Intelligent calibration method and device, computer equipment, storage medium and program product

Abstract

The invention relates to the technical field of bidding document evaluation, and discloses an intelligent calibration method and device, computer equipment, a storage medium and a program product. The method comprises the steps of obtaining at least one to-be-calibrated bidding file and a preset bidding rule; screening the bidding files according to a preset bidding rule, and determining candidate bidding files; analyzing the candidate bidding file according to a preset review strategy to obtain a corresponding review result, the preset review strategy being predetermined based on the historical bidding data and the historical calibration data corresponding to the historical bidding data; and determining a calibrated target bidding file according to the review result. By implementing the technical scheme of the invention, automatic and accurate bidding document evaluation and calibration based on the preset rule and historical data can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of bidding document evaluation, and in particular to an intelligent calibration method, device, computer equipment, storage medium and program product. Background Art

[0002] The current bid evaluation and bidding process usually involves issuing a tender notice through official channels, detailing project requirements, qualification requirements, and bid deadlines. Bidders are required to submit paper tender documents, including technical proposals and commercial quotations, within the specified time. Subsequently, the bid evaluation committee will conduct a detailed manual review and scoring of the bid documents in accordance with the standards and methods in the bidding documents. Finally, the bid evaluation committee will discuss and negotiate, and determine the winning candidate based on the review results, and the tenderer will then make the final bidding decision.

[0003] However, the entire process is highly dependent on manual operations, and it takes a lot of manpower and time from the submission and review of bidding documents to the bidding decision. At the same time, this manual review and scoring is easily affected by subjective factors, which may lead to inaccurate or biased bidding results. Summary of the invention

[0004] In view of this, the present invention provides an intelligent calibration method, apparatus, computer equipment, storage medium and program product to solve the problem of how to reduce the time consumption and subjective bias in the bid evaluation process caused by manual operation.

[0005] In a first aspect, the present invention provides an intelligent calibration method, comprising: obtaining at least one bidding document to be calibrated and preset bidding rules; screening each bidding document according to the preset bidding rules to determine candidate bidding documents; analyzing the candidate bidding documents according to a preset evaluation strategy to obtain corresponding evaluation results, wherein the preset evaluation strategy is predetermined based on historical bidding data and corresponding historical calibration data; and determining a target bidding document for calibration according to the evaluation results.

[0006] The intelligent calibration method provided by the embodiment of the present invention reduces manual intervention and improves the automation level of the evaluation process through preset rules and evaluation strategies. By using preset bidding rules and historical data for screening, candidate bidding documents can be determined more accurately, thereby improving the accuracy of screening. The evaluation strategy is based on historical bidding and calibration data, making the evaluation process more scientific and data-driven, and reducing subjectivity. Automated screening and analysis can greatly improve processing efficiency and shorten the time cycle of bid evaluation. The preset rules and strategies ensure the consistency of evaluation standards and avoid inconsistent evaluation results due to human factors.

[0007] In an optional implementation, each bidding document is screened according to preset bidding rules to determine candidate bidding documents, including: parsing at least one bidding document to determine corresponding first indicator data; querying a pre-established rule base according to the first indicator data to determine a corresponding target rule set; wherein the rule base is a collection of target rule conditions defined by a user through a rule configuration interface; checking the first indicator data according to the target rule set to determine whether the first indicator data meets the first rule condition included in the target rule set; and determining the bidding document that meets the first rule condition as a candidate bidding document.

[0008] The intelligent calibration method provided by the embodiment of the present invention allows the user to define the target rule conditions through the rule configuration interface, so that the evaluation criteria can be customized according to specific needs, thereby improving flexibility. By parsing the bid documents and comparing them with the pre-established rule base, the bid documents that meet the target rules can be accurately screened out, thereby enhancing the accuracy of the screening. Based on the inspection of specific indicator data and target rule sets, the evaluation process is made more objective and data-driven, reducing the influence of subjective judgment. The use and maintenance of the rule base helps to systematically manage the rule conditions and ensure consistency and standardization in the evaluation process. Automated data parsing and rule matching improve evaluation efficiency and reduce manual intervention and potential operational errors.

