purify the key information in the key information list to obtain the keyword information of the problem information feedback by each user, and define its part of speech to form a keyword information library;

[0014] The method of processing the extracted information by a weighted algorithm and classifying common problems includes:

[0015] Comprehensively consider multiple dimensions such as the number of user feedback problems, page views, comments, and likes, and calculate a popularity score for each keyword. The specific formula is as follows:

[0016] Popularity score = (the number of problems corresponding to the keyword / the number of problems corresponding to the highest keyword in the current period) * 0.6 + (the page views of the corresponding problems / the highest page views of the corresponding problems) * 0.2 + (the number of comments on the corresponding problems / the highest number of comments on the problems) * 0.15 + (the number of likes on the corresponding problems / the highest number of likes on the problems) * 0.05,

[0017] Select the mainstream common problems according to the popularity score.

[0018] Furthermore, the data processing method applied to the feedback platform also includes:

[0019] Process the extracted information to obtain sudden problems;

[0020] Intelligently match the sudden problems with the labels of the members of the observation group, and have the matched members of the observation group reply to and solve the problems;

[0021] Convert the online comments after the sudden problems are solved into quantifiable satisfaction.

[0022] Furthermore, the specific method for processing the extracted information to obtain sudden problems is:

[0023] Statistical growth rate of the problems corresponding to each keyword, if the statistical growth rate exceeds the preset rate, the problems corresponding to the keyword are classified as sudden problems.

[0024] Furthermore, the specific method for statistical growth rate of the problems corresponding to each keyword is:

[0025] Statistical number of problems corresponding to each keyword and the release time of each problem, calculate the time span of the release time of these problems, and then calculate the ratio of the number of problems and the time span, and use it as the growth rate.

[0026] Furthermore, after calculating the time span of the release time of these problems, determine whether the time span is greater than the preset minimum span value. If the time span is greater than the preset minimum span value, further calculate the ratio of the number of problems and the time span, and use it as the growth rate.

[0027] Furthermore, for each piece of keyword information in the problem information feedback by users, key tags of people, events, places, things, and organizations are generated for managers to quickly understand and decide whether to adopt it.

[0028] Furthermore, after the keyword information library is formed, the method for extracting key content from the problem information feedback by users further includes:

[0029] Establishing a two-level theme library of departments and problems;

[0030] In the early stage, the corresponding information is input into the corresponding theme library for classification through the method of user filling and manual correction;

[0031] In the later stage, by using the data accumulation input in the early stage, a bottom-level word library is formed, that is, different theme libraries correspond to different keyword information libraries, so as to realize automatic classification of the content of users' questions and exposures, and continuously optimize and adjust during the actual use process.

[0032] Furthermore, the method for defining tags for the members of the observation group includes:

[0033] Data collection:

[0034] Collect the basic information, professional background, hobbies, and relevant experience of the members of the observation group. The basic information includes: gender, age, permanent residence area. The professional background includes: education level, major, and main research direction. The hobbies include: hobby type, obtained certificates, competition items; the relevant experience includes: participated projects, published papers;

[0035] Tag definition:

[0036] Based on the basic information of the members, construct personal portrait tags;

[0037] Construct industry expertise tags through the professional background, hobbies, and relevant experience of the members;

[0038] Tag verification and optimization:

[0039] After defining the personal portrait tags and industry expertise tags of the members, verify and optimize the personal portrait tags and industry expertise tags of the members;

[0040] Through extracting and classifying the data information of the professional background, hobbies, and relevant experience of the members of the observation group, summarize the industry expertise information words that can reflect the professional ability and interests of the members, and form industry expertise tags based on the industry expertise information words;

[0041] Verify and optimize the industry expertise tags of the members by comparing and verifying with the information of other members of the observation group;

[0042] The method for intelligently matching problems with commonalities with the tags of the members of the observation group includes:

[0043] Using text matching technology to match and analyze the problems feedback by users with the tags of the members of the observation group, including:

[0044] Industry mapping matching: According to the problem classification, determine the industry or field to which it belongs, and search for tags related to this industry or field in the tags of the members of the observation group, so as to screen out members with relevant industry backgrounds or professional knowledge;

[0045] Interest mapping matching: Use the keywords in the problem to match other tags such as the hobbies and professional certificates of the members of the observation group;

[0046] Finally, according to the results of the matching degree evaluation, select one or more appropriate members of the observation group to track and handle the problem.

