Intelligent auxiliary bid evaluation method based on rule configuration

Abstract

The invention discloses an intelligent auxiliary bid evaluation method through rule configuration. The method comprises the following steps: determining an evaluation standard of a bid evaluation task based on the rule configuration; compiling a bidding file, extracting bidding response content from the bidding file, and converting the bidding response content into structured data through OCP identification; according to a review standard, comparing the bidding response contents converted into the structured data item by item, judging whether to respond or not, and giving a review result; and sending the evaluation result to the bid evaluation expert end, receiving result confirmation information returned by the bid evaluation expert end, and generating bid evaluation information. The review process is more standard, the review result is more correct, and the review efficiency is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of bid evaluation, and in particular to an intelligent auxiliary bid evaluation method configured by rules. Background Art

[0002] In the traditional model, the bid evaluation work is manually compared, analyzed, judged, and quantitatively scored by bid evaluation experts. In this model, the following technical problems exist: Serious conflict between quality and efficiency: With the improvement of the business environment, the number of bidders for a single bidding project has gradually increased in recent years, and projects involving hundreds or thousands of people are common. In a limited time, bid evaluation experts face cumbersome evaluation clauses. It is extremely time-consuming to carefully read each bid document, and a lot of time and energy are spent on qualification confirmation, compliance verification, and quotation analysis, resulting in less time for technical bid evaluation and low evaluation efficiency. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, the purpose of the present invention is to propose an intelligent auxiliary bid evaluation method configured by rules, through intelligent technology, such as OCR, NLP technology, relying on the practical experience accumulated in bid evaluation work for many years, sorting out rules that meet the business needs of bid evaluation, establishing a rule base, and dynamically managing the rule base, and dynamically configuring the evaluation rules according to business changes. With the help of information technology means, the credit part and the business part of the relevant data are extracted from the bid documents submitted by the bidder, and the data is processed and output as computer-recognizable structured data. The structured data of the bid documents are compared and verified with the evaluation criteria in accordance with the rules, so as to complete the evaluation and scoring of the bid documents. The bid evaluation experts do not need to perform manual comparison and scoring, but only need to verify and confirm the computer automatic scoring results. This method can make full use of the characteristics of computer fast calculation speed, accurate calculation, and unified judgment criteria, so as to make the evaluation process more standardized, the evaluation results more correct, and the evaluation efficiency more efficient.

[0004] To achieve the above object, an embodiment of the present invention proposes an intelligent assisted bid evaluation method through rule configuration, comprising: Determine the evaluation criteria for the bid evaluation task based on rule configuration; Prepare bidding documents, extract bidding response content from bidding documents, and convert bidding response content into structured data through OCP recognition; According to the evaluation criteria, the bid response content converted into structured data is compared item by item to determine whether it is responsive and give the evaluation result; The evaluation results are sent to the bid evaluation expert side, and the result confirmation information returned by the bid evaluation expert side is received to generate the bid evaluation information.

[0005] According to some embodiments of the present invention, determining the evaluation criteria of the bid evaluation task based on the rule configuration includes: Define review rule configuration information and build a review rule library; Prepare bidding documents, identify them, and extract the bid evaluation method from them; Determine the evaluation criteria for the bid evaluation task based on the evaluation rule base and the bid evaluation method.

[0006] According to some embodiments of the present invention, preparing a bidding document includes: setting requirements, evaluation steps and scoring mechanism; wherein: The required standards include qualification requirements, credibility requirements and qualifications of key personnel; Qualification requirements include production safety license, business license and professional qualification requirements.

[0007] According to some embodiments of the present invention, preparing a bidding document includes: Prepare the response file directory, export the file template under the corresponding chapter, fill in the file template, import it after preparation, sign and seal the imported file, and generate the response file as the bidding document.

[0008] According to some embodiments of the present invention, the bid response content converted into structured data is compared item by item according to the evaluation criteria to determine whether to respond and give the evaluation result, including: The bid response content converted into structured data will be subject to hardware information review, price revision, preliminary review, business review, technical review, first price scoring, second price scoring and comprehensive scoring in sequence; the review items of the hardware information review include MAC address and IP address.

