Intelligent review method, device and computer equipment for bidding documents

Abstract

The application relates to an intelligent review method and device for a bidding document and a computer device. The method comprises the following steps: obtaining a bidding document of each bidding party and bidding review standard information, and identifying objective review standards and subjective review standards of the bidding party based on the bidding review standard information; splitting the bidding document of each bidding party into objective bidding content and subjective bidding content of each bidding party, and generating objective review results of each bidding party through the objective review standards based on the objective bidding content of each bidding party; generating subjective review results of each bidding party through a subjective review analysis model according to the subjective review standards based on the objective review results and the subjective bidding content of each bidding party; and generating bidding review results of each bidding party based on the subjective review results and the objective review results of each bidding party. The method can improve the accuracy of bidding review.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and big data evaluation technology, and in particular to an intelligent evaluation method, apparatus and computer equipment for tender documents. Background Technology

[0002] Since the overall process and review methods of bidding and tendering still mainly rely on manual review, the entire bidding and tendering process and review process are lengthy and have a high degree of deviation, which cannot meet the actual needs of bidding and tendering to the greatest extent. Therefore, how to improve the efficiency of the bidding and tendering process and review process is the current research focus.

[0003] The traditional intelligent processing of the bidding review process involves adding an intelligent review step. For some standardized, simple, and cumbersome judgments, as well as non-subjective review content, an intelligent review model is set up, and then human review is assisted to obtain the review result. However, this review method has a separation, which separates subjective judgment content from non-subjective judgment content, affecting the accuracy and objectivity of subjective judgment, and thus resulting in low accuracy of bidding review. Summary of the Invention

[0004] Therefore, it is necessary to provide an intelligent evaluation method, apparatus, and computer equipment for tender documents to address the aforementioned technical issues.

[0005] Firstly, this application provides an intelligent evaluation method for tender documents, including: Obtain the bid documents of each bidder and the bidding review standard information of the bidding party, and based on the bidding review standard information, identify the objective review standard and the subjective review standard of the bidding party; The bid documents of each bidder are broken down into objective bid content and subjective bid content. Based on the objective bid content, objective review results are generated for each bidder according to the objective review criteria. Based on the objective review results of each bidder and the subjective bidding content of each bidder, and in accordance with the subjective review standards, the subjective review results of each bidder are generated through the subjective review analysis model. Based on the subjective review results of each bidder and the objective review results of each bidder, the bid evaluation results of each bidder are generated.

[0006] Optionally, identifying the bidding party's objective review standards and subjective review standards based on the bidding review standard information includes: The bidding review criteria information is broken down into subjective review content and objective review content, and the bidding requirements information of the bidding party is obtained. Based on the bidding requirements information, a requirements analysis strategy is used to identify the bidding correlation information between the subjective review content and the objective review content; The objective review content will be used as the objective review standard of the bidding party, and the subjective review content and the bidding-related information will be used as the subjective review standard of the bidding party.

[0007] Optionally, the step of splitting the bid documents of each bidder into the objective bid content and the subjective bid content of each bidder includes: For each bid document, based on the bid document, the semantic distribution information of the bid document is identified through a text recognition network; Based on the semantic distribution information, the preset tender document information is queried to identify the first semantic distribution information of subjective content and the second semantic distribution information of objective content. Based on the first semantic distribution information of subjective content and the second semantic distribution information of objective content, the tender document is split into the objective tender content of the bidder and the subjective tender content of the bidder.

[0008] Optionally, the step of generating objective review results for each bidder based on their objective bid content and through the objective review criteria includes: For each bidder, based on the objective bidding content of the bidder, the bidding data of each bidding information type is identified, and based on each objective review standard, the sub-review standards of each bidding information type and the key weight values ​​of each bidding information type are identified; Based on the bidding data of each bidding information type, sub-bid review results of each bidding information type are generated through the sub-review criteria of each bidding information type; Based on the sub-bid review results of each bid information type, an objective review result for the bidder is generated using preset key weight values ​​for each bid information type.