[0047] Furthermore, the method for intelligently matching problems with commonalities with the tags of the members of the observation group further includes:

[0048] Using text matching technology to match and analyze the problems feedback by users with the tags of the members of the observation group. After obtaining the preliminary matching results, conduct a correlation evaluation, accuracy verification, and optimization algorithm on the matching results;

[0049] Correlation evaluation: Comprehensively consider factors such as the experience of the matched members of the observation group in this field, published papers or research results, and evaluate the correlation between the matched members of the observation group and the problem;

[0050] Accuracy verification: Verify the matching results through manual verification or machine learning algorithms to ensure the accuracy of the matching;

[0051] Optimization algorithm: According to the feedback in actual applications, continuously adjust the member tag information and keyword information library to improve the matching accuracy and efficiency.

[0052] Furthermore, the method for converting the online comments after the problems with commonalities are solved into quantifiable satisfaction includes:

[0053] Collect online comments from the feedback platform and preprocess the data;

[0054] According to the preprocessed data, the model for calculating satisfaction is as follows:

[0055] Emotional score assignment: Conduct emotion recognition on the comment content, use sentiment analysis algorithms to identify the emotional tendency in the comments, classify the comments as positive, negative or neutral, positive comments get higher scores, negative comments are deducted points, and neutral comments get no points;

[0056] Degree of detail of comments: Count the number of characters in the comment content, set different length intervals, and each interval corresponds to a different score. Shorter comments receive lower scores, while longer and more detailed comments receive higher scores;

[0057] Keywords and topics mentioned: Through keyword extraction technology, identify relevant keywords and topics mentioned in the comments, and score them according to the positive and negative attributes and importance of the keywords;

[0058] Total satisfaction score = (Positive and negative dimension score * 0.5) + (Degree of detail of comment score * 0.3) + (Keywords and topics score * 0.2).

[0059] Beneficial effects: The data processing method applied to the feedback platform provided by this application has achieved remarkable results in solving the processing efficiency and quality of the problems feedback by the masses. Through big data technology, this solution enables us to conduct in-depth analysis, quickly locate, and professionally track the feedback problems. It not only overcomes the technical problems of low processing efficiency and lack of pertinence of traditional methods but also greatly improves the efficiency and accuracy of problem processing. At the same time, by constructing the labels of the observation group and applying the intelligent matching algorithm, the automatic docking of problems with industry experts is realized. This innovative method not only quickly combines professional knowledge with practical problems but also significantly improves the scientificity and accuracy of problem-solving. Therefore, the data processing method applied to the feedback platform of this application has shown excellent results in processing the problems feedback by the masses and has made important contributions to improving the quality and efficiency of public services. Description of the Drawings

[0060] Figure 1 is a schematic diagram of a data processing method applied to a feedback platform of the present invention; Detailed Embodiments

[0061] To make the technical solutions of the present invention clearer, the following further describes the present invention in detail with reference to the accompanying drawings and specific embodiments.

[0062] As Figure 1 shown, it is a data processing method applied to a feedback platform of this solution, including the following method steps:

[0063] Step 1: Extract the key content of the problem information feedback by the user, and perform weighted algorithm processing on the extracted information to classify the common problems;

[0064] Step 2: Define labels for the members of the observation group;

[0065] Step 3: Intelligently match the common problems with the labels of the members of the observation group, and have the matched observation group members reply and solve the problems;

[0066] Step 4: Convert the online reviews after solving the common problems into quantifiable satisfaction.

[0067] In step 1 of the above method, the specific method for extracting key content from the problem information feedback by users is as follows:

[0068] First, establish a database for the feedback platform. The database collects the feedback problem information of users, including: picture information and text information. Then, according to the above picture information and text information, obtain a list of key information. Here, the way to obtain the list of key information can be through a third-party capability interface and a media AI model for key information extraction. Next, purify the key information in the above list of key information to obtain the keyword information of the problem information feedback by each user, and define its part of speech to form a keyword information library. That is to say, the keyword information library includes the keyword information extracted and defined from the problems feedback by multiple users.