[0009] According to some embodiments of the present invention, the review result includes: The results of the compliance analysis include inspection of fees, taxes, non-competitive fees, and consistency of lists, which is a consistency check between the bid list and the tender list of each bidding unit; The computational analysis results are used to check the calculation errors of the bid list of each bidding unit; The rationality analysis result is the imbalance analysis of the bidding list of each bidding unit; The result of the similarity analysis is the similarity analysis of the bid lists and quotations of each bidding unit.

[0010] According to some embodiments of the present invention, before generating the bid evaluation information, the method further includes: Summarize the scores of each bidding document in the evaluation results, rank them, and get the first place; Determine the ranking of each bidding document according to the result confirmation information returned by the bid evaluation expert, and obtain the second ranking; The first ranking is compared with the second ranking, and when it is determined that the first ranking is inconsistent with the second ranking, a prompt message of the modification basis is generated.

[0011] According to some embodiments of the present invention, extracting bid response content from a bid document includes: Analyze the bidding document to determine feature information; the feature information includes the extension name, file header feature and file tail feature of the bidding document; calculate a corresponding feature value according to the feature information of the bidding document, compare the feature value with a preset feature value range corresponding to a preset set, determine a corresponding target preset set according to the comparison result, cluster the bidding document to obtain a plurality of classification sets; Perform part-of-speech tagging on any file in the classification set, perform dependency syntactic analysis based on the result of the part-of-speech tagging, obtain a dependency syntactic tree corresponding to the file, and use the root of the dependency syntactic tree as the keyword of the file; determine the corresponding preset domain dictionary based on the keyword; perform dependency syntactic analysis within the domain of the corresponding classification set based on the preset domain dictionary to obtain a first semantic analysis result; Determine a preset latent semantic dictionary associated with the preset domain dictionary, and perform dependency syntactic analysis on the corresponding classification set in the domain according to the preset latent semantic dictionary to obtain a second semantic analysis result; the preset latent semantic dictionary includes a part-of-speech aggregation dictionary and an event recognition dictionary; The bid response content is extracted from the bid document according to the first semantic analysis result and the second semantic analysis result.

[0012] According to some embodiments of the present invention, before preparing the bidding document and extracting the bidding response content from the bidding document, the process further includes: Collect risk information of bidding enterprises and affiliated enterprises in bidding documents, and determine enterprise risk value. When it is determined that the enterprise risk value is greater than the preset risk threshold, generate unqualified enterprise prompt information.

[0013] According to some embodiments of the present invention, extracting bid response content from a bid document according to the first semantic analysis result and the second semantic analysis result includes: According to the first semantic analysis result and the second semantic analysis result, a plurality of semantic information is obtained, and according to the amount of the semantic information, a corresponding analysis function is obtained in a preset quantity-analysis function relationship; Calculate the matching degree of each semantic information with the target semantic information corresponding to the bid response content according to the analysis function; in, is the semantic feature value of the Pth semantic information; is the number of keywords in the Pth semantic information; is the word feature value of the i-th keyword in the P-th semantic information; is the fusion coefficient of each keyword in the Pth semantic information, and its value range is (0,2); in, is the matching degree between the Pth semantic information and the target semantic information corresponding to the bid response content; is the semantic feature value of the target semantic information; is the first coefficient of the analysis function Act, and its value range is (0,1); is the second coefficient of the analysis function Act, which is proportional to the size of the semantic information and has a value range of (0,1), and + =1; is the average value of the semantic feature values ​​of all semantic information; The semantic information with the highest matching degree is determined, and the content corresponding to the semantic information with the highest matching degree is used as the bid response content.

[0014] The present invention proposes an intelligent auxiliary bid evaluation method configured by rules. Through intelligent technologies, such as OCR and NLP technologies, relying on the practical experience accumulated in bid evaluation work for many years, rules that meet the business needs of bid evaluation are sorted out, a rule base is established, and the rule base is dynamically managed, and the evaluation rules are dynamically configured according to business changes. With the help of information technology, the credit part and the business part related data are extracted from the bid documents submitted by the bidders, and the data are processed and output as structured data that can be recognized by the computer. The structured data of the bid documents are compared and verified with the evaluation standards in accordance with the rules, so as to complete the evaluation and scoring of the bid documents. The bid evaluation experts do not need to perform manual comparison and scoring, but only need to verify and confirm the computer automatic scoring results. This method can make full use of the characteristics of computer fast calculation speed, accurate calculation, and unified judgment standards, so that the evaluation process is more standardized, the evaluation results are more correct, and the evaluation efficiency is more efficient.

