Bid invitation information feedback comparison system based on big data

Abstract

The invention relates to a bid invitation information feedback comparison system based on big data, and relates to the technical field of big data, and the system comprises an information acquisition module, an information processing module, an information extraction module, an information comparison module, an information evaluation module, a ranking calculation module and a decision generation module. The technical key points are as follows: bid invitation and bidding document information is collected, and a document database is constructed; and extracting qualification evaluation feature words by using a natural language processing technology, and comparing the qualification evaluation feature words with preset qualification demand information to generate a qualification bid evaluation report. In addition, the method further comprises the steps of evaluating the price rationality of the bidding party quotation information, and generating a price evaluation report according to the price rationality. And finally, calculating the ranking of the bidding parties according to each bid evaluation report, generating decision support information, and marking the bidding party with the top ranking as a recommended bidding party. Through comprehensive qualification and price evaluation, a simple, efficient and practical solution is provided for small and medium-sized enterprises.

Description

Technical Field

[0001] The present invention belongs to the technical field of bidding, and in particular relates to a bidding information feedback comparison system based on big data. Background Art

[0002] Bidding refers to the act of a bidder submitting an offer to the tenderer within the specified period upon the invitation of the tenderer, in accordance with the conditions specified in the tender notice or tender form.

[0003] Currently in the field of bidding, it is usually necessary to check the bidding documents to bid manually, but manual bidding is slow and inefficient, and may also lead to misunderstandings of the contents of the bidding documents, errors in bidding conditions, and performance information. For some small and medium-sized enterprises that lack a dedicated bidding department, there are problems such as heavy workload and low efficiency. Based on this, a system for overall bidding that is suitable for bidding of small and medium-sized enterprises is proposed, which can reduce manual operations, improve efficiency, and intelligently select the best bidding documents. Summary of the invention

[0004] This application provides a bidding information feedback comparison system based on big data that can solve the above technical problems. The solution is as follows:

[0005] In a first aspect, the present application provides a bidding information feedback comparison system based on big data, which is characterized by comprising:

[0006] The information acquisition module 110 is used to acquire the bidding document information and the bid document information corresponding to the bidding information.

[0007] The information processing module 120 is used to classify and integrate the bidding and tendering document information to form a document database.

[0008] The information extraction module 130 is used to obtain qualification evaluation feature words and extract document information related to the qualification evaluation feature words from the document database using natural language processing technology.

[0009] The information comparison module 140 is used to compare the document information related to the qualification evaluation keywords with the preset qualification requirement information, summarize the qualification comparison scores of each bidder, and generate a qualification evaluation report. The preset qualification requirement information includes: enterprise qualification certificate, industry qualification certificate, financial status certificate, credit certificate and quality management system certificate;

[0010] The information evaluation module 150 is used to obtain the quotation information of the bidder using natural language processing technology, and to conduct price rationality evaluation and generate a price rationality evaluation report.

[0011] The ranking calculation module 160 is used to calculate the ranking of each bidder based on each bid evaluation report. The decision generation module 170 is used to summarize the bid evaluation reports for comprehensive calculation and generate decision support information.

[0012] In one embodiment, the information evaluation module is further configured to:

[0013] According to the bidder's quotation information in the document database, the corresponding market price information is obtained.

[0014] Calculate and process the quotation information and the corresponding market price information to generate quotation rationality judgment information. For a quotation, according to the formula Get σ and determine whether Among them, σ represents the standard deviation of the quotation, Xi represents the i-th market price of the quotation, μ represents the average price, and X represents the bid price.

[0015] like The quotation is judged to be reasonable.

[0016] Otherwise, the quotation will be regarded as abnormal and price abnormality information will be generated to instruct the tendering party personnel to review the abnormal price.

[0017] In one embodiment, the information evaluation module is further configured to:

[0018] Use natural language processing technology to obtain the prices provided by the tenderer and the bidder in the database, calculate the price matching degree, and generate a price matching evaluation report. The price matching degree is used to measure the consistency between the expected tender price and the bid quotation, and is calculated as follows:

[0019] Determine the difference between the bid evaluation price and the bid evaluation benchmark price.

