Intelligent subjective text analysis system oriented to statistical industry unit investigation and survey

Abstract

The invention relates to the technical field of statistical industry. The system is characterized by comprising a task management module, an intelligent statistical analysis module, a keyword module, a high-frequency word module, a similar word module, a clustering statistical module, a word cloud display module and a text list management module. The invention aims to solve the problem that required data cannot be directly and accurately obtained due to large data volume, different contents and subjective simple answer formats when a statistical industry unit faces a large amount of research text data needing to be reported and reported. Through the big data technology and the artificial intelligence and sentiment analysis technology, the multi-service scene requirement is met, a statistical industry unit is helped to efficiently and accurately obtain needed text data, and the decision-making ability and competitiveness are improved.

Description

Technical Field

[0001] The present invention is an intelligent subjective text analysis system for statistical industry unit surveys. The system is applicable to the statistical industry units involved in this survey, specifically covering industrial units, social science and culture units (social science and culture units), service industry units, and information polling centers, etc. This system aims to efficiently and accurately analyze a large amount of subjective text data, thereby providing strong data support for decision-making. Background Art

[0002] Among the statistical industry units, industrial units, social science and culture units (social science and culture units), service industry units and information polling centers receive a large amount of text data that needs to be reported and has been reported in their daily work. These data are large in volume and have different contents. Among them, there are problems in the form of subjective short-answer questions, which makes traditional statistical analysis methods difficult to apply. For example, in industrial units, the feedback on production conditions reported by the units includes "Recent fluctuations in raw material prices have had a certain impact on production progress. We are working hard to find alternative suppliers." The content is different and subjective; the feedback on cultural activities received by social science and culture units is such as "This event is very meaningful, but the publicity is not strong enough."; Customers of service industry units commented that "the service attitude is good, but the waiting time is too long."; The public opinion survey of the information polling center also has similar subjective short-answer questions, which are difficult to handle by traditional methods. At the same time, in various special surveys, a large amount of unstructured questionnaire text data will also be generated, which also faces the problem of statistical analysis. For example, in the special market research survey, the collected questionnaire text data of consumers' evaluation of different products includes subjective descriptive content such as "This product looks beautiful, but it is not very convenient to use." These text data are unstructured and huge in quantity, making it difficult to quickly and accurately extract key information during statistical analysis, such as consumers' overall satisfaction with product appearance and ease of use. In addition, current web search engines are mainly based on keywords, but these keywords usually do not have sentiment analysis functions. For example, when the keyword "mobile phone brand" is entered into a web search engine, the search engine will return web links related to the keyword, but it is impossible to determine whether the sentiment towards different mobile phone brands on these web pages is positive or negative. Therefore, statistical industry units need a technology that can flexibly, efficiently and accurately perform efficient and accurate data analysis on large amounts of subjective text data. Summary of the invention

[0003] The present invention is an intelligent subjective text analysis system for statistical industry unit surveys, which aims to solve the problem that statistical industry units cannot obtain accurate data when facing a large amount of text data that needs to be reported and has been reported in daily work. Specifically, it accurately solves the problem that traditional statistical analysis methods are difficult to apply due to large amounts of data and different contents, and the existence of subjective short-answer questions. It uses the sentiment analysis function to better meet the analysis needs of text data in specific scenarios, and provides efficient and accurate text data analysis solutions for statistical industry units such as industrial units, social science and cultural units, service industry units, and information polling centers.

[0004] In order to achieve the above requirements, the present invention is composed of a task management module, an intelligent statistical analysis module, a keyword module, a high-frequency word module, a similar word module, a clustering statistics module, a word cloud display module and a text list management module.

[0005] The task management module: This module is mainly used to create, manage and assign text analysis tasks, and is customized according to different business scenarios (industry, service industry, social science and culture, information polling center) and needs. Users can enter task names, task descriptions, and set task deadlines to facilitate effective organization and tracking of different types of text analysis tasks. For different business scenarios, personalized task assignments are performed based on regional characteristics, requirements of responsible persons, and differences in survey objects to ensure the pertinence and accuracy of tasks.

