Fair competition examination monitoring model based on big data and artificial intelligence technology

Abstract

The invention discloses a fair competition review monitoring model based on big data and artificial intelligence technology, and relates to the technical field of data processing, and the fair competition review monitoring model comprises a data acquisition module, a review rule base module, an intelligent review module and a result display and feedback module. The fair competition review monitoring model disclosed by the invention deeply integrates the characteristics of intelligent data acquisition, real-time accurate monitoring, efficient automatic output and the like, and aims to greatly reduce the workload of manual review, effectively avoid omission and negligence in the fair competition review process, improve the accuracy of a judgment result without being limited by professional knowledge of people, and improve the working efficiency of the fair competition review. Therefore, powerful support is provided for daily operation, the working efficiency and quality can be remarkably improved, and continuous optimization of a fair and competitive environment of the market is promoted.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically to the field of fair competition review monitoring model technology based on big data and artificial intelligence technology. Background Art

[0002] In order to establish and improve the market economy system, give full play to the advantages of market competition, and revitalize the vitality of market entities, market fair competition review business is needed. At present, fair competition review, as a key mechanism for maintaining market economic order, currently relies mainly on manual review process. This process involves experts or professional institutions to conduct in-depth analysis of various policy measures to assess whether they comply with the principle of fair competition. This method has played an important role in ensuring the accuracy of the review, but it has also exposed some limitations.

[0003] Manual review requires meticulous analysis of every policy measure or regulation, resulting in a long review cycle that makes it difficult to keep up with the rapidly changing market. Due to limited human resources, manual review is unable to cope with a large number of review tasks, resulting in low overall review efficiency. Personal subjective judgments that may exist in the manual review process will affect the consistency and fairness of the review results. Manual review requires a large investment in human, material and financial resources.

[0004] With the continuous innovation of information technology, we will take advantage of the opportunity of digital construction to build and develop a fair competition review monitoring model based on big data and artificial intelligence technology for fair competition review business. Summary of the invention

[0005] The purpose of the present invention is to solve the technical problems of long cycle, low efficiency, high cost and poor consistency in manual review in the market fair competition review business. The present invention provides a fair competition review monitoring model based on big data and artificial intelligence technology to improve the accuracy and efficiency of fair competition review. The model can quickly identify possible restrictive competition behaviors through automated analysis of policy measures, providing a scientific basis for decision-making.

[0006] In order to achieve the above-mentioned purpose, the present invention specifically adopts the following technical solutions: The present invention provides a fair competition review monitoring model based on big data and artificial intelligence technology, including: Data collection module, which uses manual upload and / or crawler technology to automatically capture data from official websites, various bulletin boards and other information channels, accurately locates and extracts required text data, and ensures the timeliness and integrity of text data; combines natural language processing technology to conduct in-depth analysis and structured processing of captured text data; The review rule base module collects past fair competition review cases through the data collection module, builds a review rule base based on case learning, conducts cross-case comparative analysis, and extracts common laws and common features (through the analysis of massive cases, extracts keywords with common features in the cases, such as enterprise relocation, financial subsidies, tax incentives, etc., and constructs a keyword knowledge base), and builds a fair competition review rule system; The intelligent review module uses big data analysis and artificial intelligence technology to conduct automated reviews of policy measures to determine whether they restrict competition and give a clear conclusion on whether they comply with the principle of fair competition; And result display and feedback module.

[0007] Specifically, the data collection module comprehensively collects, effectively integrates, and deeply analyzes various types of policy measures, market data, laws and regulations, and other diversified information, providing comprehensive and accurate data support for subsequent policy reviews, market analysis, or legal assessments, thereby ensuring the adequacy and scientific nature of the information in the decision-making process.

[0008] The review rule base module obtains cases from multiple authoritative channels such as the government, legal databases and market regulators to ensure the diversity and comprehensiveness of the case base, covering different industries, policy types and review scenarios. Each case is analyzed in detail to accurately identify the specific content of the policy measures, the review results, the anti-competitive behaviors involved, and the rules and standards followed during the review.

[0009] The intelligent review module can greatly improve review efficiency and ensure that policy measures undergo rigorous and scientific evaluation before they are introduced, thereby effectively maintaining a fair competition environment in the market. The result display and feedback module is designed to present complex review results to users in an intuitive and easy-to-understand manner, ensuring that users can quickly and accurately understand the compliance status of policy measures.

[0010] In the data collection module, you can use the API interface to obtain data, establish cooperative relationships with relevant departments or institutions, and directly obtain data through the API interface. This method usually ensures the accuracy and timeliness of the data, while reducing legal risks in the process of data capture.

[0011] In the result display and feedback module, visualization tools can be applied to intuitively display complex review results. You can consider using visualization tools (such as Tableau, Power BI, etc.) to present data and analysis results. These tools can generate visualization elements such as charts and dashboards to help users quickly understand review results and key information.