[0020] If the bid evaluation price is higher than the bid evaluation benchmark price, the price matching score

[0021] If the bid evaluation price is lower than the bid evaluation benchmark price, the price matching score Among them, F represents the basic score of the evaluation price, B represents the bid price, A represents the bidding benchmark price, E1 represents the deduction value for every percentage point that the evaluation price is higher than the evaluation benchmark price, and E2 represents the deduction value for every percentage point that the evaluation price is lower than the evaluation benchmark price.

[0022] In one embodiment, the information evaluation module is further configured to:

[0023] Use natural language processing technology to obtain the project cycle information provided by the tenderer and the bidder in the database, calculate the matching degree, and generate a project cycle matching evaluation report.

[0024] Among them, the project cycle matching degree is used to measure the consistency between the project cycle expected by the tender and the project cycle expected by the bid. The calculation formula is as follows:

[0025]

[0026] Among them, P2 represents the project cycle matching score, C represents the expected project cycle of the bidding, D represents the expected project cycle of the tender, and K represents the parameters determined by the preset project cycle according to the bidding requirements.

[0027] In one embodiment, the information evaluation module is further configured to:

[0028] Obtain information about the bidder's performance in similar projects, qualifications of personnel to be invested in the project, quality assurance plan and after-sales service plan.

[0029] According to the scoring criteria established by the tenderer, the bidder's performance in similar projects, qualifications of personnel to be invested in the project, quality assurance plan and after-sales service plan are scored, and a delivery quality evaluation report is generated.

[0030] In one embodiment, the ranking of each bidder is calculated based on each bid evaluation report, including:

[0031] Use the following formula to calculate the comprehensive evaluation score:

[0032]

[0033] Among them, T is the comprehensive score, Ni represents the evaluation scores of different aspects, Wi represents the weight of the corresponding evaluation aspect, and n is the total number of items in the evaluation report.

[0034] The ranking of each bidder is calculated based on the comprehensive score of each bidder.

[0035] In one embodiment, the information comparison module is further used to:

[0036] Obtain market information through web crawlers.

[0037] Combine real-time and historical market information to analyze market trends and generate market trend analysis information to instruct tendering personnel to optimize bidding strategies.

[0038] According to the market trend analysis information, key factor information is obtained, and based on the key factor information, the calculation formula of the comprehensive score is updated.

[0039] In one embodiment, the information evaluation module is further configured to:

[0040] Obtain scoring basis information involving technology, business and law, and generate risk analysis information. The risk analysis information is used to instruct the tenderer's personnel to conduct risk analysis, where the scoring basis includes: Technical risk scoring basis: technical defects, risk probability.

[0041] Business risk scoring is based on: contract terms, price fluctuations, and payment methods.

[0042] Legal risk scoring is based on: contract compliance, project violations.

[0043] In one embodiment, the information comparison module is further used to:

[0044] Get the latest information on tender and bidding documents on a regular basis.

[0045] Update existing bidding and tendering document information to form updated bidding and tendering document information.

[0046] Secondly, this application also provides a bidding information feedback comparison method based on big data, including:

[0047] S101. Acquire bidding document information and bid document information corresponding to the bidding information.

[0048] S102: Classify and integrate the bidding and tendering document information to form a document database.

[0049] S103: Acquire qualification assessment feature words, and use natural language processing technology to extract document information related to the qualification assessment feature words from a document database.

[0050] S104. Compare the document information involving the qualification evaluation keywords with the preset qualification requirement information, summarize the qualification comparison scores of each bidder, and generate a qualification evaluation report. The preset qualification requirement information includes: enterprise qualification certificate, industry qualification certificate, financial status certificate, credit certificate and quality management system certificate.

[0051] S105. Use natural language processing technology to obtain the bidder's quotation information, conduct price rationality assessment, and generate a price rationality evaluation report.

[0052] S106. Calculate the ranking of each bidder based on each bid evaluation report.

[0053] S107. Generate decision support information, in which the top-ranked bidders are marked as recommended bidders.

[0054] In a third aspect, a terminal device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the bidding information feedback comparison system based on big data as described above when executing the computer program.

[0055] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method described in any one of claims 1 to 10 when executed by a processor.