[0009] Optionally, the subjective review analysis model includes a subjective review model and a subjective analysis model. The step of generating subjective review results for each bidder based on their objective review results and subjective bidding content, according to the subjective review standards, through the subjective review analysis model, includes: Based on the bidding association information of each bidder, identify the associated review results in the objective review results of each bidder; Based on the subjective bidding content of each bidder and the associated review results of each bidder, and according to the subjective review content of each bidder, the subjective review model generates sub-subjective review results for each bidder from each subjective review perspective. Based on the sub-subjective review results of each bidder from various subjective review perspectives, the subjective review results of the bidder are generated through the subjective analysis model.

[0010] Optionally, generating the bid review results for each bidder based on their subjective review results and objective review results includes: The subjective review results of each bidder are fed back to the expert client, and the subjective review modification suggestions of each bidder are received from the expert client. Based on the subjective review modification suggestions of each bidder and the sub-subjective review results of each bidder from each subjective review perspective, the subjective analysis model is used to regenerate the new subjective review results of each bidder. The new subjective review results of each bidder and the objective review results of each bidder shall be used as the bid evaluation results of each bidder.

[0011] Secondly, this application also provides an intelligent evaluation device for tender documents, comprising: The acquisition module is used to acquire the bid documents of each bidder and the bidding review standard information of the bidding party, and based on the bidding review standard information, identify the objective review standard and the subjective review standard of the bidding party. The generation module is used to split the bid documents of each bidder into the objective bid content and the subjective bid content of each bidder, and generate the objective review results of each bidder based on the objective bid content and the objective review criteria. The review module is used to generate subjective review results for each bidder based on the objective review results and subjective bidding content of each bidder, according to the subjective review standards and through the subjective review analysis model, and to generate bid evaluation results for each bidder based on the subjective review results and objective review results of each bidder.

[0012] Optionally, the acquisition module is specifically used for: The bidding review criteria information is broken down into subjective review content and objective review content, and the bidding requirements information of the bidding party is obtained. Based on the bidding requirements information, a requirements analysis strategy is used to identify the bidding correlation information between the subjective review content and the objective review content; The objective review content will be used as the objective review standard of the bidding party, and the subjective review content and the bidding-related information will be used as the subjective review standard of the bidding party.

[0013] Optionally, the generation module is specifically used for: For each bid document, based on the bid document, the semantic distribution information of the bid document is identified through a text recognition network; Based on the semantic distribution information, the preset tender document information is queried to identify the first semantic distribution information of subjective content and the second semantic distribution information of objective content. Based on the first semantic distribution information of subjective content and the second semantic distribution information of objective content, the tender document is split into the objective tender content of the bidder and the subjective tender content of the bidder.

[0014] Optionally, the generation module is specifically used for: For each bidder, based on the objective bidding content of the bidder, the bidding data of each bidding information type is identified, and based on each objective review standard, the sub-review standards of each bidding information type and the key weight values ​​of each bidding information type are identified; Based on the bidding data of each bidding information type, sub-bid review results of each bidding information type are generated through the sub-review criteria of each bidding information type; Based on the sub-bid review results of each bid information type, an objective review result for the bidder is generated using preset key weight values ​​for each bid information type.

[0015] Optionally, the audit module is specifically used for: Based on the bidding association information of each bidder, identify the associated review results in the objective review results of each bidder; Based on the subjective bidding content of each bidder and the associated review results of each bidder, and according to the subjective review content of each bidder, the subjective review model generates sub-subjective review results for each bidder from each subjective review perspective. Based on the sub-subjective review results of each bidder from various subjective review perspectives, the subjective review results of the bidder are generated through the subjective analysis model.

[0016] Optionally, the audit module is specifically used for: The subjective review results of each bidder are fed back to the expert client, and the subjective review modification suggestions of each bidder are received from the expert client. Based on the subjective review modification suggestions of each bidder and the sub-subjective review results of each bidder from each subjective review perspective, the subjective analysis model is used to regenerate the new subjective review results of each bidder. The new subjective review results of each bidder and the objective review results of each bidder shall be used as the bid evaluation results of each bidder.