[0009] In an optional implementation, the preset review strategy includes a pre-established review model library; the candidate bid documents are analyzed according to the preset review strategy to obtain corresponding review results, including: identifying whether the first indicator data includes initial key data, the initial key data is data that requires the preset review strategy to review; when it is determined that the first indicator data includes the initial key data, the candidate bid documents are analyzed according to the review model library to obtain corresponding review results.

[0010] The intelligent calibration method provided by the embodiment of the present invention ensures that the key data is focused on during the review process by identifying and analyzing the initial key data, thereby enhancing the pertinence and effectiveness of the review. The use of the review model library for analysis makes the review process more standardized and scientific, reducing the interference of subjective judgment. Analysis and review based on actual data can more objectively reflect the actual situation and compliance of the bidding documents. Automatic identification and analysis of key data improves the automation and systematic management of the review, and helps to improve work efficiency and accuracy. By using a preset review model, the review results can be more consistent and reliable, thereby improving the overall review quality.

[0011] In an optional implementation, the candidate bidding documents are analyzed according to the review model library to obtain corresponding review results, including: extracting initial key data to obtain key features; inputting the key features into the review model library to obtain review results.

[0012] The intelligent calibration method provided by the embodiment of the present invention can focus more on the most important information during the review process by extracting key features from the initial key data, avoiding the interference of redundant data, and improving the pertinence and efficiency of the review. The extracted key features are input into the review model library, and the preset review model is used for analysis, which ensures the systematicness and standardization of the review process and reduces the influence of human subjectivity. Automatic extraction of key features and input into the model library greatly improves the processing speed and review efficiency. Review based on the key features actually extracted can more accurately reflect the actual situation of the bidding documents, ensure that the decision is based on data, and thus improve the scientificity and reliability of the decision. Using the review model library for review ensures the consistency and reliability of the results. All bidding documents are evaluated according to the same standards, reducing the variability of the review results.

[0013] In an optional implementation, before extracting the initial key data to obtain the key features, the method further includes: performing data cleaning on the initial key data to obtain target key data.

[0014] The intelligent calibration method provided by the embodiment of the present invention can remove duplicate, erroneous or inconsistent data through data cleaning, ensuring that the data used is accurate and reliable, thereby improving the quality of the review results. Through the cleaning process, irrelevant or unimportant information is eliminated, noise is reduced, and only relevant key data is used during analysis and review, thereby improving the accuracy of the analysis. Cleaning data helps to standardize the format and normalize information, so that the data remains consistent in different stages and different systems, and improves the availability and consistency of the data. Using the cleaned and sorted target key data for review ensures that the decision is based on high-quality and high-accuracy data, thereby improving the reliability and scientificity of the decision.

[0015] In an optional embodiment, after determining the target bid document for calibration according to the evaluation results, the method further includes: determining a first calibration result of the target bid document; in response to a selection operation on a display form of the first calibration result, determining a target display form of the first calibration result; and visually displaying the first calibration result according to the target display form.

[0016] The intelligent calibration method provided by the embodiment of the present invention can determine the display mode according to different needs and user preferences in response to the selection operation of the display form of the first calibration result, so that the result presentation is more in line with the needs of the audience. By visually displaying the first calibration result according to the target display form, complex data and results are easier to understand and interpret, reducing the difficulty of information processing. Visual display can reveal trends and patterns in the data, helping users to better analyze and interpret the results, so as to make more informed decisions.

[0017] In an optional embodiment, determining historical bidding data includes: obtaining at least one sample bidding document and evaluation opinion data corresponding to the at least one sample bidding document; the evaluation opinion data is used to represent the evaluation opinions put forward by the evaluators after evaluating the at least one sample bidding document according to preset evaluation criteria; and determining the at least one sample bidding document and the evaluation opinion data as historical bidding data.