[0056] The technical solution of this application significantly improves the efficiency of the bidding process by automatically acquiring and processing bidding and tendering document information. This method realizes the rapid classification and integration of information by constructing a document database, reducing the tediousness of manual operations. The use of natural language processing technology to accurately extract qualification evaluation feature words and compare them with preset qualification requirements effectively improves the accuracy of qualification review. In addition, by conducting price rationality evaluation, the solution can obtain the bidder's quotation information and compare it with market price information to generate quotation rationality judgment information, thereby avoiding price anomalies and providing scientific decision-making support for the tenderer. The calculation of the comprehensive ranking takes into account multiple factors such as qualifications and prices, ensuring the objectivity and fairness of the bidder ranking. Overall, this solution helps small and medium-sized enterprises simplify the bidding process and reduce costs, while improving the quality of decision-making and the success rate of bidding projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A structural diagram of a bidding information feedback comparison system based on big data provided by an embodiment of the present invention;

[0059] Figure 2 A schematic diagram of the structure of an information processing module in a bidding information feedback comparison system based on big data provided by an embodiment of the present invention;

[0060] Figure 3 A flowchart of a bidding information feedback comparison method based on big data is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] The bidding information feedback comparison system based on big data provided in the embodiment of the present application can be applied to an environment where simple and fast bidding is required: the method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. After obtaining the bidding information, the terminal interacts with the server, classifies, integrates and intelligently analyzes the information using the big data analysis technology on the server, automatically generates a bid evaluation report, and displays it to the user through the terminal to assist in decision-making, thereby achieving a simple, fast and efficient bidding process.

[0063] In one embodiment, Figure 1 As shown, a bidding information feedback comparison system based on big data is provided, which includes an information acquisition module, an information processing module, an information extraction module, an information comparison module, an information evaluation module, a ranking calculation module and a decision generation module. The entire collection system uses big data technology to operate, and in the subsequent operation and processing process, data collection and processing can be performed for the required project types:

[0064] The information acquisition module 110 is used to obtain the bidding document information and the bidding document information corresponding to the bidding information. Specifically, the bidding document information refers to all the official documents and materials issued by the bidding party, including but not limited to the bidding announcement, bidding documents, technical specifications, bills of quantities, contract terms, etc. These documents provide the bidders with the specific requirements and conditions of the bidding project. Bidding document information: This refers to all the documents and materials submitted by the bidder according to the requirements of the bidding party, including bids, business and technical proposals, price quotations, enterprise qualification certificates, project implementation plans, etc. These documents demonstrate the bidder's ability to meet the bidding requirements. These documents can be collected from various sources, including scanning and inputting paper documents, crawling data from online resources through web crawler technology, etc.

[0065] The information processing module 120 is used to classify and integrate the bidding and tendering document information to form a document database. Specifically, the classification of bidding and tendering document information can be based on document type (bidding notice, bid, etc.), content (such as technical specifications, price quotations, etc.) or other relevant standards. The purpose of this step is to organize the information into categories that are easy to manage and retrieve. Based on the classification, key information is extracted from the document. This may include text, numbers, dates and other important data. The extracted information needs to be converted into a format that can be processed by a computer, such as a text file, a database entry, etc.

[0066] The information extraction module 130 is used to obtain qualification evaluation feature words and use natural language processing technology to extract document information related to the qualification evaluation feature words from the document database. Among them, the qualification evaluation feature words refer to keywords that can represent or indicate the qualification conditions of the bidder, such as "ISO certification", "industry experience", "technical patents", etc. Natural language processing (NLP) is a branch of artificial intelligence and linguistics, which is dedicated to enabling computers to understand, interpret and generate content in human language.

[0067] The information comparison module 140 is used to compare the document information involving the qualification evaluation keywords with the preset qualification requirement information, summarize the qualification comparison scores of each bidder, and generate a qualification evaluation report. The preset qualification requirement information includes: enterprise qualification certificate, industry qualification certificate, financial status certificate, credibility certificate and quality management system certificate. Among them, the preset qualification requirement information refers to a series of qualification requirements preset by the tenderer according to the project requirements. Compare the qualification document information provided by the bidder with the qualification requirements preset by the tenderer to verify whether the bidder meets these requirements. This step involves a detailed review of the document content to ensure that the qualification certificate provided is authentic, valid and meets the requirements.