[0017] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0018] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0019] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0020] The aforementioned intelligent review method, apparatus, and computer equipment for bid documents acquire the bid documents of each bidder and the bidding review standards information of the bidding party. Based on the bidding review standards information, it identifies the objective review standards and subjective review standards of the bidding party. It then breaks down each bidder's bid document into objective bid content and subjective bid content. Based on the objective bid content, it generates objective review results for each bidder according to the objective review standards. Based on the objective review results and subjective bid content, it generates subjective review results for each bidder according to the subjective review standards and a subjective review analysis model. Finally, based on the subjective review results and objective review results, it generates bid evaluation results for each bidder. This solution, during subjective analysis, combines the objective review results of bidders with their subjective bid content. Following subjective review standards, the solution utilizes a subjective review analysis model to intelligently generate subjective review results for each bidder. This not only avoids human bias in traditional manual analysis and improves the accuracy of the subjective review in aligning with the tenderer's requirements, but also enhances the efficiency of subjective review, avoiding the high cost and low timeliness of manual review. Furthermore, by constructing a subjective review analysis model, this solution comprehensively reviews each bidder's subjective bid content in conjunction with objective review results, avoiding the one-sidedness and limitations of a single subjective review, thereby effectively improving the accuracy of bidding review. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating an intelligent review method for tender documents in one embodiment; Figure 2 This is a flowchart illustrating an example of intelligent review of tender documents in one embodiment; Figure 3 This is a structural block diagram of an intelligent bid review device in one embodiment. Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0024] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0025] The intelligent review method for bid documents provided in this application embodiment can be applied to a system for intelligent review of bid documents. This system can be used on terminals, including but not limited to various personal computers, laptops, mid-range computers, etc. When performing subjective analysis, the terminal combines the objective review results of the bidders with their subjective bid content, and generates subjective review results for each bidder intelligently according to the subjective review standards and the subjective review analysis model constructed in this solution. This not only avoids the human bias information of traditional manual analysis and improves the accuracy of the subjective review in matching the bidding requirements of the tendering party, but also improves the efficiency of subjective review, avoiding the high cost and low timeliness problems of manual review. Furthermore, by constructing a subjective review analysis model, this solution combines objective review results with a comprehensive review of the subjective bid content of each bidder during subjective review, avoiding the one-sidedness and limitations of a single subjective review, thereby effectively improving the accuracy of bidding review.

[0026] In one exemplary embodiment, such as Figure 1 As shown, an intelligent review method for tender documents is provided. Taking the application of this method to a terminal as an example, the method includes the following steps S101 to S103. Wherein: Step S101: Obtain the bid documents of each bidder and the bidding review standard information of the bidding party, and based on the bidding review standard information, identify the objective review standard and the subjective review standard of the bidding party.

[0027] In this embodiment, the terminal receives files transmitted from the clients of various enterprises, obtains the tender documents of different enterprises, and identifies each enterprise as a bidder. Then, the terminal receives the tender review standard information transmitted from the client of the tendering party. This tender review standard information includes the tendering party's review of objective content and subjective content in the tender documents. Based on the tender review standard information, the terminal identifies the tendering party's objective review standards and subjective review standards. The subjective review standards include subjective review content and correlation review information between the subjective and objective review content. The objective review standards only contain objective review content, and the correlation review information refers to the review content within the objective review content that affects the subjective review content. For example, if the subjective review content concerns the enterprise's production strength, the correlation review content could be information related to the enterprise's current capital, current assets, R&D investment, and number of R&D personnel. If the subjective review content concerns the enterprise's R&D capabilities, the correlation review content could be the number of R&D personnel, R&D investment, R&D equipment costs, and R&D plans.

[0028] Step S102: The bid documents of each bidder are broken down into the objective bid content and the subjective bid content of each bidder. Based on the objective bid content of each bidder, the objective review results of each bidder are generated through objective review standards.

[0029] In this embodiment, the terminal breaks down each bidder's bid documents into objective bid content and subjective bid content. Based on the objective bid content, it generates objective review results for each bidder according to objective review standards. These objective review results include a weighted average of the sub-objective review results for each type of bid information. Each type of bid information represents the review standards used by the tendering party to assess the objective strength of each bidder, such as company costs, investment amount, number of R&D personnel, R&D personnel capabilities, company land area, and factory area.