[0069] Among them, the keyword information of the problem information feedback by each user generates key labels of people, things, places, objects, and organizations for the management personnel to quickly understand and decide whether to adopt the problem feedback by the user. Through the screening of key labels, the corresponding problems that need to be adopted and solved can be quickly and accurately filtered out. Because different management departments have corresponding social problems to solve, in this way, the problems corresponding to the processing fields of the management departments can be quickly and effectively filtered out.

[0070] As a further method, after constructing the keyword information library, the method for extracting key content from the problem information feedback by users also includes: establishing two-level theme libraries of departments and problems. After establishing the department theme library and the problem theme library, in the early stage of using the data processing method applied to the feedback platform, input the corresponding information into the corresponding theme library for classification through the method of user filling and manual correction (data accumulation in the early stage). In the later stage of use, the platform applied to the feedback forms an underlying word library by using the data accumulation input in the early stage. Different theme libraries correspond to different keyword information libraries, that is, the department theme library corresponds to the keyword information theme library related to the department management field, and the problem theme library corresponds to the keyword information library extracted and defined from the problems feedback by users. In this way, the platform applied to the feedback can automatically classify the content of users' questions and exposures, that is, when the feedback problem is proposed, it is directly classified into the corresponding department theme library and the corresponding problem theme library, quickly locking the management department and the problem direction, with high efficiency, accurate classification, and being convenient for accurate solution in the later stage and providing accurate solutions. Such a classification method is continuously optimized and adjusted according to the information changes of the department theme library, the problem theme library, and the keyword information library in the actual use process.

[0071] In step 1 of the above method, when processing the extracted information with a weighting algorithm, the specific methods for classifying common problems include:

[0072] Comprehensively considering multiple dimensions such as the number of user feedback problems, page views, comments, and likes, calculate a popularity score for each keyword. The specific formula is as follows:

[0073] Popularity score = (the number of problems corresponding to the keyword / the number of problems corresponding to the highest keyword in the current period) * 0.6 + (the page views of the corresponding problems / the page views of the highest corresponding problems) * 0.2 + (the number of comments on the corresponding problems / the number of comments on the highest problems) * 0.15 + (the number of likes on the corresponding problems / the number of likes on the highest problems) * 0.05

[0074] Select the mainstream common problems based on the above popularity scores. That is, sort the problems to be solved in the feedback according to the popularity scores. The higher the popularity score of a problem, the higher its social impact, and it needs to be solved urgently. This can optimize the solution strength for problems with greater social impact in user feedback, and the social stability attribute is higher.

[0075] The methods for defining labels for the members of the observation group in step 2 above (the members of the observation group refer to those who can propose professional solutions to corresponding problems on this platform, and the observation group includes professionals in multiple management fields) include:

[0076] Data collection:

[0077] Collect the basic information, professional background, hobbies, and relevant experience of the members of the observation group. Among them, the basic information includes: gender, age, permanent residence area; the professional background includes: education level, major, and main research direction; the hobbies include: hobby type, obtained certificates, competition projects; the relevant experience includes: participated projects, published papers.

[0078] Label definition:

[0079] Based on the above basic information of the members, construct personal portrait labels. For example, a certain member constructs personal portrait labels of "male", "30 - 35 years old", and "East China region" based on the basic information.

[0080] Based on the above professional background, hobbies, and relevant experience of the members, construct industry expertise labels. For example, by extracting and classifying the data information of a certain member's professional background, hobbies, and relevant experience, summarize the industry expertise information words that can reflect the member's professional ability and interests, and form industry expertise labels based on the industry expertise information words.

[0081] Label verification and optimization:

[0082] After defining the personal portrait tags and industry expertise tags, verify and optimize the personal portrait tags and industry expertise tags of the members. Specifically, the personal portrait tags of the members can be verified and optimized by communicating and confirming with the members themselves, and the industry expertise tags of the members can be verified and optimized by comparing and verifying with the information of other team members. If it is found that the tags are inaccurate or need to be adjusted, the platform will optimize and update them in a timely manner.

[0083] In step 3 of the above method, the specific method of intelligently matching the common problems with the tags of the members of the observation group is as follows:

[0084] Using text matching technology, match and analyze the problems feedback by the users with the tags of the members of the observation group. The specific matching methods include:

[0085] Industry mapping matching: According to the problem classification, determine the industry or field to which it belongs, and search for the tags related to this industry or field in the tags of the members of the observation group, so as to screen out the members with relevant industry backgrounds or professional knowledge;

[0086] Interest mapping matching: Use the keywords in the problem to match other tags such as the hobbies and professional certificates of the members of the observation group;

[0087] Finally, according to the results of the matching degree evaluation, select one or more suitable members of the observation group to track and handle the problems.