[0068] The information evaluation module 150 is used to obtain the bid information of the bidder using natural language processing technology, and to perform price rationality evaluation and generate a price rationality evaluation report. The price rationality evaluation includes comparing the bidder's bid with historical data, market standards or other bidders' bids to evaluate whether the bid falls within a reasonable range.

[0069] The ranking calculation module 160 is used to calculate the ranking of each bidder based on each bid evaluation report, that is, to evaluate and rank all bidders based on a series of objective criteria.

[0070] The decision generation module 170 is used to generate decision support information, in which the top-ranked bidders are marked as recommended bidders. The decision support information includes the comprehensive score, ranking and other relevant evaluation data of each bidder. The top-ranked bidders are specially marked as "recommended bidders" so that decision makers can quickly identify the best bidders, thereby simplifying the decision-making process.

[0071] Natural language processing technology can automatically extract key information from a large number of bidding documents, reduce the time of manual reading and data entry, and significantly improve the efficiency of bidding. Through automated information extraction and comparison, the misreading of the content of the bidding documents and the omission of bidding conditions and performance information are reduced, and the accuracy of the bidding process is improved. Using natural language processing technology and big data analysis, the system can intelligently evaluate and compare the qualifications and quotations of each bidder, select the best bidding document, and solve the problems of low efficiency and strong subjectivity of manual selection. The technical characteristics of this system make the bidding process automated and intelligent, reduce the workload of small and medium-sized enterprises in bidding, especially for small and medium-sized enterprises that lack special bidding departments, and improve work efficiency. The bidding decision model based on big data can provide decision makers with more scientific and accurate decision-making basis, and enhance the decision support ability of bidding. Through these beneficial effects, it can provide a small and medium-sized enterprise with an overall bidding system that reduces manual operation, improves efficiency, and intelligently selects the best bidding documents, effectively solving the technical problems raised in the background technology.

[0072] In one embodiment, the information evaluation module is further configured to:

[0073] According to the bidder's quotation information in the document database, obtain the corresponding market price information;

[0074] Calculate and process the quotation information and the corresponding market price information to generate quotation rationality judgment information. For a quotation, according to the formula Get σ and determine whether Among them, σ represents the standard deviation of the quotation, Xi represents the i-th market price of the quotation, μ represents the average price, and X represents the bid price;

[0075] like The quotation is judged to be reasonable;

[0076] Otherwise, the bid is considered abnormal and price abnormality information is generated to instruct the tenderer to review the abnormal price. If the deviation between the bid price X and the market price average μ is within the standard deviation σ, that is, the bid price is within the reasonable fluctuation range of the market price, then the bid is considered reasonable. If the bid price X exceeds this range, that is, the bid price is significantly higher or lower than the average market price and exceeds the reasonable fluctuation range, then the bid is considered abnormal.

[0077] In one embodiment, the information evaluation module is further configured to:

[0078] Use natural language processing technology to obtain the prices provided by the tenderer and the bidder in the database, calculate the price matching degree, and generate a price matching evaluation report; the price matching degree is used to measure the consistency between the expected tender price and the bid quotation, and is calculated as follows:

[0079] Determine whether the bid evaluation price is higher than the bid evaluation benchmark price;

[0080] If the bid evaluation price is higher than the bid evaluation benchmark price, the price matching score If the bid evaluation price is lower than the bid evaluation benchmark price, the price matching score Among them, F represents the basic score of the evaluation price, B represents the bid price, A represents the bidding benchmark price, E1 represents the deduction value for each percentage point higher than the evaluation benchmark price, and E2 represents the deduction value for each percentage point lower than the evaluation benchmark price. Among them, if the bid price is higher than the bidding benchmark price, the system will calculate the price matching score based on the percentage by which the bid price exceeds the benchmark price. For every percentage point higher than the benchmark price, a certain score E1 will be deducted from the basic score F. If the bid price is lower than the bidding benchmark price, the system will also calculate the price matching score based on the percentage by which the bid price is lower than the benchmark price. For every percentage point lower than the benchmark price, a certain score E2 will be deducted from the basic score F. In this way, the tenderer can quickly identify which bidders' quotations are closest to the expected price and which quotations are too high or too low, thereby assisting the decision-making process.