[0030] Step S103: Based on the objective review results of each bidder and the subjective bidding content of each bidder, according to the subjective review standards, the subjective review results of each bidder are generated through the subjective review analysis model. Based on the subjective review results of each bidder and the objective review results of each bidder, the bid evaluation results of each bidder are generated.

[0031] In this embodiment, the terminal generates subjective review results for each bidder based on the objective review results and subjective bidding content of each bidder, according to subjective review standards and through a subjective review analysis model. Based on these subjective and objective review results, the terminal then generates a bid evaluation result for each bidder. The subjective review analysis model includes a subjective review model and a subjective analysis model. The subjective review model is an AI model based on natural language processing technology, used to combine subjective bidding content and objective review results to comprehensively analyze sub-subjective review results from various subjective review perspectives for each bidder. These subjective review perspectives may include, but are not limited to, enterprise R&D strength, enterprise production strength, enterprise project execution strength, and enterprise security protection capabilities. The bid evaluation result includes the new subjective review results and the objective review results for each bidder. The specific generation process will be explained in detail later.

[0032] Based on the above scheme, during subjective analysis, by combining the objective review results of the bidders with their subjective bid content, and following subjective review standards, the subjective review analysis model constructed in this scheme intelligently generates subjective review results for each bidder. This not only avoids the human bias of traditional manual analysis and improves the accuracy of the subjective review in aligning with the bidding requirements of the tendering party, but also improves the efficiency of subjective review, avoiding the high cost and low timeliness of manual review. Secondly, by constructing a subjective review analysis model, this scheme combines objective review results with a comprehensive review of each bidder's subjective bid content, avoiding the one-sidedness and limitations of a single subjective review, thereby effectively improving the accuracy of bidding review.

[0033] Optionally, based on the bidding review standard information, the objective review standards and subjective review standards of the bidding party are identified, including: breaking down the bidding review standard information into subjective review content and objective review content, and obtaining the bidding party's bidding requirements information; based on the bidding requirements information, identifying the bidding correlation information between the subjective review content and the objective review content through a requirements analysis strategy; using the objective review content as the bidding party's objective review standard, and using the subjective review content and the bidding correlation information as the bidding party's subjective review standard.

[0034] In this embodiment, the terminal breaks down the bidding review standard information into subjective review content and objective review content, and obtains the bidding party's bidding requirements information. This bidding requirements information refers to the project requirements of the bidding party for this bidding project. These requirements include comprehensive requirements regarding the bidder's production, capital, R&D, facilities, personnel, field of expertise, qualifications, awards, and capabilities. These comprehensive requirements can be presented in various formats, such as a paragraph or a table.

[0035] Then, based on the bidding requirements information, the terminal uses a requirements analysis strategy to identify the bidding correlation information between subjective review content and objective review content. This requirements analysis strategy is a semantic recognition network based on a large language model, used to identify the semantic content of the requirements in the bidding requirements information. Based on this semantic content, it queries for target subjective review content related to the semantic content in each subjective review content, and for target objective content related to the semantic content in each objective review content. The target subjective review content, target objective content, and the semantic content are then used as the bidding correlation information between the subjective and objective review content. The objective review content is used as the objective review standard for the bidding party, and the subjective review content and the bidding correlation information are used as the subjective review standard for the bidding party.

[0036] Based on the above scheme, by combining bidding requirement information and comprehensively analyzing the bidding correlation information between subjective review content and objective review content, the matching degree between the identified bidding correlation information and the bidding requirement information is improved.

[0037] Optionally, the bid documents of each bidder are split into objective bid content and subjective bid content of each bidder, including: for each bid document, based on the bid document, identifying the semantic distribution information of the bid document through a text recognition network; based on the semantic distribution information, querying the preset bidding document information, identifying the first semantic distribution information of the subjective content and the second semantic distribution information of the objective content, and based on the first semantic distribution information of the subjective content and the second semantic distribution information of the objective content, splitting the bid document into the objective bid content and the subjective bid content of each bidder.

[0038] In this embodiment, for each bid document, the terminal identifies its semantic distribution information using a text recognition network. This semantic distribution information characterizes the semantic content corresponding to each text position within the bid document. The text recognition network is based on a large language model.