[0012] In one embodiment, the data collection module can intelligently identify key information in text data through natural language processing technology, form clear and content-rich data paragraphs, and convert the data paragraphs into a structured format that is easy to understand and analyze.

[0013] Specifically, natural language processing technology can greatly improve the efficiency of data processing and ensure the accuracy and availability of data.

[0014] In one embodiment, the key information includes policy highlights, market data indicators, and legal and regulatory provisions.

[0015] In one embodiment, the professional insights and experience of experts are utilized to ensure the accuracy and depth of the fair competition review rule system.

[0016] Specifically, the professional insights and experience of experts are used to ensure the accuracy and depth of the rule system, covering the key points of currently known important review areas and being highly scalable and flexible to cope with new situations and challenges that may arise in the future.

[0017] In one embodiment, the method for constructing a fair competition review rule system is as follows: S1. Assume that the extracted keywords represent the description of the illegal content, so the keywords are the link between the illegal standards and the illegal content; the extracted keywords are represented by a set of triples (key features, illegal content, illegal standards), one of which (u, i, b) means that the illegal standard u gives the illegal content i a key feature b; So the recommended formula for violation standard u for violation content i is: ; In the formula, is the number of times the violation criteria determines the key feature b, is the number of times the key feature b is extracted from the illegal content; S2. Introduce natural language processing and machine learning algorithms to continuously optimize and improve the fair competition review rules system; S3. By continuously learning and analyzing past review cases and regulatory changes, the fair competition review rules system can intelligently identify and extract more accurate and efficient review rules and standards; S4. Continuously optimizing and training the fair competition review rules system not only improves the efficiency and accuracy of the review work, but also ensures that the fair competition review rules system keeps pace with the times, so that it always keeps pace with the latest regulatory requirements and market trends.

[0018] In one embodiment, the intelligent review module adopts the following processing methods to improve the accuracy and efficiency of the review: A1. Carry out detailed pre-processing operations on policy measures. By constructing a paragraph segmentation method, lengthy and complex text content can be divided into several logically clear and thematic paragraphs to improve the accuracy and efficiency of subsequent text analysis. This step is the basis for subsequent analysis and is crucial to ensuring the quality of the review results.

[0019] A2. Based on the constructed review rule base, key feature information of policy measures is extracted; this feature information covers all aspects of policy measures that may involve restrictions on competition, such as market access conditions, price control mechanisms, subsidy policies, etc.; by accurately extracting these features, the impact of policy measures on market competition can be more comprehensively evaluated.

[0020] A3. Use trained machine learning models (such as decision trees, random forests, neural networks, etc.) to conduct predictive analysis on policy measures. After being trained and verified with a large amount of historical data, they have a high degree of accuracy and stability. They can make intelligent judgments on policy measures based on the extracted feature information and give clear conclusions on whether they comply with the principle of fair competition.

[0021] In one implementation, the result display and feedback module presents complex review results to users in an intuitive and easy-to-understand manner, ensuring that users can quickly and accurately understand the compliance status of policy measures. At the same time, in order to further improve the accuracy and completeness of the review, a user feedback mechanism is provided to allow users to confirm, modify or supplement the review results.

[0022] The beneficial effects of the present invention are as follows: 1. The fair competition review monitoring model based on big data and artificial intelligence technology disclosed in the present invention improves review efficiency: In review work, time is efficiency. This technical solution achieves a comprehensive acceleration of the review work by introducing an automated review process. This process can automatically process large amounts of data and quickly complete review tasks, thereby significantly shortening the review cycle. At the same time, automated review can also reduce human intervention, improve the coherence and consistency of the review process, and make the entire review work faster and more efficient.

[0023] 2. Enhance the accuracy of review: The accuracy and reliability of review results are the lifeline of review work. In order to improve the quality of review, make full use of big data analysis and artificial intelligence technology. These technologies can deeply explore the laws behind the data and accurately identify potential risks and problems, thereby significantly improving the accuracy and reliability of review results. With the support of big data, the review work can have a more comprehensive and in-depth understanding of the actual situation of policies and measures, ensuring the rigor and authority of the review work.

[0024] 3. Reduce costs: In the context of increasingly tight resources, reducing costs is a challenge that review work must face. This technical solution has achieved a significant reduction in administrative costs by reducing the human, material and financial resources required for manual review. The automated review process can automatically process large amounts of data, reducing dependence on manual labor, thereby reducing labor costs. At the same time, due to the accuracy and efficiency of automated review, it also reduces material and financial losses caused by errors and delays.