[0081] In one embodiment, the information evaluation module is further configured to:

[0082] Use natural language processing technology to obtain the project cycle information provided by the tenderer and the bidder in the database, calculate the matching degree, and generate a project cycle matching evaluation report;

[0083] Among them, the project cycle matching degree is used to measure the consistency between the project cycle expected by the tender and the project cycle expected by the bid. The calculation formula is as follows:

[0084]

[0085] Among them, P2 represents the project cycle matching score, C represents the expected project cycle of the tender, D represents the expected project cycle of the bid, and K represents the parameters determined by the preset project cycle according to the tender requirements. Specifically, based on the above calculations, the system will generate a project cycle matching score for each bidder, and summarize these scores in the project cycle matching evaluation report to help the tenderer evaluate whether the bidder's project cycle matches the tenderer's expectations, which is crucial for the project to be completed on time. If the bidder's project cycle is significantly different from the tenderer's expectations, it may mean the risk of project delay.

[0086] In one embodiment, the information evaluation module is further configured to:

[0087] Obtain information on the bidder's performance in similar projects, qualifications of personnel to be invested in the project, quality assurance plan and after-sales service plan;

[0088] According to the scoring criteria set by the tenderer, the tenderer's performance in similar projects, qualifications of personnel to be invested in the project, quality assurance plan and after-sales service plan are scored, and a delivery quality evaluation report is generated;

[0089] In one embodiment, the ranking of each bidder is calculated based on each bid evaluation report, including:

[0090] Use the following formula to calculate the comprehensive evaluation score:

[0091]

[0092] Wherein, T is the comprehensive score, Ni represents the evaluation scores of different aspects, Wi represents the weights of the corresponding evaluation aspects, and n is the total number of items in the evaluation report; the ranking of each bidder is calculated based on the comprehensive scores of each bidder. In this embodiment, the evaluation process first collects information about the bidder's performance in similar projects, personnel qualifications, quality assurance plans, and after-sales service plans through natural language processing technology, and then evaluates this information according to the tenderer's scoring criteria and generates a delivery quality evaluation report. The comprehensive score calculation formula is used to calculate the comprehensive score T of each bidder, taking into account the scores Ni and corresponding weights Wi of different evaluation aspects, as well as the total number of items n in the evaluation report. The ranking of each bidder is determined based on these comprehensive scores to select the most suitable winning bidder. This process ensures that the evaluation is not only based on price and project cycle, but also includes key factors such as project delivery quality, so as to make more comprehensive and objective decisions.

[0093] In one embodiment, the information comparison module is further used to:

[0094] Obtain market information through web crawlers;

[0095] Combine real-time and historical market information to analyze market trends and generate market trend analysis information to instruct tendering personnel to optimize bidding strategies;

[0096] According to the market trend analysis information, key factor information is obtained, and the calculation formula of the comprehensive score is updated based on the key factor information. Specifically, web crawler technology is used to obtain real-time and historical market information from the Internet. This information is used to conduct market trend analysis and generate market trend analysis information to help tenderers optimize bidding strategies based on market trends. Key factor information is extracted from the market trend analysis, and this key factor information is used to update the calculation formula of the comprehensive score to ensure that the bid evaluation report can reflect the latest market conditions and trends. This step makes the bid evaluation process not only based on direct information from the bidders, but also takes into account the impact of the market environment, making it more comprehensive and adaptable to market changes.

[0097] In one embodiment, the information evaluation module is further configured to:

[0098] Obtain scoring basis information involving technology, business and law, and generate risk analysis information. The risk analysis information is used to instruct the tenderer's personnel to conduct risk analysis, among which the scoring basis includes: technical risk scoring basis: technical defects, risk probability; business risk scoring basis: contract terms, price fluctuations, payment methods; legal risk scoring basis: contract compliance, project violations. Specifically, the technical risk scoring basis includes technical defects and risk probability. Technical defects may involve potential problems in the technical solutions proposed by the bidder, and risk probability is an assessment of the possibility of these technical problems. The technical risk scoring basis includes technical defects and risk probability. Technical defects may involve potential problems in the technical solutions proposed by the bidder, and risk probability is an assessment of the possibility of these technical problems. The legal risk scoring basis includes contract compliance and project violations. Contract compliance refers to whether the contract complies with the requirements of relevant laws and regulations, while project violations involve whether the bidder has a record of violating laws and regulations in past projects.