[0039] Then, based on the semantic distribution information, the terminal queries the preset tender document information to identify the first semantic distribution information of the subjective content and the second semantic distribution information of the objective content. The tender document information is preset in the terminal and includes the semantic range corresponding to both the objective and subjective content. Then, based on the semantic distribution information, the terminal identifies the text content location of the semantic content belonging to the semantic range corresponding to the objective content (i.e., the first semantic distribution information) and the text content location of the semantic content belonging to the semantic range corresponding to the subjective content (i.e., the second semantic distribution information).

[0040] Finally, based on the first semantic distribution information of subjective content and the second semantic distribution information of objective content, the terminal splits the bid document into the bidder's objective bid content and the bidder's subjective bid content.

[0041] Based on the above solution, there is no need to objectively or subjectively mark the bidding documents. Instead, the documents are directly identified and intelligently segmented through a text recognition network. This improves the accuracy and efficiency of segmenting subjective and objective bidding content, greatly optimizes the cost of manual marking, and enhances the efficiency of segmentation.

[0042] Optionally, based on the objective bidding content of each bidder, objective review results are generated for each bidder through objective review standards. This includes: for each bidder, identifying bidding data for each type of bidding information based on the objective bidding content, and identifying sub-review standards and key weight values ​​for each type of bidding information based on the objective review standards; generating sub-bid review results for each type of bidding information based on the bidding data of each type of bidding information through the sub-review standards; and generating the objective review results for each bidder based on the sub-bid review results of each type of bidding information through the preset key weight values ​​for each type of bidding information.

[0043] In this embodiment, the terminal identifies bid data for each bidder based on the objective bid content, and identifies sub-review standards and key weight values ​​for each bid information type based on objective review standards. The key weight value is the impact weight of each bid information type on the current bidding project. This impact weight value is preset in the objective review standards.

[0044] Next, based on the bidding data for each bidding information type, the terminal generates sub-bid review results for each bidding information type according to the sub-review criteria for each type. The terminal then weights these sub-bid review results using preset key weight values ​​for each bidding information type to obtain the sub-target bid review results for each type. Finally, the terminal uses the sub-target bid review results for all bidding information types as the objective review results for the bidders. Each sub-review criterion includes review values ​​corresponding to different ranges of bidding data, and the terminal then uses these review values ​​as its own bid review results.

[0045] Based on the above scheme, by reviewing each type of bidding information separately and then weighting them, an objective review result of the bidders is obtained, thereby improving the efficiency and accuracy of the objective review of bidders.

[0046] Optionally, the subjective review analysis model includes a subjective review model and a subjective analysis model. Based on the objective review results and subjective bidding content of each bidder, and in accordance with subjective review standards, the subjective review analysis model generates subjective review results for each bidder. This includes: identifying related review results in the objective review results of each bidder based on the bidding-related information of each bidder; generating sub-subjective review results for each bidder from various subjective review perspectives based on the subjective bidding content and related review results of each bidder, and generating the bidder's subjective review results from various subjective review perspectives using the subjective review model; and generating the bidder's subjective review results from various subjective review perspectives based on the sub-subjective review results of each bidder from various subjective review perspectives using the subjective analysis model.

[0047] In this embodiment, the terminal identifies the associated review results in the objective review results of each bidder based on the bidding association information of each bidder. These associated review results are the sub-target bid review results corresponding to each target objective content and each type of bid information. A correspondence exists between the bid information type and the objective content; this correspondence is stored in the terminal. The terminal identifies the bid information type corresponding to each target objective content by querying this correspondence.

[0048] Then, based on the subjective bidding content of each bidder and the associated review results of each bidder, the terminal generates sub-subjective review results for each bidder from various subjective review perspectives using a subjective review model, according to the subjective review content of each bidder. Next, based on the sub-subjective review results of each bidder from each subjective review perspective, the terminal generates the bidder's subjective review result using a subjective analysis model. Each subjective review perspective represents the direction of subjective review of the subjective bidding content. The sub-subjective review result is the review conclusion for that subjective review perspective, and this conclusion is represented as text content. This subjective review model combines the subjective bidding content and associated review results to intelligently review the subjective bidding content from different subjective review perspectives, thereby obtaining the subjective review result. The subjective analysis model combines the sub-subjective review results from each subjective review perspective to comprehensively analyze the bidder's subjective bidding content, generating more comprehensive subjective evaluation information for the subjective bidding content.