[0015] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0016] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 is a flow chart of an intelligent assisted bidding evaluation method configured by rules according to an embodiment of the present invention; Figure 2 It is a schematic diagram of an intelligent assisted bid evaluation method configured by rules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0019] like Figure 1-Figure 2 As shown, the embodiment of the present invention proposes an intelligent assisted bid evaluation method through rule configuration, including steps S1-S4: S1. Determine the evaluation criteria for the bid evaluation task based on rule configuration; S2. Prepare bidding documents, extract bidding response content from bidding documents, and convert bidding response content into structured data through OCP recognition; S3. According to the evaluation criteria, the bid response contents converted into structured data are compared one by one to determine whether they are responsive and give the evaluation results; S4. Send the evaluation results to the bid evaluation expert end, receive the result confirmation information returned by the bid evaluation expert end, and generate bid evaluation information.

[0020] The working principle of the above technical solution is: through OCP recognition, the bid response content is converted into structured data, including converting image files and attachments in the bid documents into structured data, which is convenient for computer recognition. The evaluation results are sent to the bid evaluation expert end, and the bid evaluation expert verifies the system's automatic evaluation results. If the result is considered correct, it is confirmed; if the result is considered incorrect, the standard related instructions are corrected. The result confirmation information returned by the bid evaluation expert end is received, and the bid evaluation information is generated.

[0021] Beneficial effects of the above technical solutions: Through intelligent technologies, such as OCR and NLP technologies, relying on the practical experience accumulated over the years in bid evaluation work, we can sort out rules that meet the business needs of bid evaluation, establish a rule base, and dynamically manage the rule base, and dynamically configure the evaluation rules according to business changes. With the help of information technology, extract the credit part and business part related data from the bid documents submitted by the bidders, process the data and output computer-recognizable structured data, follow the rules to compare and verify the structured data of the bid documents with the evaluation standards, so as to complete the evaluation and scoring of the bid documents. The bid evaluation experts do not need to compare and score manually, but only need to verify and confirm the computer automatic scoring results. This method can make full use of the characteristics of computer's fast calculation speed, accurate calculation and unified judgment standards, so as to make the evaluation process more standardized, the evaluation results more correct and the evaluation efficiency more efficient. Unified evaluation standards: adopting intelligent evaluation methods, the computer uses unified standards and rules to automatically identify the evaluation standards and methods in the bidding documents to evaluate each bid document, with consistent standards and rules, and improve the objectivity and fairness of the evaluation results. Efficient review quality: Relying on intelligent technology to analyze and compare various bidding documents, replacing experts to complete repetitive and mechanical work, so that bid evaluation experts can focus on technical bid reviews that better reflect the expert's ability within a limited time, ensuring more sufficient review time and more efficient review quality. Accurate review results: Give full play to the supercomputing capabilities and accuracy of computers, combine with a complete rule system, follow the review standards and requirements, and judge and compare bidding documents faster and more accurately.

[0022] According to some embodiments of the present invention, determining the evaluation criteria of the bid evaluation task based on the rule configuration includes: Define review rule configuration information and build a review rule library; Prepare bidding documents, identify them, and extract the bid evaluation method from them; Determine the evaluation criteria for the bid evaluation task based on the evaluation rule base and the bid evaluation method.

[0023] The working principle and beneficial effects of the above technical solution: Provide rule configuration function, which can configure review rules according to business needs and build a review rule library. Prepare bidding documents, identify and extract the content of the bid evaluation method in the bidding documents, and determine the review criteria for the bid evaluation task based on the review rule library and the content of the bid evaluation method. It is convenient to accurately determine the review criteria for the bid evaluation task.