[0025] 4. Promote policy optimization: The continuous optimization and upgrading of policies is an important driving force for social progress. This technical solution promotes the optimization and improvement of the review rule base by establishing a sound feedback mechanism, continuously collecting and analyzing user feedback. This mechanism can timely discover the deficiencies of policy measures and provide scientific basis and decision-making support for policy makers. By continuously optimizing the review rule base, the compliance and scientific nature of policy measures can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 This is a framework diagram of a fair competition review monitoring model based on big data and artificial intelligence technology in the present invention; Figure 2 It is the control flow chart of the fair competition review monitoring model. DETAILED DESCRIPTION

[0028] In order to make the technical problems, technical solutions and technical effects of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0029] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0030] like Figure 1 to Figure 2As shown, this embodiment provides a fair competition review monitoring model based on big data and artificial intelligence technology, including a data collection module, a review rule base module, an intelligent review module, and a result display and feedback module; The data collection module uses manual upload and / or crawler technology to automatically capture data from official websites, various bulletin boards and other information channels, accurately locates and extracts the required text data, and ensures the timeliness and integrity of the text data; it combines natural language processing technology to deeply analyze and structure the captured text data. The data collection module can intelligently identify key information in the text data through natural language processing technology, form clear and rich data paragraphs, and convert the data paragraphs into a structured format that is easy to understand and analyze. Natural language processing technology can greatly improve the efficiency of data processing and ensure the accuracy and availability of data.

[0031] The review rule base module collects past fair competition review cases through the data collection module, builds a review rule base based on case learning, conducts cross-case comparative analysis, extracts common laws and common features, and builds a set of fair competition review rule systems. It uses the professional insights and experience of experts to ensure the accuracy and depth of the rule system, covers the key points of currently known important review areas, and has high scalability and flexibility to cope with new situations and new challenges that may arise in the future. The construction method of the fair competition review rule system is as follows: S1. Assume that the extracted keywords represent the description of the illegal content, so the keywords are the link between the illegal standards and the illegal content; the extracted keywords are represented by a set of triples (key features, illegal content, illegal standards), one of which (u, i, b) means that the illegal standard u gives the illegal content i a key feature b; So the recommended formula for violation standard u for violation content i is: ; In the formula, is the number of times the violation criteria determines the key feature b, is the number of times the key feature b is extracted from the illegal content; S2. Introduce natural language processing and machine learning algorithms to continuously optimize and improve the fair competition review rules system; S3. By continuously learning and analyzing past review cases and regulatory changes, the fair competition review rules system can intelligently identify and extract more accurate and efficient review rules and standards; S4. Continuously optimizing and training the fair competition review rules system not only improves the efficiency and accuracy of the review work, but also ensures that the fair competition review rules system keeps pace with the times, so that it always keeps pace with the latest regulatory requirements and market trends.

[0032] Natural language processing is closely related to machine learning algorithms, which rely on machine learning algorithms to process and understand human language. Commonly used machine learning algorithms include Naive Bayes, Support Vector Machine (SVM), Decision Tree, Random Forest, and deep learning models such as Recurrent Neural Network (RNN), Long Short-Term Memory Network (LSTM) and Transformer. These algorithms are widely used in tasks such as text classification, sentiment analysis, machine translation, speech recognition, and question-answering systems. In recent years, pre-trained language models such as BERT and GPT have significantly improved the performance of NLP tasks through large-scale data training, becoming the mainstream direction of current research and application.

[0033] The intelligent review module uses big data analysis and artificial intelligence technology to conduct automated reviews of policy measures to determine whether they restrict competition and give a clear conclusion on whether they comply with the principle of fair competition. The intelligent review module adopts the following processing methods to improve the accuracy and efficiency of the review: A1. Carry out detailed pre-processing operations on policy measures. By constructing a paragraph segmentation method, lengthy and complex text content can be divided into several logically clear and thematic paragraphs to improve the accuracy and efficiency of subsequent text analysis. This step is the basis for subsequent analysis and is crucial to ensuring the quality of the review results.

[0034] A2. Based on the constructed review rule base, key feature information of policy measures is extracted; this feature information covers all aspects of policy measures that may involve restrictions on competition, such as market access conditions, price control mechanisms, subsidy policies, etc.; by accurately extracting these features, the impact of policy measures on market competition can be more comprehensively evaluated.

[0035] A3. Use trained machine learning models (such as decision trees, random forests, neural networks, etc.) to conduct predictive analysis on policy measures. After being trained and verified with a large amount of historical data, they have a high degree of accuracy and stability. They can make intelligent judgments on policy measures based on the extracted feature information and give clear conclusions on whether they comply with the principle of fair competition.

[0036] And result display and feedback module.

[0037] Specifically, the data collection module comprehensively collects, effectively integrates, and deeply analyzes various types of policy measures, market data, laws and regulations, and other diversified information, providing comprehensive and accurate data support for subsequent policy reviews, market analysis, or legal assessments, thereby ensuring the adequacy and scientific nature of the information in the decision-making process.