[0049] Based on the above scheme, subjective reviews are conducted from different subjective review perspectives by combining subjective bidding content and related review results. Then, the subjective bidding content is comprehensively analyzed by combining each subjective review perspective, thereby improving the accuracy of the review of subjective bidding content.

[0050] Optionally, based on the subjective review results and objective review results of each bidder, the bid evaluation results of each bidder are generated, including: feeding back the subjective review results of each bidder to the expert client and receiving the subjective review modification suggestions from the expert client; based on the subjective review modification suggestions of each bidder and the sub-subjective review results of each bidder from each subjective review perspective, regenerating the new subjective review results of each bidder through a subjective analysis model; and using the new subjective review results of each bidder and the objective review results of each bidder as the bid evaluation results of each bidder.

[0051] In this embodiment, the terminal feeds back the subjective review results of each bidder to the expert client and receives subjective review modification suggestions from the expert client. These suggestions address shortcomings in the subjective review of the bid content, such as the lack of verification of related company information. Then, based on these suggestions and the sub-subjective review results from each bidder's perspective, the terminal regenerates new subjective review results for each bidder using a subjective analysis model. Since the subjective review model performs reviews from each perspective separately, there is no need to re-perform separate reviews. Instead, the subjective bid content corresponding to the suggested modifications, along with the sub-subjective review results from each perspective, is input into the subjective analysis model before generating the bidder's subjective review results. This improves the efficiency and accuracy of modifying the subjective review results.

[0052] Finally, the terminal will use the new subjective review results of each bidder, as well as the objective review results of each bidder, as the bid evaluation results for each bidder.

[0053] Based on the above scheme, and combined with the modification suggestions from expert feedback, this scheme adjusts and improves the subjective review content, avoiding the bias and localized focus issues of intelligent analysis, thereby further optimizing the accuracy of subjective review.

[0054] This application also provides an example of intelligent evaluation of tender documents, such as... Figure 2 As shown, the specific processing procedure includes the following steps: Step S201: Obtain the bid documents of each bidder and the bidding review standards information of the bidding party.

[0055] Step S202: The bidding review standard information is broken down into subjective review content and objective review content, and the bidding party's bidding requirements information is obtained.

[0056] Step S203: Based on the bidding requirements information, identify the bidding correlation information between subjective review content and objective review content through a requirements analysis strategy.

[0057] Step S204: The objective review content shall be used as the objective review standard of the bidding party, and the subjective review content and bidding-related information shall be used as the subjective review standard of the bidding party.

[0058] Step S205: For each bid document, based on the bid document, the semantic distribution information of the bid document is identified through a text recognition network.

[0059] Step S206: Based on semantic distribution information, query the preset tender document information, identify the first semantic distribution information of subjective content and the second semantic distribution information of objective content, and based on the first semantic distribution information of subjective content and the second semantic distribution information of objective content, split the tender document into the bidder's objective tender content and the bidder's subjective tender content.

[0060] Step S207: For each bidder, based on the objective bidding content of the bidder, identify the bidding data of each bidding information type, and based on each objective review standard, identify the sub-review standard of each bidding information type and the key weight value of each bidding information type.

[0061] Step S208: Based on the bidding data of each bidding information type, generate the sub-bid review results of each bidding information type through the sub-review criteria of each bidding information type.

[0062] Step S209: Based on the sub-bid review results of each bid information type, generate the objective review results of the bidders through the preset key weight values ​​of each bid information type.

[0063] Step S210: Based on the bidding association information of each bidder, identify the associated review results in the objective review results of each bidder.

[0064] Step S211: Based on the subjective bidding content of each bidder and the associated review results of each bidder, and according to the subjective review content of each bidder, the sub-subjective review results of each bidder from each subjective review perspective are generated through the subjective review model.

[0065] Step S212: Based on the sub-subjective review results of each bidder from each subjective review perspective, the subjective review results of the bidder are generated through a subjective analysis model.