[0024] According to some embodiments of the present invention, preparing a bidding document includes: setting requirements, evaluation steps and scoring mechanism; wherein: The required standards include qualification requirements, credibility requirements and qualifications of key personnel; Qualification requirements include production safety license, business license and professional qualification requirements; among them, professional qualification requirements include old version / construction / general contracting qualification / general contracting for municipal public works construction / level three and above or new version / construction / professional contracting qualification / professional contracting for lifting equipment installation projects / level B and above.

[0025] In one embodiment, a maximum score is set, the scores of all review processes total 100 points, and the system displays the total score of the current step.

[0026] According to some embodiments of the present invention, preparing a bidding document includes: Prepare the response file directory, export the file template under the corresponding chapter, fill in the file template, import it after preparation, sign and seal the imported file, and generate the response file as the bidding document.

[0027] In one embodiment, the bidder can import other files by "adding chapters".

[0028] According to some embodiments of the present invention, the bid response content converted into structured data is compared item by item according to the evaluation criteria to determine whether to respond and give the evaluation result, including: The bid response content converted into structured data will be subject to hardware information review, price revision, preliminary review, business review, technical review, first price scoring, second price scoring and comprehensive scoring in sequence; the review items of the hardware information review include MAC address and IP address.

[0029] The beneficial effects of the above technical solution are as follows: In the hardware information review phase, the system provides a one-click analysis function to determine whether there is duplication of hardware information, and the judges make a confirmation after checking the analysis results. Determine whether the MAC address and IP address of the enterprise lessee organization are correct.

[0030] According to some embodiments of the present invention, the review result includes: The results of the compliance analysis include inspection of fees, taxes, non-competitive fees, and consistency of lists, which is a consistency check between the bid list and the tender list of each bidding unit; The computational analysis results are used to check the calculation errors of the bid list of each bidding unit; The rationality analysis result is the imbalance analysis of the bidding list of each bidding unit; The result of the similarity analysis is the similarity analysis of the bid lists and quotations of each bidding unit.

[0031] The beneficial effects of the above technical solution are: automatic evaluation of enterprise strength, qualifications and performance, the system provides a one-click evaluation function, and the judges confirm the evaluation results after viewing them. The system calculates the score according to the set price evaluation rules, and the final score is confirmed and submitted by the head of the evaluation team. It is convenient to comprehensively analyze the bid lists of each bidding unit and make comprehensive considerations, so as to improve the fairness and accuracy of the bid evaluation.

[0032] According to some embodiments of the present invention, before generating the bid evaluation information, the method further includes: Summarize the scores of each bidding document in the evaluation results, rank them, and get the first place; Determine the ranking of each bidding document according to the result confirmation information returned by the bid evaluation expert, and obtain the second ranking; The first ranking is compared with the second ranking, and when it is determined that the first ranking is inconsistent with the second ranking, a prompt message of the modification basis is generated.

[0033] The working principle and beneficial effects of the above technical solution: After all the reviews are completed, the system automatically summarizes the scores and ranks them, i.e. the first ranking; the head of the judging panel confirms the final ranking, i.e. the second ranking, based on the opinions of the judging panel. The first ranking is compared with the second ranking, and when it is determined that the first ranking and the second ranking are inconsistent, a prompt message is generated to annotate the basis for modification. Avoid arbitrary interference with the system's bid evaluation results to ensure the fairness and accuracy of the bid evaluation work.

[0034] According to some embodiments of the present invention, extracting bid response content from a bid document includes: Analyze the bidding document to determine feature information; the feature information includes the extension name, file header feature and file tail feature of the bidding document; calculate a corresponding feature value according to the feature information of the bidding document, compare the feature value with a preset feature value range corresponding to a preset set, determine a corresponding target preset set according to the comparison result, cluster the bidding document to obtain a plurality of classification sets; Perform part-of-speech tagging on any file in the classification set, perform dependency syntactic analysis based on the result of the part-of-speech tagging, obtain a dependency syntactic tree corresponding to the file, and use the root of the dependency syntactic tree as the keyword of the file; determine the corresponding preset domain dictionary based on the keyword; perform dependency syntactic analysis within the domain of the corresponding classification set based on the preset domain dictionary to obtain a first semantic analysis result; Determine a preset latent semantic dictionary associated with the preset domain dictionary, and perform dependency syntactic analysis on the corresponding classification set in the domain according to the preset latent semantic dictionary to obtain a second semantic analysis result; the preset latent semantic dictionary includes a part-of-speech aggregation dictionary and an event recognition dictionary; The bid response content is extracted from the bid document according to the first semantic analysis result and the second semantic analysis result.