[0088] Step 3 of the above solution can accurately and quickly match the problems with the members of the observation group with professional problem-solving abilities through the above industry mapping matching and interest mapping matching, so that the problems raised by the users can be scientifically solved, improving the strength and accuracy of solving user problems and meeting social needs.

[0089] Furthermore, the specific method of intelligently matching the common problems with the tags of the members of the observation group also includes:

[0090] Using text matching technology, match and analyze the problems feedback by the users with the tags of the members of the observation group. After obtaining the preliminary matching results, conduct a correlation evaluation, accuracy verification and optimization algorithm on the matching results, as follows;

[0091] Correlation evaluation: Comprehensively consider factors such as the experience of the matched members of the observation group in this field, published papers or research results, etc., and evaluate the correlation between the matched members of the observation group and the problems;

[0092] Accuracy verification: Verify the matching results through manual verification or machine learning algorithms to ensure the accuracy of the matching;

[0093] Optimization algorithm: According to the feedback in actual applications, continuously adjust the member label information and keyword information database to improve the accuracy and efficiency of matching.

[0094] In step 4 of the above method, the specific method of converting the network comments after solving the common problems into quantifiable satisfaction includes:

[0095] Collect network comments from the feedback platform and preprocess the data. The preprocessing methods here include: removing irrelevant characters, punctuation marks, special symbols, etc., performing word segmentation, removing stop words, etc.

[0096] According to the preprocessed data above, the model for calculating satisfaction is as follows:

[0097] Emotional score assignment: Identify the emotion of the comment content, use sentiment analysis algorithms to identify the sentiment tendency in the comment, classify the comment as positive, negative or neutral. Positive comments get higher scores, negative comments get deducted points, and neutral comments get no points;

[0098] Detail level of the comment: Count the number of words in the comment content, set different length intervals, and each interval corresponds to a different score. Shorter comments get lower scores, while longer and more detailed comments get higher scores;

[0099] Keywords and topics mentioned: Through keyword extraction technology, identify the relevant keywords and topics mentioned in the comment, and score them according to the positive and negative attributes and importance of the keywords;

[0100] Total satisfaction score = (positive and negative dimension score * 0.5) + (comment detail level score * 0.3) + (keywords and topics score * 0.2).

[0101] According to the above satisfaction calculation, the satisfaction of social users with the problem solution can be obtained timely and accurately. Thus, based on this satisfaction, the social feedback of this common problem can be understood, enabling relevant management departments to more accurately understand the social situation and impact related to this problem, and then timely adjust the management methods in the fields of relevant social management departments, play a better social regulation role, and improve the quality of public services.

[0102] In summary, the data processing method applied to the feedback platform provided by this application has achieved remarkable results in solving the processing efficiency and quality of the problems feedback by the masses. Through big data technology, this solution enables us to deeply analyze, quickly locate, and professionally track the feedback problems. It not only overcomes the technical problems of low processing efficiency and weak pertinence of traditional methods but also greatly improves the efficiency and accuracy of problem processing. At the same time, by constructing the tags of the observation group and applying the intelligent matching algorithm, the automatic docking of problems with industry experts is realized. This innovative method not only quickly combines professional knowledge with practical problems but also significantly improves the scientificity and accuracy of problem-solving. Therefore, the data processing method applied to the feedback platform of this application has shown excellent results in processing the problems feedback by the masses and has made important contributions to improving the quality and efficiency of public services.

[0103] It can be understood that the identification of common problems is based on the heat value of keywords. The calculation of the heat value refers to multiple dimensions such as the number of feedback problems, the number of views, the number of comments, and the number of likes. However, in some cases, for some current sudden hot or urgent events, the problems just released have not been widely viewed, commented, or liked, and the calculated heat value is small and cannot be verified as a common problem, so it cannot be taken seriously. However, the number of these reflected problems is large and generally more important.