[0066] Step S213: Feed back the subjective review results of each bidder to the expert client, and receive the subjective review modification suggestions from each bidder from the expert client.

[0067] Step S214: Based on the subjective review modification suggestions of each bidder and the sub-subjective review results of each bidder from each subjective review perspective, the new subjective review results of each bidder are regenerated through the subjective analysis model.

[0068] Step S215: The new subjective review results of each bidder and the objective review results of each bidder shall be used as the bid evaluation results of each bidder.

[0069] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0070] Based on the same inventive concept, this application also provides an intelligent bid document review device for implementing the intelligent bid document review method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations of one or more intelligent bid document review device embodiments provided below can be found in the limitations of the intelligent bid document review method described above, and will not be repeated here.

[0071] In one exemplary embodiment, such as Figure 3 As shown, an intelligent review device for tender documents is provided, comprising: an acquisition module 310, a generation module 320, and an review module 330, wherein: The acquisition module 310 is used to acquire the bid documents of each bidder and the bidding review standard information of the bidding party, and based on the bidding review standard information, identify the objective review standard and the subjective review standard of the bidding party. The generation module 320 is used to split the bid documents of each bidder into the objective bid content and the subjective bid content of each bidder, and generate the objective review results of each bidder based on the objective bid content and the objective review criteria. The review module 330 is used to generate subjective review results for each bidder based on the objective review results and subjective bidding content of each bidder, according to the subjective review standards and through the subjective review analysis model, and to generate bid evaluation results for each bidder based on the subjective review results and objective review results of each bidder.

[0072] Optionally, the acquisition module 310 is specifically used for: The bidding review criteria information is broken down into subjective review content and objective review content, and the bidding requirements information of the bidding party is obtained. Based on the bidding requirements information, a requirements analysis strategy is used to identify the bidding correlation information between the subjective review content and the objective review content; The objective review content will be used as the objective review standard of the bidding party, and the subjective review content and the bidding-related information will be used as the subjective review standard of the bidding party.

[0073] Optionally, the generation module 320 is specifically used for: For each bid document, based on the bid document, the semantic distribution information of the bid document is identified through a text recognition network; Based on the semantic distribution information, the preset tender document information is queried to identify the first semantic distribution information of subjective content and the second semantic distribution information of objective content. Based on the first semantic distribution information of subjective content and the second semantic distribution information of objective content, the tender document is split into the objective tender content of the bidder and the subjective tender content of the bidder.

[0074] Optionally, the generation module 320 is specifically used for: For each bidder, based on the objective bidding content of the bidder, the bidding data of each bidding information type is identified, and based on each objective review standard, the sub-review standards of each bidding information type and the key weight values ​​of each bidding information type are identified; Based on the bidding data of each bidding information type, sub-bid review results of each bidding information type are generated through the sub-review criteria of each bidding information type; Based on the sub-bid review results of each bid information type, an objective review result for the bidder is generated using preset key weight values ​​for each bid information type.

[0075] Optionally, the audit module 330 is specifically used for: Based on the bidding association information of each bidder, identify the associated review results in the objective review results of each bidder; Based on the subjective bidding content of each bidder and the associated review results of each bidder, and according to the subjective review content of each bidder, the subjective review model generates sub-subjective review results for each bidder from each subjective review perspective. Based on the sub-subjective review results of each bidder from various subjective review perspectives, the subjective review results of the bidder are generated through the subjective analysis model.

[0076] Optionally, the audit module 330 is specifically used for: The subjective review results of each bidder are fed back to the expert client, and the subjective review modification suggestions of each bidder are received from the expert client. Based on the subjective review modification suggestions of each bidder and the sub-subjective review results of each bidder from each subjective review perspective, the subjective analysis model is used to regenerate the new subjective review results of each bidder. The new subjective review results of each bidder and the objective review results of each bidder shall be used as the bid evaluation results of each bidder.

[0077] Each module in the aforementioned intelligent bid evaluation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0078] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements an intelligent tender document review method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0079] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0080] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of a beer warehouse inventory optimization method.

[0081] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of a beer warehouse inventory optimization method.

[0082] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of a beer warehouse inventory optimization method.