[0099] In one embodiment, the information comparison module is also used to: regularly obtain the latest bidding and tendering document information; update the existing bidding and tendering document information to form updated bidding and tendering document information. Specifically, the system or user regularly (may be daily, weekly or monthly, depending on the needs of the project and industry standards) collects the latest bidding and tendering document information from various sources. This information may include newly released bidding announcements, updated bidding requirements, policy changes, market trends, etc. The channels for collecting information may include official websites, industry databases, news releases, and directly obtained from the tenderer or bidder. Update the existing bidding and tendering document information: After collecting new document information, the existing document information needs to be updated. Including replacing outdated information, adding new content, deleting documents that are no longer applicable, etc. The update process needs to ensure the consistency and accuracy of all document information to avoid information conflicts and misleading. After the update, the latest bidding and tendering document information will be formed. This information will be used in the subsequent bid evaluation process, decision support and project management. As policies and regulations change, timely updating of document information helps to maintain project compliance. The latest document information can provide more accurate data support for the tenderer. Reduce the risk of outdated information by updating it regularly.

[0100] refer to Figure 1 , the information comparison module 140 includes:

[0101] The information updating unit 141 is used to regularly obtain the latest bidding and tendering document information, update the existing bidding and tendering document information, and form updated bidding and tendering document information.

[0102] The market trend analysis unit 142 is used to obtain market information through a web crawler. Combine the real-time and historical market information to perform market trend analysis and generate market trend analysis information to instruct the tendering party personnel to optimize the tendering strategy. According to the market trend analysis information, key factor information is obtained, and according to the key factor information, the calculation formula of the comprehensive score is updated.

[0103] refer to Figure 2 , the information calculation module 150 includes:

[0104] The price rationality calculation unit 151 is used to obtain the corresponding market price information according to the bidder's quotation information in the document database. According to the bidder's quotation information in the document database, the corresponding market price information is obtained. According to the quotation information and the corresponding market price information, calculation processing is performed to generate quotation rationality judgment information.

[0105] The qualification evaluation unit 152 is used to compare the document information involving the qualification evaluation keywords with the preset qualification requirement information, summarize the qualification comparison scores of each bidder, and generate a qualification evaluation report. The preset qualification requirement information includes: enterprise qualification certificate, industry qualification certificate, financial status certificate, credit certificate and quality management system certificate.

[0106] The price matching technology unit 153 is used to use the natural language processing technology to obtain the prices provided by the tenderer and the bidder in the database, perform price matching calculations, and generate the price matching evaluation report.

[0107] The project cycle matching degree calculation unit 154 is used to use the natural language processing technology to obtain the project cycle information provided by the tenderer and the bidder in the database, perform matching degree calculation, and generate a project cycle matching degree evaluation report.

[0108] The quality evaluation calculation unit 155 is used to obtain information about the bidder's performance in similar projects, qualifications of personnel to be invested in the project, quality assurance plan and after-sales service plan. The information about the bidder's performance in similar projects, qualifications of personnel to be invested in the project, quality assurance plan and after-sales service plan is scored according to the scoring criteria established by the tenderer to generate a delivery quality evaluation report.

[0109] The comprehensive score calculation unit 156 is used to calculate the ranking of each bidder according to the comprehensive score of each bidder.

[0110] The risk assessment unit 157 is used to obtain scoring basis information involving technology, business and law, and generate risk analysis information, which is used to instruct the tendering party personnel to perform risk analysis.