[0018] In the intelligent calibration method provided by the embodiment of the present invention, historical data can be used as a reference standard in the review process to help reviewers maintain consistency and reduce subjective bias, thereby improving the accuracy and fairness of the review. Through the accumulation and analysis of historical data, a data-driven decision model can be established to more scientifically guide future bidding and review work.

[0019] In an optional embodiment, determining historical calibration data includes: obtaining a second calibration result corresponding to at least one sample bidding document; the second calibration result is used to represent the final bidding document selected by the tendering personnel from at least one sample bidding document based on the review opinion data; and determining the second calibration result as the historical calibration data.

[0020] The intelligent calibration method provided by the embodiment of the present invention saves the second calibration result as historical data, allowing data analysis of past calibration decisions to discover potential patterns and trends, thereby providing data-driven support for future decisions.

[0021] In a second aspect, the present invention provides an intelligent calibration device, comprising: an acquisition module, used to acquire at least one bidding document to be calibrated and preset bidding rules; a screening module, used to screen each bidding document according to the preset bidding rules and determine candidate bidding documents; an analysis module, used to analyze the candidate bidding documents according to a preset evaluation strategy to obtain corresponding evaluation results, wherein the preset evaluation strategy is predetermined based on historical bidding data and corresponding historical calibration data; a first determination module, used to determine the target bidding document for calibration according to the evaluation results.

[0022] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the intelligent calibration method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0023] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the intelligent calibration method of the first aspect or any corresponding embodiment thereof.

[0024] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the intelligent calibration method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 is a schematic flow chart of an intelligent calibration method according to an embodiment of the present invention;

[0027] Figure 2 is a flow chart of another intelligent calibration method according to an embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of a rule matching engine module according to an embodiment of the present invention;

[0029] Figure 4 is a schematic diagram of a custom expansion interface module according to an embodiment of the present invention;

[0030] Figure 5 is a structural block diagram of an intelligent calibration device according to an embodiment of the present invention;

[0031] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0033] Tendering is a formal procurement process used to select suppliers or contractors to meet specific needs. This process usually includes issuing a tender notice, accepting bids, evaluating bids, and ultimately selecting and awarding a contract. The main purpose of tendering is to obtain the most suitable products, services or works through competition, ensuring fairness, transparency and best value in procurement.

[0034] In related technologies, a tender notice is issued through official channels, providing information such as project requirements, qualification requirements and bidding deadlines so that potential bidders can understand and participate. Then, the bidders prepare and submit technical and commercial documents according to the requirements of the tender documents. Subsequently, the bid evaluation committee conducts a detailed review and scores the bid documents based on the prescribed bid evaluation criteria. Finally, based on the bid evaluation results, the tenderer or the bid evaluation committee discusses and negotiates, finally determines the successful bidder, and enters the contract signing and performance stage.

[0035] However, the above bidding process is inefficient because the entire process is highly dependent on manual operations, involving the submission of bid documents, review and bidding decisions, which consumes a lot of manpower and time. In addition, manual review and scoring are easily affected by subjective factors, which may lead to inaccurate or biased evaluation results. At the same time, the process lacks modern technology support, such as big data and artificial intelligence, which limits the accuracy and efficiency of bid evaluation and decision-making.

[0036] In view of this, the technical solution of the present invention can significantly improve the flexibility and efficiency of the calibration process by introducing a rule-based configuration system. Users can quickly adjust the calibration rules according to actual needs, simplifying the parameter adjustment process and reducing the difficulty of operation and the risk of system errors. At the same time, the system supports dynamic adjustment and combination of multiple calibration rules, enhancing adaptability and functionality. The optimized algorithm and rule configuration improves the efficiency and accuracy of calibration, reduces maintenance costs, and simplifies system maintenance. The user-friendly interface and flexible rule configuration enhance the user experience and enhance the user's trust and satisfaction with the system.