[0035] Working principle of the above technical solution: In this embodiment, the content of the bidding document is read and analyzed to determine its basic feature information, such as the file extension (such as .docx, .pdf), file header features (such as metadata or header description in a specific format), and file tail features (such as signature, date, etc.). Calculate feature values: Based on the extracted feature information, calculate the corresponding feature values. Set corresponding weights for the extensions, file header features, and file tail features of different bidding documents, and perform weighted calculations based on the weights and the data after numerical processing to calculate the corresponding feature values ​​for subsequent classification or recognition processes. Compare the calculated feature values ​​with the feature value ranges in the preset set to determine the target preset set to which each file belongs. Subsequently, the bidding documents are clustered according to these sets to form several classification sets. Each classification set represents different types of bidding documents or different response contents. The classification and sorting of bidding documents is achieved, which is convenient for improving the recognition efficiency and accuracy of data.

[0036] In this embodiment, text processing is performed on each file in the classification set, and part-of-speech tagging is performed first. Each word or phrase in the text is marked with its corresponding part of speech (such as noun, verb, adjective, etc.), which is the basis for understanding the semantics of the text. Based on the results of the part-of-speech tagging, dependency syntax analysis is performed to generate a dependency syntax tree for each file. The dependency syntax tree shows the dependency relationship between the various components in the sentence, where the root of the tree usually represents the core information or main action of the sentence. The root of the dependency syntax tree is used as the keyword of the file, and the keyword can highly summarize the core content of the file. Based on the keyword query, the preset keyword-preset domain dictionary data table is determined to determine the corresponding preset domain dictionary. The domain dictionary is a collection of commonly used words and expressions in a specific field, which helps to understand the text in the field more accurately. The classification set is subjected to dependency syntax analysis in the field using the preset domain dictionary to obtain the first semantic analysis result. The semantic information of the file in the specific field is further mined, and semantic analysis is performed based on the corresponding domain dictionary, which improves the accuracy of the semantic analysis result.

[0037] In this embodiment, a preset implicit semantic dictionary associated with a preset domain dictionary is determined, and the dictionary includes a part-of-speech aggregation dictionary and an event recognition dictionary. The part-of-speech aggregation dictionary is used to classify similar parts of speech in order to understand the text more abstractly; the event recognition dictionary is used to identify the events described in the text and their related elements. The preset domain dictionary represents a direct semantic analysis dictionary, and the preset implicit semantic dictionary represents an indirect semantic analysis dictionary. The classification set is further subjected to dependency syntactic analysis using the implicit semantic dictionary to obtain a second semantic analysis result. It aims to reveal the implicit semantic information and event structure in the document, and to ensure the improvement of the comprehensiveness and accuracy of the semantic analysis. Combining the first semantic analysis result and the second semantic analysis result, the semantic content in the bidding document can be fully and deeply understood, and the bidding response content can be extracted from the bidding document to facilitate the subsequent review and decision-making process.

[0038] The above technical solution has the beneficial effects of: classifying and arranging the bidding documents to improve the efficiency of document recognition. Determining the field of each classification set, based on the dictionary of the corresponding field, performing semantic analysis in direct and indirect ways to obtain the first semantic analysis result and the second semantic analysis result, thereby facilitating accurate acquisition of the bidding response content.

[0039] According to some embodiments of the present invention, before preparing the bidding document and extracting the bidding response content from the bidding document, the process further includes: Collect risk information of bidding enterprises and affiliated enterprises in bidding documents, and determine enterprise risk value. When it is determined that the enterprise risk value is greater than the preset risk threshold, generate unqualified enterprise prompt information.