[0006] The intelligent statistical analysis module has complex data processing capabilities and can conduct a comprehensive and in-depth analysis of text data. By mining and sorting a large amount of text information, valuable information is extracted and presented to the user in an intuitive way. The module has built-in statistical analysis algorithms, such as natural language processing (NLP), which deeply parses and mines the text to extract key information from the text. The intelligent statistical analysis module uses algorithms to analyze according to the characteristics of the text content to ensure the accuracy and depth of the analysis results. The module contains four submodules. 1. Error correction statistical analysis submodule; 2. Text word count statistical analysis submodule; 3. High-frequency word distribution statistical analysis submodule; 4. Year-on-year-month statistical analysis submodule.

[0007] The high-frequency word module: This module can conduct in-depth analysis of the input text data, automatically identify the words with high frequency and make accurate statistics. At the same time, it will use sentiment analysis technology, which uses built-in algorithms to deeply analyze the text, not only to determine the high-frequency words themselves, but also to judge the sentiment tendency of high-frequency words. It helps statistical industry units to more comprehensively understand the core content and key themes of the text, and provide more accurate support for subsequent analysis and decision-making, including the grasp of the sentiment tendency of the text.

[0008] The keyword module: This module can automatically identify and extract key information from text data, extract keywords, and can also use user-defined keywords and sentiment analysis technology to judge the sentiment tendency of the extracted key information, helping statistical units to quickly grasp the core content of the text. The source of keywords is divided into three parts, and sentiment analysis related technologies are integrated into the process of obtaining keywords from these three sources. The first part is manually added by users from high-frequency words. When the high-frequency word module counts high-frequency words, it uses relevant algorithms to perform preliminary sentiment analysis on the text and judge the sentiment tendency of high-frequency words. When users choose to add keywords, they will refer to the sentiment tendency of high-frequency words to ensure that the added keywords are in line with the overall sentiment context; the second part is manually created by operators in keywords. Operators can create keywords with sentiment tendencies based on their overall sentiment understanding of the text and their familiarity with business scenarios; the third part is manually added by users from similar words. When manually adding keywords from similar words, the similar word module also considers the sentiment tendency of words in the process of identifying similar words.

[0009] The similar word module: This module can automatically identify and extract similar words to keywords in text data, help users expand the scope of keywords, improve the comprehensiveness and accuracy of text analysis, and integrate sentiment analysis technology to quickly judge and grasp the core content of the text. The similar word library is a general word library. When identifying and classifying words with similar meanings, the sentiment tendency of the words will be considered, so that the expanded keyword range is more in line with the actual emotional context of the text, thereby improving the accuracy of text analysis.

[0010] The clustering statistics module: This module can automatically identify and cluster similar text data through internal rules, realize the aggregation of similar text data, facilitate statistical users to analyze and manage by category, discover the connection and influence between clustered data, and improve the depth and accuracy of similar text data analysis. Usually, keyword classification is used to establish the clustering relationship of text data, and similar words are used to expand keyword classification, assist sentiment analysis technology, and help users establish reasonable clustering statistics rules.

[0011] The word cloud display module can help users intuitively understand the high-frequency words in the text by increasing the font size and highlighting the color, so that users can quickly understand the theme and focus of the text.

[0012] The text list management module refers to the result list of valuable information output after the user classifies, screens and analyzes the text data. This module means that the user can carefully classify and accurately screen a large amount of text data to obtain an orderly and structured result list. In this process, the user can group the text data according to different categories, tags or attributes according to their needs and preferences, and further refine these classifications through various screening conditions. In the end, the user will get a clear, concise and easy-to-understand list that contains all the screened and classified text data. This list not only makes it convenient for users to quickly find and browse the required information, but also helps users better manage and use these text data.

[0013] Innovation Applicability to multiple business scenarios: The system covers multiple business scenarios including industry, service industry, social science and culture, and information polling center, and accurately solves the problems faced by units in different fields in market research and user feedback analysis. Whether it is the feedback analysis of product quality and production processes by industrial units, the evaluation of customer satisfaction by the service industry, the grasp of research trends in the social science and culture field, or the collection and interpretation of public opinion by the information polling center, this system can provide targeted solutions. Through in-depth understanding and analysis of different business scenarios, the system can perform personalized task management and text analysis according to the characteristics of each scenario, ensuring accurate analysis results in different fields and adapting to the ever-changing market demands and internal operational needs.