[0037] According to an embodiment of the present invention, an embodiment of an intelligent calibration method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] In this embodiment, an intelligent calibration method is provided, which can be used for a calibration system, wherein the calibration system is built into a computer device. Figure 1 is a flow chart of an intelligent calibration method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0039] Step S101, obtaining at least one bidding document to be determined and preset bidding rules.

[0040] Bidding documents are written materials submitted by each bidding unit, including their bidding plan, quotation, technical capability description, company qualifications, etc. Specifically, before the bidding deadline, all bidding units must submit bidding documents in accordance with the bidding requirements. The system collects these documents and ensures their integrity and validity.

[0041] Preset bidding rules are specifications for standardized review and bid determination of bidding documents, and are used to evaluate and screen each bidding document. Specifically, before the bidding begins, the tenderer will set review rules based on project requirements, industry standards, or contract terms. These rules can include quantitative scores (such as price, technical capability scores) and qualitative judgments (such as the innovation of the solution, implementation plan). During the bidding process, the system will call these preset bidding rules to review the bidding documents to be determined. These rules are usually set in advance by the tenderer to ensure the consistency and fairness of the bid evaluation process.

[0042] Step S102, screening each bidding document according to preset bidding rules to determine candidate bidding documents.

[0043] Candidate bid documents are those that are selected after screening and meet the preset bidding rules. The system will evaluate and screen the received bid documents according to the preset bidding rules, with the aim of determining which bid documents meet the basic requirements and are eligible for further review by applying standardized review criteria. Specifically, the system analyzes each bid document according to preset rules (such as technical standards, qualification requirements, price restrictions, etc.). For example, it may be checked whether the bidding unit meets the technical capability requirements, whether it is within the budget, whether all required documents have been submitted, etc. Based on the screening results, the system marks the bid documents that meet the requirements as candidate documents, which are usually the bids that are considered the most competitive after preliminary screening.

[0044] Step S103, analyzing the candidate bidding documents according to a preset evaluation strategy to obtain corresponding evaluation results, wherein the preset evaluation strategy is predetermined based on historical bidding data and corresponding historical calibration data.

[0045] The preset review strategy refers to the evaluation criteria and methods determined in advance during the bidding review process, which are used to conduct systematic and standardized analysis and scoring of bid documents. Specifically, the candidate bid documents will be analyzed in depth according to the pre-set review strategy. Among them, the preset review strategy may include review criteria, scoring methods and other relevant requirements, which are used to systematically evaluate the pros and cons of each candidate bid document. The system analyzes each candidate bid document item by item according to the preset review strategy, records the compliance of each standard, and assigns or scores. For example, the technical review may include a detailed examination of the details of the technical solution, and the price review includes an analysis of the rationality of the quotation.

[0046] Furthermore, preset review strategies are developed based on past bidding and tendering experience. These strategies use historical data to optimize the review process and improve the accuracy and fairness of the review. Specifically, effective review criteria and strategies are identified through the analysis of historical bidding data and tendering results. For example, which technical indicators in past projects can best predict project success, which price levels can best ensure the economic feasibility of the project, etc. Based on these historical data, a review strategy suitable for the current bidding project is developed.

[0047] The evaluation results are a comprehensive evaluation of each candidate bid document. These results will serve as the basis for decision-making and help determine the final winning candidates. Specifically, by scoring or evaluating each candidate bid document, the corresponding evaluation results are generated. Among them, these results may include the comprehensive score of each bid document, the detailed distribution of each score, and evaluation opinions.

[0048] Step S104, determining the target bidding document for the bid according to the evaluation results.

[0049] The target bid document is the bid document that is determined to be the most consistent with the bidding requirements and evaluation criteria among all the bid documents after the evaluation results are analyzed and compared, that is, the final winning bid document. Specifically, the scores, evaluations and other evaluation data of each bid document are summarized into a comprehensive evaluation report. This report may include information such as the score of each bid document on each evaluation standard, the comprehensive score, and the comments of the evaluation team. The summarized evaluation results are compared, and the performance of each bid document on different evaluation standards is analyzed, and the bid documents are ranked according to their comprehensive scores or evaluations. Among them, the bid document with the highest score can be considered the best candidate.