[0111] The bidding information feedback comparison system based on big data proposed in this application has achieved the following technical effects and solved the corresponding technical problems: 1. Improve bidding efficiency: The system reduces manual operations through automated information acquisition and processing, and improves the speed and efficiency of bidding. 2. Reduce misreading and omissions: Using natural language processing technology, the system can accurately extract and analyze the content in the bidding documents, reducing misreading and omissions that may occur in manual reading. 3. Intelligent selection of the best bidding documents: The system can automatically compare the bidding documents with the bidding requirements, and intelligently select the bidding documents that best meet the requirements, solving the problem of the lack of a dedicated bidding department for small and medium-sized enterprises. 4. Improve the scientific nature of decision-making: The system provides decision-makers with a basis for decision-making by learning relevant rules and methods, thereby improving the scientific nature of bidding and procurement decisions. 5. Reduce costs and improve efficiency: The system reduces a large amount of repetitive work, such as manual submission, statistics and analysis of procurement requirements, thereby reducing costs and improving efficiency. 6. Improve the level of unstructured data utilization: The system extracts elements from the bidding winning announcement through natural language processing technology to form structured data, thereby improving the level of unstructured data utilization of enterprises. 7. Optimize bidding and procurement strategies: The system integrates massive amounts of internal and external data, optimizes bidding and procurement strategies, and formulates bidding and procurement plans scientifically, reasonably, and accurately. In summary, the system improves the efficiency and accuracy of bidding information processing, reduces risks, and improves regulatory efficiency by integrating advanced technologies such as natural language processing, big data analysis, and artificial intelligence. It is particularly suitable for small and medium-sized enterprises, helping them improve their competitiveness in the bidding field.

[0112] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a power supply safety management method as described above when executing the computer program.

[0113] In an exemplary embodiment, Figure 3 As shown, a bidding information feedback comparison method based on big data is provided, including:

[0114] S101. Acquire bidding document information and bid document information corresponding to the bidding information.

[0115] S102: Classify and integrate the bidding and tendering document information to form a document database.

[0116] S103, obtaining qualification assessment feature words, and using natural language processing technology to extract document information related to the qualification assessment feature words from the document database formed in step S102.

[0117] S104. Compare the document information involving the qualification evaluation keywords with the preset qualification requirement information, summarize the qualification comparison scores of each bidder, and generate a qualification evaluation report. The preset qualification requirement information includes: enterprise qualification certificate, industry qualification certificate, financial status certificate, credit certificate and quality management system certificate.

[0118] S105. Use natural language processing technology to obtain the bidder's quotation information, conduct price rationality assessment, and generate a price rationality evaluation report.

[0119] S106. Calculate the ranking of each bidder based on each bid evaluation report.

[0120] S107. Generate decision support information, in which the top-ranked bidders are marked as recommended bidders.

[0121] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0122] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only schematic, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0123] The above-mentioned embodiments only express several implementation methods of the embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the embodiments of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the embodiments of the present application, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A bidding information feedback comparison system based on big data, characterized in that: include: The information acquisition module 110 is used to acquire the bidding document information and the bidding document information corresponding to the bidding information; The information processing module 120 is used to classify and integrate the bidding and tendering document information to form a document database; The information extraction module 130 is used to obtain qualification evaluation feature words and extract document information related to the qualification evaluation feature words from the document database using natural language processing technology; The information comparison module 140 is used to compare the document information involving the qualification evaluation keywords with the preset qualification requirement information, summarize the qualification comparison scores of each bidder, and generate a qualification evaluation report. The preset qualification requirement information includes: enterprise qualification certificate, industry qualification certificate, financial status certificate, credit certificate and quality management system certificate; The information evaluation module 150 is used to analyze and calculate the data in the document database, generate the bid evaluation report, obtain the bid information of the bidder using natural language processing technology, and perform price rationality evaluation to generate a price rationality evaluation report; A ranking calculation module 160 is used to calculate the ranking of each bidder based on each bid evaluation report; The decision generation module 170 is used to generate decision support information, in which the top-ranked bidders are marked as recommended bidders.

2. The bidding information feedback comparison system based on big data according to claim 1 is characterized in that: The information evaluation module is also used to: According to the bidder's quotation information in the document database, obtain the corresponding market price information; The quotation information and the corresponding market price information are calculated and processed to generate quotation rationality judgment information. For a quotation, according to the formula Get σ and determine whether Among them, σ represents the standard deviation of the quotation, Xi represents the i-th market price of the quotation, μ represents the average price, and X represents the bid price; like The quotation is judged to be reasonable; Otherwise, the quotation will be regarded as abnormal and price abnormality information will be generated to instruct the tendering party personnel to review the abnormal price.