[0014] Sentiment analysis judgment: The intelligent subjective text analysis system of the present invention uses advanced sentiment analysis models to conduct comprehensive and in-depth sentiment analysis of text information from statistical industry units. Through this model, the positive sentiment value, negative sentiment value and neutral sentiment tendency of the text can be accurately returned. This innovative measure provides statistical industry units with extremely valuable analysis results, allowing the units to more accurately understand the emotional attitudes contained in the text, and provide strong data support for subsequent decision-making and work. Compared with traditional analysis methods, the sentiment analysis function of this system is more scientific, accurate, and efficient, and can better meet the analysis needs of statistical industry units when faced with large amounts of complex subjective text data. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is an overall flow chart of an intelligent subjective text analysis system for statistical industry unit surveys according to an embodiment of the present invention; Figure 2 This is a functional module diagram of an intelligent subjective text analysis system for statistical industry unit surveys described in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more clearly understood, the following Figure 1-2 The specific implementation of the present invention is described in detail.

[0017] like Figure 1 As shown, the overall architecture of the system of the present invention is designed in a process-oriented and modular way to ensure that the whole process from data input to output is efficient and orderly. The system first receives raw text data from different business scenarios (such as industry, service industry, social science and culture, information polling center), and these data enter the task management module for task allocation and scheduling after preprocessing. Subsequently, the data flows to the intelligent statistical analysis module, which integrates multiple algorithms to perform in-depth mining and analysis of the text and extract key information. The keyword module, high-frequency word module, and similar word module are used to extract keywords from the text, count high-frequency words, and identify similar words, respectively, to provide a basis for subsequent clustering statistics. The clustering statistics module automatically classifies and aggregates the text according to the extracted feature information to form a valuable analysis report. The word cloud display module presents the analysis results in an intuitive way, which is convenient for decision makers to quickly understand and make judgments. The text list management module is responsible for the storage, retrieval and version control of the text throughout the process to ensure the security and traceability of the data.

[0018] like Figure 2 As shown, the present invention is a functional module diagram of an intelligent subjective text analysis and classification system for group unit business management data, including a task management module, an intelligent statistical analysis module, a keyword module, a high-frequency word module, a similar word module, a clustering statistics module, a word cloud display module and a text list management module.

[0019] In this implementation case, the task management module is placed at the front end of the system as the front end entrance of the system. The task management module is responsible for receiving analysis tasks submitted by users, including task creation, task allocation, progress monitoring and result feedback. This module plans the task execution path through intelligent algorithms, optimizes resource allocation, and ensures that tasks are completed on time. At the same time, it provides a real-time query function for task status, so that users can grasp the progress of tasks at any time.

[0020] The intelligent statistical analysis module is closely connected with the task management module to receive the assigned task data. This module contains four submodules. 1. Error correction statistical analysis submodule: Check and correct the input text data for errors to improve the accuracy of the data. In the industrial field, equipment feedback texts are essential for enterprises to understand the operation of equipment, perform maintenance and improvements. However, these texts are often written by front-line staff and may contain typos and grammatical errors. For example, an equipment maintenance worker in a factory wrote in the feedback: "The coupling of this machine is a bit loose and needs to be tightened." The "coupling" here is a typo of "coupling". If error correction is not performed, it may affect the subsequent statistical analysis results and lead to wrong judgments and decisions. 2. Text word count statistical analysis submodule: Statistical text word count distribution to help units understand the detail and complexity of the text. In the service industry, customer evaluation is crucial to improving service quality. The text word count statistical analysis submodule can effectively analyze the length of the evaluation text, thereby judging the detail of customer feedback. For example, in a customer review of a hotel, "The service is very good and the environment is also good." This review has only ten words, which means that the customer's feedback is relatively concise and may not provide too many specific details. Another review is "The hotel's service is very thoughtful, the staff is warm and friendly, the room is clean and tidy, and the facilities are complete. The breakfast is also rich and tastes good. I hope to stay here again next time." This review has nearly a hundred words, which is obviously more detailed, allowing the hotel to understand the specific feelings of customers in many aspects, which helps the hotel to make targeted improvements and upgrades. 3. High-frequency word distribution statistical analysis submodule: Analyze the high-frequency words and their distribution in the text to provide key information for the unit. In industrial production, equipment failure-related texts are crucial for timely discovery and resolution of problems. The high-frequency word distribution statistical analysis submodule can effectively count the high-frequency words in these texts to quickly locate problems. For example, in a factory's equipment failure report, the words "loud noise", "serious heat" and "strong vibration" appeared. Through the high-frequency word distribution statistical analysis submodule, it can be found that "noise", "heat" and "vibration" are high-frequency words. This indicates that the equipment may have problems with unstable mechanical structure and poor heat dissipation. Based on this key information, the factory can conduct targeted inspections and repairs on the equipment to improve production efficiency. 4. Year-on-year and month-on-month statistical analysis submodule: Perform year-on-year and month-on-month analysis on text data of different periods to help units understand the changing trends of the market and user feedback. For example, in sociological research, compare the text data of research reports on "urbanization process" last year and this year. Through year-on-year analysis, it is found that this year's content on "the role of smart city construction in urbanization" has increased significantly, indicating that the research hotspots in this field are developing in a more specific direction.A further month-on-month analysis shows that compared with the previous quarter, the discussion on the "new trend of rural population migration to cities" has increased, indicating that the research focus has changed in the short term.