[0050] The intelligent calibration method provided by the embodiment of the present invention reduces manual intervention and improves the automation level of the evaluation process through preset rules and evaluation strategies. By using preset bidding rules and historical data for screening, candidate bidding documents can be determined more accurately, thereby improving the accuracy of screening. The evaluation strategy is based on historical bidding and calibration data, making the evaluation process more scientific and data-driven, and reducing subjectivity. Automated screening and analysis can greatly improve processing efficiency and shorten the time cycle of bid evaluation. The preset rules and strategies ensure the consistency of evaluation standards and avoid inconsistent evaluation results due to human factors.

[0051] In this embodiment, an intelligent calibration method is provided, which can be used for a calibration system, wherein the calibration system is built into a computer device. Figure 2 is a flow chart of an intelligent calibration method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0052] Step S201, obtaining at least one bidding document to be determined and preset bidding rules. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0053] Step S202, screening each bidding document according to preset bidding rules to determine candidate bidding documents.

[0054] Specifically, the above step S202 includes:

[0055] Step S2021, parse at least one bidding document to determine corresponding first indicator data.

[0056] The first indicator data refers to the key indicators extracted from the bidding documents, which are predetermined indicators based on the preset bidding rules, and may include, for example, technical parameters, price, delivery time, etc. These key indicators are used for subsequent rule matching and screening to determine whether the bidding documents meet the preset standards or requirements. Specifically, after reading the content in the bidding documents, the first indicator data is extracted from the bidding documents using automated tools, such as optical character recognition technology to extract text data (such as technical solutions, quotation details, qualification certificates, etc.) from the bidding documents.

[0057] Step S2022, querying a pre-established rule base according to the first indicator data to determine a corresponding target rule set; wherein the rule base is a set of target rule conditions defined by the user through a rule configuration interface.

[0058] The rule base is a collection of various predefined rules and conditions. These rules and conditions are used to evaluate and verify the data in the bidding documents. Among them, the rule base is defined and managed through the rule configuration interface corresponding to the calibration system. The target rule conditions can include evaluation criteria, qualification requirements, constraints, etc. For example, technical indicators must meet certain performance standards, and the quotation amount must not exceed the budget limit. Specifically, users define various rules through the rule configuration interface. Rules can be simple conditional judgments or complex logical combinations. Each rule usually includes conditions and execution logic, such as "if the equipment performance parameters are higher than a certain value, the technical requirements are met."

[0059] Specifically, the first indicator data is used as input to query the matching rules in the rule base. For example, the first indicator data includes a price of 120,000 yuan, and the user-defined target rule condition that matches the price in the rule base is "price is higher than 100,000 yuan". Based on the query results, the rule set that matches the first indicator data is filtered out from the rule base. The target rule set is those rules that match the first indicator data. The determined target rule set is recorded for subsequent review and analysis.

[0060] Step S2023: Check the first indicator data according to the target rule set to determine whether the first indicator data meets the first rule condition included in the target rule set.

[0061] The target rule set is a set of rules that are selected from the rule base and match the first indicator data. It contains a series of rule conditions that are used to evaluate whether the first indicator data of the bidding document meets the requirements. Each rule condition defines a specific requirement that the data should meet. For example, a technical indicator must be greater than a threshold, or a quotation amount must be within a specified range.

[0062] Check the first indicator data for each rule condition included in the target rule set one by one. Specifically, extract relevant fields or values ​​from the first indicator data. Compare the extracted data with the rule conditions to check whether the data meets the rule conditions. For example, if the rule condition is "the technical indicator must be greater than 100", check whether the technical indicator in the first indicator data is indeed greater than 100. For another example, if the rule condition is "the quotation amount must not exceed 50,000 yuan", check whether the quotation amount in the first indicator data is less than or equal to 50,000 yuan. If the first indicator data meets the conditions in all target rule sets, it means that the data meets these rules; otherwise, it does not meet them.