[0040] The beneficial effects of the above technical solution are: collecting risk information of bidding enterprises and related enterprises in bidding documents, determining enterprise risk values, and generating unqualified enterprise prompt information when the enterprise risk value is determined to be greater than the preset risk threshold. This facilitates the assessment of the overall risk of enterprises in advance, screens out enterprises that do not meet risk requirements, reduces the number of reviewed enterprises, and increases the review rate.

[0041] According to some embodiments of the present invention, extracting bid response content from a bid document according to the first semantic analysis result and the second semantic analysis result includes: According to the first semantic analysis result and the second semantic analysis result, a plurality of semantic information is obtained, and according to the amount of the semantic information, a corresponding analysis function is obtained in a preset quantity-analysis function relationship; Calculate the matching degree of each semantic information with the target semantic information corresponding to the bid response content according to the analysis function; in, is the semantic feature value of the Pth semantic information; is the number of keywords in the Pth semantic information; is the word feature value of the i-th keyword in the P-th semantic information; is the fusion coefficient of each keyword in the Pth semantic information, and its value range is (0,2); in, is the matching degree between the Pth semantic information and the target semantic information corresponding to the bid response content; is the semantic feature value of the target semantic information; is the first coefficient of the analysis function Act, and its value range is (0,1); is the second coefficient of the analysis function Act, which is proportional to the size of the semantic information and has a value range of (0,1), and + =1; is the average value of the semantic feature values ​​of all semantic information; The semantic information with the highest matching degree is determined, and the content corresponding to the semantic information with the highest matching degree is used as the bid response content.

[0042] The working principle and beneficial effects of the above technical solution are as follows: a plurality of semantic information are obtained according to the first semantic analysis result and the second semantic analysis result, and a corresponding analysis function is obtained in a preset quantity-analysis function relationship according to the number of semantic information; the matching degree between each semantic information and the target semantic information corresponding to the bid response content is calculated according to the analysis function; in the calculation process, the larger the semantic information, the The larger the value, the preset semantic information and the comparison data table of the variable coefficients of the analysis function Act are set. Indicates to expand X by 10 times, for example, X=3, is equal to 0.2, then =15; for example, =1.2, m=2, the word feature values ​​of the i-th keyword in the P-th semantic information are 2 and 1.5 respectively, then the semantic feature value of the P-th semantic information is 4.2. When the number of semantic information is 6, the semantic feature value of the target semantic information is 1.5, the first coefficient of the analysis function Act is 0.6, the second coefficient is 0.4, the average semantic feature value of all semantic information is 3, and the match degree between the P-th semantic information and the target semantic information corresponding to the bid response content is 13.3%. Determine the semantic information with the highest match, and use the content corresponding to the semantic information with the highest match as the bid response content. This facilitates accurate determination of the bid response content.

[0043] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent assisted bidding evaluation method configured by rules, characterized in that: include: Determine the evaluation criteria for the bid evaluation task based on rule configuration; Prepare bidding documents, extract bidding response content from bidding documents, and convert bidding response content into structured data through OCP recognition; According to the evaluation criteria, the bid response content converted into structured data is compared item by item to determine whether it is responsive and give the evaluation result; The evaluation results are sent to the bid evaluation expert side, and the result confirmation information returned by the bid evaluation expert side is received to generate the bid evaluation information.

2. The intelligent assisted bidding evaluation method according to claim 1, characterized in that: The evaluation criteria for the bid evaluation task are determined based on the rule configuration, including: Define review rule configuration information and build a review rule library; Prepare bidding documents, identify them, and extract the bid evaluation method from them; Determine the evaluation criteria for the bid evaluation task based on the evaluation rule base and the bid evaluation method.

3. The intelligent assisted bidding evaluation method according to claim 2, characterized in that: Prepare bidding documents, including: setting requirements, evaluation procedures and scoring mechanism; among which, The required standards include qualification requirements, credibility requirements and qualifications of key personnel; Qualification requirements include production safety license, business license and professional qualification requirements.

4. The intelligent assisted bidding evaluation method according to claim 1, characterized in that: Preparation of bidding documents, including: Prepare the response file directory, export the file template under the corresponding chapter, fill in the file template, import it after preparation, sign and seal the imported file, and generate the response file as the bidding document.