[0021] like Figure 2 As shown in the figure, the keyword module, high-frequency word module, and similar word module are connected to the intelligent statistical analysis module to provide keyword information to the intelligent statistical analysis module to help it understand the meaning and theme of the text more accurately. These three modules work together to provide basic data support for the clustering statistics module. The keyword module extracts keywords from the text, the high-frequency word module counts the words that appear more frequently, and the similar word module identifies and classifies words with similar meanings.

[0022] The keyword module: This module can automatically identify and extract key information from text data, extract keywords, and can also use user-defined keywords and sentiment analysis technology to judge the sentiment tendency of the extracted key information, helping statistical units to quickly grasp the core content of the text. In the industrial field, the keyword module extracts key indicators and sentiment tendency keywords for texts on product quality and production efficiency. For the text "This equipment has high precision and greatly improved production efficiency", the keywords "high precision" and "improved production efficiency" are extracted and judged as positive emotions; in the service industry, customer evaluation texts are analyzed to extract keywords for service quality and response speed. "The service of this hotel is very thoughtful and the staff responds very quickly", the keywords "thoughtful service" and "quick response" are extracted and judged as positive emotions; in the field of social sciences and literature, keyword extraction is performed on research papers and reports to help researchers quickly understand the theme and core ideas. In a paper on social development trends, the keywords "sustainable development" and "scientific and technological innovation" are extracted; in the information poll center, keyword analysis is performed on the opinion poll text to understand the hot issues of public concern. In a public opinion poll on urban transportation, the keywords "congestion" and "public transportation" are extracted.

[0023] The high-frequency word module can conduct in-depth analysis of the input text data, automatically identify the words with high frequency and make accurate statistics, and use sentiment analysis technology to deeply analyze the text through the built-in algorithm to determine the sentiment tendency of high-frequency words. In industrial production, the high-frequency word module counts the high-frequency words in the equipment failure report, such as "failure", "maintenance", and "downtime", to help enterprises find the focus of equipment problems in time. When analyzing customer complaint texts in the service industry, the high-frequency word "poor service attitude" is clearly identified as a negative sentiment tendency through sentiment analysis technology; and when analyzing customer praise texts, the high-frequency word "considerate service" is judged as a positive sentiment tendency. In the field of social sciences and literature, the high-frequency words in the texts related to research hotspots, such as "artificial intelligence" and "big data", are counted to provide researchers with references for research directions; in the information poll center, the high-frequency words in the public opinion survey results, such as "environmental protection", "education", and "medical care", reflect the key areas of public concern.

[0024] The similar word module helps users expand the scope of keywords and integrates sentiment analysis technology. The similar word library is a general word library. When identifying and classifying words with similar meanings, the sentiment tendency of the words is considered, so that the expanded keyword range is more in line with the actual sentiment context of the text, thereby improving the accuracy of text analysis. In the industrial field, the similar word module finds similar technical parameter words for product description texts to help companies compare and analyze products. For example, the words "high precision", "high accuracy" and "high resolution" are considered similar words. In the service industry, similar words such as "warm and thoughtful", "friendly and cordial", and "intimate service" all have positive sentiment tendencies. In the field of social sciences and culture, the sentiment tendencies of similar words such as "social fairness" and "social justice" and "social equality" are also consistent. In the information poll center, similar word analysis is performed on the expression of opinions in the poll text to better understand the public's opinion tendencies. For example, the words "support", "agree" and "recognize" have similarities.