3. The bidding information feedback comparison system based on big data according to claim 1 is characterized in that: The information evaluation module is also used to: The natural language processing technology is used to obtain the prices provided by the tenderer and the bidder in the database, and the price matching degree is calculated to generate the price matching degree evaluation report; wherein the price matching degree is used to measure the consistency between the expected tender price and the bid quotation, and is calculated as follows: Determine whether the bid evaluation price is higher than the bid evaluation benchmark price; If the bid evaluation price is higher than the benchmark price, the price matching score If the bid evaluation price is lower than the bid evaluation benchmark price, the price matching score Among them, F represents the basic score of the evaluation price, B represents the bid price, A represents the bidding benchmark price, E1 represents the deduction value for every percentage point that the evaluation price is higher than the evaluation benchmark price, and E2 represents the deduction value for every percentage point that the evaluation price is lower than the evaluation benchmark price.

4. The bidding information feedback comparison system based on big data according to claim 1 is characterized in that: The information evaluation module is also used to: Using the natural language processing technology to obtain the project cycle information provided by the tenderer and the bidder in the database, and performing matching calculation to generate a project cycle matching evaluation report; The project cycle matching degree is used to measure the consistency between the estimated project cycle of the bidding and the estimated project cycle of the tender, and the calculation formula is as follows: Among them, P2 represents the project cycle matching score, C represents the expected project cycle of the bidding, D represents the expected project cycle of the tender, and K represents the parameters determined by the preset project cycle according to the bidding requirements.

5. The bidding information feedback comparison system based on big data according to claim 1 is characterized in that: The information evaluation module is also used to: Obtain information on the bidder's performance in similar projects, qualifications of personnel to be invested in the project, quality assurance plan and after-sales service plan; According to the scoring criteria established by the tenderer, the bidder's performance in similar projects, qualifications of personnel to be invested in the project, quality assurance plan and after-sales service plan will be scored, and a delivery quality evaluation report will be generated.

6. The bidding information feedback comparison system based on big data according to any one of claims 1 to 5, characterized in that: The information evaluation module is also used to: The comprehensive evaluation score is calculated using the following formula: Among them, T is the comprehensive score, Ni represents the evaluation scores of different aspects, Wi represents the weight of the corresponding evaluation aspect, and n is the total number of items in the evaluation report; The ranking of each bidder is calculated based on the comprehensive scores of each bidder.

7. The bidding information feedback comparison system based on big data according to claim 6 is characterized in that: The information comparison module is also used for: Obtain market information through web crawlers; Combining the real-time and historical market information, market trend analysis is performed to generate market trend analysis information for instructing the tendering party personnel to optimize the tendering strategy; Key factor information is obtained according to the market trend analysis information, and the calculation formula of the comprehensive score is updated according to the key factor information.

8. The bidding information feedback comparison system based on big data according to claim 1 is characterized in that: Comparing the document information involving the qualification evaluation keywords with the preset qualification requirement information, the information evaluation module is further used to: Obtain scoring basis information involving technology, business and law, and generate risk analysis information, wherein the risk analysis information is used to instruct the tenderer's personnel to conduct risk analysis, wherein the scoring basis includes: technical risk scoring basis: technical defects, risk probability; Business risk scoring is based on: contract terms, price fluctuations, payment methods; Legal risk scoring is based on: contract compliance, project violations.

9. The bidding information feedback comparison system based on big data according to claim 1 is characterized in that: The information comparison module is also used for: Regularly obtain the latest bidding and tender document information; Update existing bidding and tendering document information to form updated bidding and tendering document information.

10. The bidding information feedback comparison method based on big data is characterized by: The steps include: S101, obtaining bidding document information and bid document information corresponding to the bidding information; S102, classifying and integrating the bidding and tendering document information to form a document database; S103, obtaining qualification evaluation feature words, and using natural language processing technology to extract document information related to the qualification evaluation feature words from the document database; S104, comparing the document information involving the qualification evaluation keywords with the preset qualification requirement information, summarizing the qualification comparison scores of each bidder, and generating a qualification evaluation report, wherein the preset qualification requirement information includes: enterprise qualification certificate, industry qualification certificate, financial status certificate, credit certificate and quality management system certificate; S105. Use natural language processing technology to obtain the bid information of the bidder, conduct price rationality evaluation, and generate a price rationality evaluation report; S106. Calculate the ranking of each bidder based on each bid evaluation report; S107: Generate decision support information, in which the top-ranked bidders are marked as recommended bidders.

Images