[0063] In some optional implementations, before the above step S2023, the method further includes: receiving a newly compiled extension code from the user according to a preset custom interface to update the rule base; wherein the extension code is used to represent the second rule condition newly defined by the user.

[0064] Extension codes are developer-defined codes or identifiers used to describe and define new rule conditions. These codes usually represent the properties and logic of the rules in a specific format so that the system can understand and apply these conditions. A custom interface is a system-provided interface used to receive external input and perform extensions or updates. It can be an API (application programming interface), a data import tool, a configuration management tool, etc. Secondary rule conditions are new rule conditions defined by developers, which are newly added conditions based on existing rules. For example, they may include new business logic, validation rules, or decision criteria. Specifically, the codes of new rule conditions created and compiled by developers. These codes are defined by developers and represent new logic or features of secondary rule conditions. The extension codes provided by developers are integrated into the rule base to make it part of the system.

[0065] Step S2024: determine the bid documents that meet the conditions of the first rule as candidate bid documents.

[0066] The bidding documents whose first indicator data meet the first rule condition in the target rule set are screened as candidate bidding documents, that is, the first indicator data in the candidate bidding documents have passed all checks of the target rule set.

[0067] The intelligent calibration method provided by the embodiment of the present invention allows the user to define the target rule conditions through the rule configuration interface, so that the evaluation criteria can be customized according to specific needs, thereby improving flexibility. By parsing the bid documents and comparing them with the pre-established rule base, the bid documents that meet the target rules can be accurately screened out, thereby enhancing the accuracy of the screening. Based on the inspection of specific indicator data and target rule sets, the evaluation process is made more objective and data-driven, reducing the influence of subjective judgment. The use and maintenance of the rule base helps to systematically manage the rule conditions and ensure consistency and standardization in the evaluation process. Automated data parsing and rule matching improve evaluation efficiency and reduce manual intervention and potential operational errors.

[0068] Step S203, analyzing the candidate bidding documents according to a preset evaluation strategy to obtain a corresponding evaluation result, wherein the preset evaluation strategy is predetermined based on historical bidding data and corresponding historical calibration data.

[0069] The preset review strategy includes a pre-trained review model library, which can be understood as a pre-built intelligent review system platform. Specifically, the intelligent review system platform is built by using technical means such as big data and artificial intelligence. The platform should have functions such as online review, automatic scoring, and data analysis to improve the efficiency and accuracy of the review. Collect relevant data of previous bidding projects, including bidding documents, bid evaluation results, and winning results. Organize and analyze the data to extract valuable information and rules to provide support for intelligent review and decision-making. Develop suitable intelligent review algorithms and models based on project characteristics and needs. Algorithms and models should be able to automatically score and sort bidding documents and provide reference opinions for the bid evaluation committee. Specifically, the process of automatically analyzing and evaluating bidding documents using artificial intelligence (AI) technology, especially machine learning, deep learning and other algorithms. These algorithms can simulate the review process of human experts, automatically extract key information from bidding documents through learning and training, and score according to preset review criteria. Among them, the implementation of intelligent review algorithms can include the following steps: cleaning, converting and standardizing bidding documents so that the algorithm can accurately extract key information. Using technologies such as natural language processing, features related to the evaluation criteria are extracted from the bidding documents. The model is trained using historical data or expert-annotated data so that the model can learn and understand the evaluation criteria. The bidding documents to be evaluated are input into the trained model, and the model will output one or more scoring values.

[0070] Among them, determining the historical bidding data includes: obtaining at least one sample bidding document and evaluation opinion data corresponding to the at least one sample bidding document; the evaluation opinion data is used to represent the evaluation opinions put forward by the evaluators after evaluating the at least one sample bidding document according to the preset evaluation criteria; and determining the at least one sample bidding document and the evaluation opinion data as historical bidding data.