[0025] The clustering statistics module can automatically identify and cluster similar text data through internal rules, realize the aggregation of similar text data, facilitate statistical users to analyze and manage by category, discover the connection and influence between clustered data, and improve the depth and accuracy of similar text data analysis. Usually, keyword classification is used to establish the clustering relationship of text data, and similar words are used to expand keyword classification, assist sentiment analysis technology, and help users establish reasonable clustering statistics rules.

[0026] Specifically, based on the data provided by the keyword module, high-frequency word module, and similar word module, clustering algorithms are used to automatically classify and aggregate texts, assist sentiment analysis technology, form text clusters with similar characteristics, provide clustering effect evaluation functions, and help users optimize clustering parameters to obtain better clustering effects. In the industrial field, cluster analysis is performed on equipment failure reports to classify similar failure types into one category to help companies develop targeted maintenance strategies. For example, "motor failure" and "transmission system failure" are classified as mechanical failures. In the service industry, cluster analysis is performed on customer reviews to classify different types of service problems so that companies can improve services in a targeted manner. For example, "poor service attitude", "slow response speed", and "excessive price" are classified as different service problem categories. In the field of social sciences and literature, cluster analysis is performed on research papers to classify related research topics into one category to provide researchers with an overall view of the research field. For example, papers on the application of artificial intelligence in the medical field are classified into one research topic category. In the information polling center, cluster analysis is performed on public opinion survey results to classify similar opinions and views into one category to help governments and companies understand the main demands of the public. For example, opinions on environmental protection and resource utilization are classified as environmental protection demands.

[0027] The word cloud display module intuitively displays the keywords and their importance in the analysis results in the form of a word cloud diagram, usually expressed by font size, to help users quickly understand the text topic. Users can adjust the parameters of the word cloud diagram, such as color and shape, through the interactive interface to better adapt to different display needs. In the industrial field, the word cloud can intuitively display key information on product quality and production efficiency. For example, in the product feedback word cloud of an industrial enterprise, the words "reliable quality" and "stable performance" are highlighted. In the service industry, the word cloud displays the key focus of customer evaluations. For example, in the hotel evaluation word cloud, the words "comfortable", "clean" and "good service" are more eye-catching. In the field of social sciences and literature, the word cloud presents research hotspots and core viewpoints. For example, in a word cloud of sociological research, the words "social change", "cultural differences" and "aging population" are highlighted. In the information poll center, the word cloud reflects the main results of the public opinion survey. For example, in a public opinion survey word cloud on urban development, the words "traffic congestion", "environmental improvement" and "educational resources" became the focus.

[0028] The text list management module is closely connected with the above modules. The results of the above modules provide a key basis for text classification, thereby ensuring the accuracy and rationality of the output text classification. As the background support of the system, the text list management module is responsible for the storage, retrieval and version control of the text throughout the process. This module is connected to each functional module to ensure the real-time synchronization and update of the data list record data. The text list management module adopts an efficient database management system and a strict data access control strategy to ensure the security and integrity of the data. At the same time, it provides a convenient retrieval function to help users quickly locate the required text data.

[0029] In summary, the intelligent subjective text analysis and classification system for statistical industry unit surveys of the present invention can meet the comprehensive needs of applicability in multiple business scenarios. By efficiently and accurately analyzing and processing subjective text data, the system provides valuable information and insights for units, helping them to make better decisions and improve their competitiveness.

[0030] The above contents are merely examples and explanations of the concept of the present invention. Based on the present invention, technicians in the field can make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. An intelligent subjective text analysis system for statistical industry unit surveys, characterized by: It includes task management module, intelligent statistical analysis module, keyword module, high-frequency word module, similar word module, clustering statistics module, word cloud display module and text list management module.