[0038] The review rule base module obtains cases from multiple authoritative channels such as the government, legal databases and market regulators to ensure the diversity and comprehensiveness of the case base, covering different industries, policy types and review scenarios. Each case is analyzed in detail to accurately identify the specific content of the policy measures, the review results, the anti-competitive behaviors involved, and the rules and standards followed during the review.

[0039] The intelligent review module can greatly improve the review efficiency and ensure that policy measures undergo rigorous and scientific evaluation before they are introduced, thereby effectively maintaining a fair competition environment in the market.

[0040] The result display and feedback module is designed to present complex review results to users in an intuitive and easy-to-understand manner, ensuring that users can quickly and accurately understand the compliance status of policy measures.

[0041] In the data collection module, you can use the API interface to obtain data, establish cooperative relationships with relevant departments or institutions, and directly obtain data through the API interface. This method usually ensures the accuracy and timeliness of the data, while reducing legal risks in the process of data capture.

[0042] In the result display and feedback module, visualization tools can be applied to intuitively display complex review results. You can consider using visualization tools (such as Tableau, Power BI, etc.) to present data and analysis results. These tools can generate visualization elements such as charts and dashboards to help users quickly understand review results and key information.

[0043] The result display and feedback module presents complex review results to users in an intuitive and easy-to-understand manner, ensuring that users can quickly and accurately understand the compliance status of policy measures. At the same time, in order to further improve the accuracy and completeness of the review, a user feedback mechanism is provided to allow users to confirm, modify or supplement the review results.

Claims

1. A fair competition review monitoring model based on big data and artificial intelligence technology, characterized in that: include: The data collection module automatically captures data, accurately locates and extracts the required text data, and combines natural language processing technology to perform in-depth analysis and structured processing on the captured text data; The review rule base module collects past fair competition review cases through the data collection module and builds a review rule base based on case learning. The review rule base conducts cross-case comparative analysis, extracts keywords with common characteristics in the cases, and builds a set of fair competition review rule system, as follows: S1. Assume that the extracted keywords represent the description of the illegal content. The extracted keywords are represented by a set of triples (key features, illegal content, illegal standards), where one keyword (u, i, b) indicates that the illegal standard u gives the illegal content i a key feature b; So the recommended formula for violation standard u for violation content i is: ； In the formula, is the number of times the violation criteria determines the key feature b, is the number of times the key feature b is extracted from the illegal content; S2. Introduce natural language processing and machine learning algorithms to continuously optimize and improve the fair competition review rules system; The intelligent review module uses big data analysis and artificial intelligence technology to conduct automated reviews of policy measures to determine whether they restrict competition and give a clear conclusion on whether they comply with the principle of fair competition; And result display and feedback module.

2. According to claim 1, a fair competition review monitoring model based on big data and artificial intelligence technology is characterized in that: The data collection module uses natural language processing technology to intelligently identify key information in text data, form well-organized and content-rich data paragraphs, and convert data paragraphs into a structured format that is easy to understand and analyze.

3. According to claim 2, a fair competition review monitoring model based on big data and artificial intelligence technology is characterized in that: Key information packages include policy highlights, market data indicators, and legal and regulatory provisions.

4. According to claim 1, a fair competition review monitoring model based on big data and artificial intelligence technology is characterized in that: Leverage expert insights and experience to ensure the accuracy and depth of the fair competition review rules system.

5. According to claim 1, a fair competition review monitoring model based on big data and artificial intelligence technology is characterized in that: In step S2, by continuously learning and analyzing past review cases and regulatory changes, the fair competition review rules system can intelligently identify and refine more accurate and efficient review rules and standards.

6. According to claim 1, a fair competition review monitoring model based on big data and artificial intelligence technology is characterized in that: The intelligent review module adopts the following processing methods to improve the accuracy and efficiency of the review: A1. Carry out detailed pre-processing of policy measures, and divide the lengthy and complex text content into several logically clear and thematic paragraphs by constructing paragraph segmentation methods, so as to improve the accuracy and efficiency of subsequent text analysis; A2. Extract key feature information of policy measures based on the constructed review rule base; A3. Use the trained machine learning model to conduct predictive analysis on policy measures. After training and verification with a large amount of historical data, it can make intelligent judgments on policy measures based on the extracted feature information and give a clear conclusion on whether they comply with the principle of fair competition.

7. According to claim 1, a fair competition review monitoring model based on big data and artificial intelligence technology is characterized in that: The result display and feedback module presents complex review results to users, ensuring that users can quickly and accurately understand the compliance status of policy measures; and provides a user feedback mechanism to allow users to confirm, modify or supplement the review results.

Images