[0071] Specifically, the purpose of clarifying the "separation of evaluation and determination" is to ensure the fairness, equity and efficiency of the bid evaluation process, while ensuring the accuracy and rationality of the bid determination decision. Formulate specific separation principles for bid evaluation and determination, such as the bid evaluation is conducted by an expert review team, while the determination is the responsibility of the tenderer or authorized agency.

[0072] The principles of separation of assessment include the principle of unified authority and responsibility, the principle of open rules, the principle of competition and selection, and the principle of independence.

[0073] Among them, the principle of unified authority and responsibility is the separation of evaluation and determination, which emphasizes that in the bidding process, evaluation and determination are separated as two relatively independent links, while ensuring that the tenderer has the decision-making power for determination, and the evaluation opinions of the evaluation committee are only used as a reference for the tenderer to determine the bid. This principle aims to solve the problem of misalignment of authority and responsibility in the past bidding process and restore the autonomy of the tenderer.

[0074] The principle of open rules is that during the implementation of the separation of evaluation and assessment, the principle of open rules should be followed to ensure that the evaluation process and evaluation criteria are clear to bidders. The evaluation results should also be publicized and announced to ensure the openness and transparency of information.

[0075] The principle of competitive selection is that in the process of bid evaluation, the principle of competitive selection should be adhered to, and the best bidder should be selected through a fair competition mechanism. At the same time, in the bidding stage, the tenderer should determine the bid based on the recommendation of the bid evaluation committee and in accordance with the procedures and methods specified in the bidding documents to ensure that the selection of the successful bidder is fair and reasonable.

[0076] The principle of independence is that the assessment separation must maintain independence, and the reviewers cannot be influenced by any vested interests. Reviewers should be professionals in the field, with the necessary professional knowledge and experience to ensure the objectivity and fairness of the review results.

[0077] The goals of separation of assessment and evaluation include promoting fair and just selection of successful bidders, restoring the autonomy of tenderers, and optimizing the business environment.

[0078] Among them, the main goal of separation of evaluation and determination is to separate bid evaluation and determination as two relatively independent links, avoid the transfer of interests and improper behavior, and ensure that the selection process of the successful bidder is fair and just.

[0079] In the implementation of the separation of evaluation and award, the tenderer will have the decision-making power for awarding the bid, and the evaluation opinions of the bid evaluation committee will only be used as a reference. This change is intended to restore the autonomy of the tenderer, enabling it to select the most suitable bidder based on the nature and characteristics of the project.

[0080] By promoting the reform of separation of assessment and evaluation, we can continuously optimize the business environment in the public resource transaction field, improve bidding efficiency, reduce transaction costs, and provide market entities with a more fair, just and efficient trading environment.

[0081] Specifically, users submit bidding documents according to the requirements of the bidding documents. The system receives the bidding documents and conducts a preliminary review to ensure that the format and content of the documents comply with the regulations. The bid evaluation committee reviews the bidding documents according to the evaluation standards and methods specified in the bidding documents. The bid evaluation committee gives evaluation opinions and recommends the winning candidates.

[0082] Among them, determining the historical calibration data includes: obtaining a second calibration result corresponding to at least one sample bidding document; the second calibration result is used to represent the final bidding document selected by the tendering personnel from at least one sample bidding document based on the evaluation opinion data; and determining the second calibration result as the historical calibration data.

[0083] Specifically, the tenderer conducts bidding according to the procedures and methods specified in the bidding documents based on the recommendation of the bid evaluation committee. The system provides a bidding interface to display the evaluation opinions of the bid evaluation committee and the recommended winning candidate information. The tenderer makes the final bidding decision based on the information provided by the system and the project requirements. The system records the bidding results and generates a bidding notice. The system publicizes the winning results to ensure the openness and transparency of information. Bidders can query the winning results through the system. Based on the winning results, the system automatically or manually triggers subsequent processes, such as contract signing and performance management.