2. According to claim 1, an intelligent subjective text analysis system for statistical industry unit surveys is characterized by: The task management module is mainly responsible for creating, managing and assigning text analysis tasks, customizing them according to different business scenarios and requirements, and creating tasks containing task names, descriptions, deadlines and other information; After receiving the data assigned by the task management module, the intelligent statistical analysis module uses a variety of algorithms and technologies to conduct comprehensive and in-depth mining and analysis of the text data to extract valuable information; The high-frequency word module receives data from the intelligent statistical analysis module, performs a comprehensive and in-depth analysis of the input text data, automatically identifies the words with higher frequency of occurrence and performs accurate statistics, and uses sentiment analysis technology to determine the sentiment tendency of the high-frequency words; The keyword module can automatically identify and extract key information from text data, extract keywords, and can also use user-defined keywords and sentiment analysis technology to judge the sentiment tendency of the extracted key information, helping statistical units to quickly grasp the core content of the text; The similar word module can automatically identify and extract similar words to keywords in text data, helping users expand the scope of keywords and improve the comprehensiveness and accuracy of text analysis. At the same time, it integrates sentiment analysis technology to quickly judge and grasp the core content of the text. The clustering statistics module can automatically identify and cluster similar text data through internal rules, realize the aggregation of similar text data, facilitate statistical users to analyze and manage by category, discover the connection and influence between clustered data, and improve the depth and accuracy of similar text data analysis; The word cloud display module is mainly used to intuitively display the keywords and their importance in the analysis results, and present the text theme and key points through a word cloud diagram; The text list management module is mainly used to manage statistics of users after intelligent classification, screening and analysis of text data, and output a result list containing text analysis. The data is orderly and structured, which is easy to manage and use.

3. The intelligent subjective text analysis system for statistical industry unit survey according to claim 2 is characterized by: The task management module is customized according to different business scenarios (industry, service industry, social science and culture, information polling center, etc.). Users can enter task name, task description, and set task deadlines, etc., to facilitate effective organization and tracking of different types of text analysis tasks. For different business scenarios, personalized task allocation is carried out according to regional characteristics, requirements of responsible persons, and differences in survey objects to ensure the pertinence and accuracy of tasks.

4. The intelligent subjective text analysis system for statistical industry unit survey according to claim 2 is characterized by: The intelligent statistical analysis module has built-in statistical analysis algorithms, such as natural language processing (NLP), which deeply analyzes and mines texts, extracts key information from texts, and ensures the accuracy and depth of analysis results; The intelligent statistical analysis module includes four submodules: an error correction statistical analysis submodule; a text word count statistical analysis submodule; a high-frequency word distribution statistical analysis submodule; and a year-on-year and month-on-month statistical analysis submodule.

5. The intelligent subjective text analysis system for statistical industry unit survey according to claim 2 is characterized by: The high-frequency word module, keyword module, similar word module, and clustering statistics module all use sentiment analysis technology to perform sentiment tendency judgment, including positive and negative sentiment judgment, to improve the accuracy of data analysis technology.

6. The intelligent subjective text analysis system for statistical industry unit survey according to claim 2 is characterized by: The keyword module user-defined keywords mainly come from three parts: the first part is manually added by the user from high-frequency words; the second part is manually created by the operator within the keyword; and the third part is manually added by the user from similar words.

7. The intelligent subjective text analysis system for statistical industry unit survey according to claim 2 is characterized by: The word cloud display module is mainly used to display the keywords and their importance in the analysis results in an intuitive way. The interactive interface in the word cloud display module can adjust the parameters of the word cloud diagram.

8. The intelligent subjective text analysis system for statistical industry unit survey according to claim 2 is characterized by: The text list management module is responsible for the storage, retrieval and version control of the text in the entire text process. This module is connected to each functional module to synchronize and update the data list in real time. The text list management module adopts a database management system and a strict data access control strategy to ensure the security and integrity of the data.

9. The intelligent subjective text analysis system for statistical industry unit survey according to claims 1 and 2 is characterized by: The intelligent statistical analysis module is closely connected with the task management module and receives the assigned task data. The keyword module, high-frequency word module, and similar word module are connected with the intelligent statistical analysis module to provide keyword information for the intelligent statistical analysis module to help it understand the meaning and theme of the text more accurately. Based on the data provided by the keyword module, high-frequency word module, and similar word module, the clustering statistics module uses a clustering algorithm to automatically classify and aggregate texts to form text clusters with similar characteristics. The word cloud display module intuitively displays the keywords and their importance in the analysis results in the form of a word cloud diagram (usually indicated by font size), helping users quickly understand the text theme. The text list management module is closely connected with the above modules and provides the basis for text classification for the above modules.

Images