[0104] In this application, to solve such problems, as an optional implementation method, the data processing method applied to the feedback platform further includes:

[0105] Process the extracted information to obtain sudden problems, intelligently match the sudden problems with the tags of the members of the observation group, and have the matched members of the observation group reply to and solve the problems, and convert the online comments after the sudden problems are solved into quantifiable satisfaction. Specifically, the processing method of converting the online comments after the sudden problems are solved into quantifiable satisfaction is the same as the aforementioned statistical method of common problems and will not be elaborated here.

[0106] In the implementation method of this application, the specific method of processing the extracted information to obtain sudden problems is:

[0107] Statistically calculate the growth rate of the problems corresponding to each keyword. If the statistically calculated growth rate exceeds the preset rate, then classify the problems corresponding to the keyword as sudden problems.

[0108] Specifically, count the number of questions corresponding to each keyword and the release time of each question, and calculate the time span of the release times of these questions. For example, if the release time of the question closest to the current time is 3:10 on November 10, 2022, and the release time of the question farthest from the current time is 2:10 on November 10, 2022, then this time span is one hour. Then calculate the ratio of the number of questions to the time span, and use it as the growth rate. If the calculated growth rate is too large, it means that a large number of people have concentrated on reflecting this problem in a short period of time and should be taken seriously. In this application, it is selected as a sudden problem for priority processing. The subsequent processing process can refer to the processing method of the aforementioned common problems. Here, the preset rate can be specifically set as needed, and this application does not make a limitation.

[0109] As a preferred implementation manner, after calculating the time span of the release times of these questions, determine whether the time span is greater than a preset minimum span value. If the time span is greater than the preset minimum span value, then further calculate the ratio of the number of questions to the time span, and use it as the growth rate.

[0110] It can be understood that in some extreme cases, the release times of two questions may be very short. According to the above calculation method, even if there are only two questions, a very large growth rate will be calculated. However, the sudden problems that this application actually wants to count refer to the questions that are published by a large number of users in a short period of time. Obviously, only two questions do not meet the expectation. Therefore, this application sets a judgment logic and introduces a minimum span value. It is calculated that the time span must satisfy being greater than this minimum span value before the subsequent growth rate calculation is carried out.

[0111] The above-described embodiments merely represent several implementation manners of the present invention, and their descriptions are relatively specific and detailed, but should not be construed as limiting the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. A data processing method applied to a feedback platform, characterized in that: The following methods are included: Extract key content from user feedback, process the extracted information using a weighted algorithm, and classify common problems; Define labels for members of the observation group; Intelligently match common questions with the tags of members of the observation group, and have the matched members of the observation group answer and solve the questions; Convert online reviews after common problems are solved into quantifiable satisfaction; The method for extracting key content from the problem information fed back by the user includes: Establishing a database for the feedback platform, the database collects user feedback information, including: picture information and text information; Get a list of key information; Purify the key information in the key information list to obtain the keyword information of each user's feedback question information, and define the part of speech for it to form a keyword information database; The method of performing weighted algorithm processing on the extracted information to classify common problems includes: Taking into account the number of user feedback questions, page views, comments, and likes, a popularity score is calculated for each keyword. The specific formula is as follows: Popularity score = (number of questions corresponding to the keyword / number of questions corresponding to the highest keyword in the current period) * 0.6 + (number of views of the corresponding question / highest number of views of the corresponding question) * 0.2 + (number of comments on the corresponding question / highest number of comments on the question) * 0.15 + (number of likes on the corresponding question / highest number of likes on the question) * 0.05, Select mainstream common issues based on their popularity scores.

2. The data processing method applied to the feedback platform according to claim 1, characterized in that: The data processing method applied to the feedback platform also includes: The extracted information is processed to obtain emergent problems; Intelligently match sudden issues with the tags of members of the observation group, and have the matched members of the observation group respond to and resolve the issues; Convert online reviews after urgent issues are resolved into quantifiable satisfaction.

3. The data processing method applied to the feedback platform according to claim 2, characterized in that: The specific method of processing the extracted information to obtain the sudden problem is: The growth rate of the questions corresponding to each keyword is counted. If the counted growth rate exceeds the preset rate, the questions corresponding to the keyword are classified as sudden questions.

4. The data processing method applied to the feedback platform according to claim 3, characterized in that: The specific method for counting the growth rate of questions corresponding to each keyword is: Count the number of questions corresponding to each keyword and the release time of each question, calculate the time span of the release time of these questions, and then calculate the ratio of the number of questions and the time span, and use it as the growth rate.