5. The intelligent assisted bidding evaluation method according to claim 1, characterized in that: According to the evaluation criteria, the bid response content converted into structured data is compared item by item to determine whether it is responsive and give the evaluation results, including: The bid response content converted into structured data will be subject to hardware information review, price revision, preliminary review, business review, technical review, first price scoring, second price scoring and comprehensive scoring in sequence; the review items of the hardware information review include MAC address and IP address.

6. The intelligent assisted bidding evaluation method according to claim 1, characterized in that: The review results include: The results of the compliance analysis include inspection of fees, taxes, non-competitive fees, and consistency of lists, which is a consistency check between the bid list and the tender list of each bidding unit; The computational analysis results are used to check the calculation errors of the bid list of each bidding unit; The rationality analysis result is the imbalance analysis of the bidding list of each bidding unit; The result of the similarity analysis is the similarity analysis of the bid lists and quotations of each bidding unit.

7. The intelligent assisted bidding evaluation method according to claim 1, characterized in that: Before generating the bid evaluation information, it also includes: Summarize the scores of each bidding document in the evaluation results, rank them, and get the first place; Determine the ranking of each bidding document according to the result confirmation information returned by the bid evaluation expert, and obtain the second ranking; The first ranking is compared with the second ranking, and when it is determined that the first ranking is inconsistent with the second ranking, a prompt message of the modification basis is generated.

8. The intelligent assisted bidding evaluation method according to claim 1, characterized in that: Extract bid response content from bid documents, including: Analyze the bidding document to determine feature information; the feature information includes the extension name, file header feature and file tail feature of the bidding document; calculate a corresponding feature value according to the feature information of the bidding document, compare the feature value with a preset feature value range corresponding to a preset set, determine a corresponding target preset set according to the comparison result, cluster the bidding document to obtain a plurality of classification sets; Perform part-of-speech tagging on any file in the classification set, perform dependency syntactic analysis based on the result of the part-of-speech tagging, obtain a dependency syntactic tree corresponding to the file, and use the root of the dependency syntactic tree as the keyword of the file; determine the corresponding preset domain dictionary based on the keyword; perform dependency syntactic analysis within the domain of the corresponding classification set based on the preset domain dictionary to obtain a first semantic analysis result; Determine a preset latent semantic dictionary associated with the preset domain dictionary, and perform dependency syntactic analysis on the corresponding classification set in the domain according to the preset latent semantic dictionary to obtain a second semantic analysis result; the preset latent semantic dictionary includes a part-of-speech aggregation dictionary and an event recognition dictionary; The bid response content is extracted from the bid document according to the first semantic analysis result and the second semantic analysis result.

9. The intelligent assisted bidding evaluation method according to claim 1, characterized in that: Before preparing the bidding documents and extracting the bidding response content from the bidding documents, it also includes: Collect risk information of bidding enterprises and affiliated enterprises in bidding documents, and determine enterprise risk value. When it is determined that the enterprise risk value is greater than the preset risk threshold, generate unqualified enterprise prompt information.

10. The intelligent assisted bidding evaluation method according to claim 8, characterized in that: Extracting bid response content from the bid document according to the first semantic analysis result and the second semantic analysis result includes: According to the first semantic analysis result and the second semantic analysis result, a plurality of semantic information is obtained, and according to the amount of the semantic information, a corresponding analysis function is obtained in a preset quantity-analysis function relationship; Calculate the matching degree of each semantic information with the target semantic information corresponding to the bid response content according to the analysis function; in, is the semantic feature value of the Pth semantic information; is the number of keywords in the Pth semantic information; is the word feature value of the i-th keyword in the P-th semantic information; is the fusion coefficient of each keyword in the Pth semantic information, and its value range is (0,2); in, is the matching degree between the Pth semantic information and the target semantic information corresponding to the bid response content; is the semantic feature value of the target semantic information; is the first coefficient of the analysis function Act, and its value range is (0,1); is the second coefficient of the analysis function Act, which is proportional to the size of the semantic information and has a value range of (0,1), and + =1; is the average value of the semantic feature values ​​of all semantic information; The semantic information with the highest matching degree is determined, and the content corresponding to the semantic information with the highest matching degree is used as the bid response content.

Images