[0083] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0084] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0085] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0086] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for intelligent evaluation of tender documents, characterized in that, The method includes: Obtain the bid documents of each bidder and the bidding review standard information of the bidding party, and based on the bidding review standard information, identify the objective review standard and the subjective review standard of the bidding party; The bid documents of each bidder are broken down into objective bid content and subjective bid content. Based on the objective bid content, objective review results are generated for each bidder according to the objective review criteria. Based on the objective review results of each bidder and the subjective bidding content of each bidder, and in accordance with the subjective review standards, the subjective review results of each bidder are generated through the subjective review analysis model. Based on the subjective review results of each bidder and the objective review results of each bidder, the bid evaluation results of each bidder are generated.

2. The method according to claim 1, characterized in that, The step of identifying the bidding party's objective review standards and subjective review standards based on the bidding review standard information includes: The bidding review criteria information is broken down into subjective review content and objective review content, and the bidding requirements information of the bidding party is obtained. Based on the bidding requirements information, a requirements analysis strategy is used to identify the bidding correlation information between the subjective review content and the objective review content; The objective review content will be used as the objective review standard of the bidding party, and the subjective review content and the bidding-related information will be used as the subjective review standard of the bidding party.

3. The method according to claim 2, characterized in that, The step of splitting the bid documents of each bidder into objective bid content and subjective bid content includes: For each bid document, based on the bid document, the semantic distribution information of the bid document is identified through a text recognition network; Based on the semantic distribution information, the preset tender document information is queried to identify the first semantic distribution information of subjective content and the second semantic distribution information of objective content. Based on the first semantic distribution information of subjective content and the second semantic distribution information of objective content, the tender document is split into the objective tender content of the bidder and the subjective tender content of the bidder.

4. The method according to claim 1, characterized in that, The objective review results for each bidder, based on their objective bid content and according to the objective review criteria, are generated, including: For each bidder, based on the objective bidding content of the bidder, the bidding data of each bidding information type is identified, and based on each objective review standard, the sub-review standards of each bidding information type and the key weight values ​​of each bidding information type are identified; Based on the bidding data of each bidding information type, sub-bid review results of each bidding information type are generated through the sub-review criteria of each bidding information type; Based on the sub-bid review results of each bid information type, an objective review result for the bidder is generated using preset key weight values ​​for each bid information type.

5. The method according to claim 2, characterized in that, The subjective review analysis model includes a subjective review model and a subjective analysis model. Based on the objective review results of each bidder and the subjective bidding content of each bidder, and according to the subjective review standards, the subjective review results of each bidder are generated through the subjective review analysis model, including: Based on the bidding association information of each bidder, identify the associated review results in the objective review results of each bidder; Based on the subjective bidding content of each bidder and the associated review results of each bidder, and according to the subjective review content of each bidder, the subjective review model generates sub-subjective review results for each bidder from each subjective review perspective. Based on the sub-subjective review results of each bidder from various subjective review perspectives, the subjective review results of the bidder are generated through the subjective analysis model.

6. The method according to claim 5, characterized in that, The process of generating bid review results for each bidder based on their subjective review results and objective review results includes: The subjective review results of each bidder are fed back to the expert client, and the subjective review modification suggestions of each bidder are received from the expert client. Based on the subjective review modification suggestions of each bidder and the sub-subjective review results of each bidder from each subjective review perspective, the subjective analysis model is used to regenerate the new subjective review results of each bidder. The new subjective review results of each bidder and the objective review results of each bidder shall be used as the bid evaluation results of each bidder.

7. An intelligent evaluation device for tender documents, characterized in that, The device includes: The acquisition module is used to acquire the bid documents of each bidder and the bidding review standard information of the bidding party, and based on the bidding review standard information, identify the objective review standard and the subjective review standard of the bidding party. The generation module is used to split the bid documents of each bidder into the objective bid content and the subjective bid content of each bidder, and generate the objective review results of each bidder based on the objective bid content and the objective review criteria. The review module is used to generate subjective review results for each bidder based on the objective review results and subjective bidding content of each bidder, according to the subjective review standards and through the subjective review analysis model, and to generate bid evaluation results for each bidder based on the subjective review results and objective review results of each bidder.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images