5. The data processing method applied to the feedback platform according to claim 4, characterized in that: After calculating the time span of the release time of these issues, determine whether the time span is greater than the preset minimum span value. If the time span is greater than the preset minimum span value, further calculate the ratio of the number of issues and the time span and use it as the growth rate.

6. The data processing method applied to the feedback platform according to claim 1, characterized in that: The keyword information of each user's feedback problem information generates key tags of people, things, places, objects, and organizations, so that managers can quickly understand and decide whether to adopt them.

7. The data processing method applied to the feedback platform according to claim 1, characterized in that: After forming the keyword information database, the method of extracting key content from the question information fed back by the user also includes: Establish subject databases at the department and issue levels; In the early stage, the corresponding information is input into the corresponding subject database for classification through user filling and manual correction; In the later stage, by using the accumulated data input in the early stage, the underlying vocabulary library is formed, that is, different subject libraries correspond to different keyword information libraries, so as to realize automatic classification of user questions and exposed content, and continuously optimize and adjust during actual use.

8. The data processing method applied to the feedback platform according to claim 1, characterized in that: The method for defining labels for members of an observation group includes: Data Collection: Collect the basic information, professional background, hobbies and relevant experience of the observation team members. Basic information includes: gender, age, and permanent residence area. Professional background includes: education, major and main research direction. Hobbies include: hobby type, certificates obtained, and competition projects. Relevant experience includes: projects participated in and papers published. Tag definition: Build personal portrait tags based on members’ basic information; Build industry expertise labels based on members’ professional backgrounds, interests, hobbies, and relevant experience; Label verification and optimization: After defining personal portrait tags and industry expertise tags, verify and optimize the personal portrait tags and industry expertise tags of members; By extracting and classifying the data information of the professional background, hobbies and relevant experience of the observation group members, the industry expertise information words that can reflect the professional ability and interests of the members are summarized, and the industry expertise labels are formed based on the industry expertise information words; Verify and optimize the member's industry expertise label by comparing it with the information of other members of the observation group; The method for intelligently matching common questions with labels of members of the observation group includes: Using text matching technology, we match user feedback questions with the tags of observation group members for analysis, including: Industry mapping and matching: According to the problem classification, determine the industry or field to which it belongs, and search for tags related to the industry or field in the tags of the observation group members, so as to screen out members with relevant industry background or expertise; Interest mapping matching: Use the keywords in the question to match the interests, hobbies, professional certificates and other labels of the observation group members; Finally, based on the results of the matching evaluation, select one or more appropriate members of the observation team to follow up and handle the problem.

9. The data processing method applied to the feedback platform according to claim 8, characterized in that: The method for intelligently matching common questions with labels of members of the observation group also includes: Using text matching technology, we match and analyze user feedback questions with the tags of observation team members. After obtaining preliminary matching results, we evaluate the relevance, verify the accuracy and optimize the algorithm. Relevance assessment: The relevance of the matched observation team members to the problem is assessed by comprehensively considering their experience in the field, published papers or research results; Accuracy verification: Verify the matching results through manual verification or machine learning algorithms to ensure the accuracy of the matching; Optimization algorithm: Based on feedback from actual applications, member tag information and keyword information library are continuously adjusted to improve matching accuracy and efficiency.

10. The data processing method applied to the feedback platform according to claim 1, characterized in that: The method of converting online reviews with common problems solved into quantifiable satisfaction includes: Collect online comments from feedback platforms and pre-process the data; According to the preprocessed data, the model for calculating satisfaction is as follows: Sentiment score assignment: sentiment recognition of the review content, using sentiment analysis algorithms to identify the sentiment tendency in the review, and classifying the review as positive, negative or neutral. Positive reviews are scored higher, negative reviews are deducted, and neutral reviews are scored zero. Level of detail of the review: Count the number of words in the review content and set different length intervals. Each interval corresponds to a different score. Shorter reviews have lower scores, while longer and more detailed reviews have higher scores. Mentioned keywords and topics: Using keyword extraction technology, we identify the keywords and topics mentioned in the comments and score them based on their positive and negative attributes and importance. Total satisfaction score = (positive and negative dimension scores*0.5) + (review detail score*0.3) + (keyword and topic score*0.2).

Images