[0084] Specifically, the bid evaluation process is a key link to ensure that the bid evaluation work is carried out in an orderly manner. According to the requirements of the bidding documents, a bid evaluation committee is established, and the members and responsibilities of the bid evaluation committee are determined. According to the requirements of the bidding documents, the bid evaluation standards and scoring rules are formulated, and the bid evaluation indicators and weights are clarified. The bid evaluation committee reviews the bid documents submitted by the bidders to ensure their completeness and compliance with the requirements. The bid evaluation committee holds a bid evaluation meeting to review the technical and business plans of the bidders and scores them according to the bid evaluation standards. The bid evaluation committee records the review process, including review opinions and scoring results. The bid evaluation committee confirms the review results and forms a bid evaluation report. The bid determination committee holds a bid determination meeting to review and confirm the bid evaluation results. The bid determination committee records the bid determination process, including bid determination opinions and bid determination results. The bid determination committee publicizes the bid determination results and makes them public to all bidders and the tenderer. The tenderer issues a notice of winning to the successful bidder and notifies other unsuccessful bidders at the same time. The successful bidder submits a performance bond in accordance with the requirements of the bidding documents. The tenderer and the successful bidder shall sign a written contract based on the tender documents and the successful bidder's bid documents.

[0085] Specifically, the above step S203 includes:

[0086] Step S2031, identifying whether the first indicator data includes initial key data, where the initial key data is data that requires a preset review strategy to be reviewed.

[0087] Initial key data are key data points or indicators preset in the review strategy, which are used for evaluation according to a specific review model. For example, initial key data may include technical specifications, performance indicators, quotation information, delivery period, etc., depending on the requirements and strategy of the review. Specifically, check whether the extracted first indicator data includes all preset initial key data. For example, if the review strategy requires checking "technical specifications" as key data, it is necessary to verify whether the first indicator data contains relevant technical specifications.

[0088] Step S2032: When it is determined that the first indicator data includes the initial key data, the candidate bidding documents are analyzed according to the evaluation model library to obtain corresponding evaluation results.

[0089] The review model library is a collection of various review models that are used to analyze and evaluate candidate bid documents. Each model defines the rules and methods for converting initial key data into review results. For example, it can include text classification models, natural language processing models, and ensemble learning models. The text classification model regards the bid document as text data and uses the text classification model to determine whether the bid document meets the review criteria. The naive Bayes model is used. The natural language processing model is used to deeply analyze and understand the text in the bid document, extract key information and score it. The recurrent neural network (RNN) is used. Multiple different types of models are integrated to obtain the final review results through voting or weighting. The ensemble learning model can comprehensively utilize the advantages of different models to improve the accuracy and stability of the review. Specifically, each model in the review model library needs to be configured according to the review requirements. This includes defining the model's input (initial key data), processing method (calculation rules), and output (review results). According to the initial key data in the bid document, select a suitable review model for analysis. The basis for selecting a model may be data type, review strategy, or specific review criteria. The initial key data is input into the selected review model, and the model performs calculations and analyses according to the preset rules and algorithms. The review results are generated based on the calculation results of the review model. The review results are used to describe the performance of the bid document in various review indicators. For example, if the model is a scoring model, the results may include the score of each indicator and the total score.

[0090] The intelligent calibration method provided by the embodiment of the present invention ensures that the key data is focused on during the review process by identifying and analyzing the initial key data, thereby enhancing the pertinence and effectiveness of the review. The use of the review model library for analysis makes the review process more standardized and scientific, reducing the interference of subjective judgment. Analysis and review based on actual data can more objectively reflect the actual situation and compliance of the bidding documents. Automatic identification and analysis of key data improves the automation and systematic management of the review, and helps to improve work efficiency and accuracy. By using a preset review model, the review results can be more consistent and reliable, thereby improving the overall review quality.

[0091] In some optional implementations, the above step S2032 includes:

[0092] Step a1: clean the initial key data to obtain the target key data.

[0093] The target key data is the cleaned data that meets the requirements of the review model and is ready for subsequent analysis. Specifically, data cleaning is the processing of raw data to remove erroneous, duplicated, inconsistent or incomplete information to ensure data quality and consistency. During the review process, the purpose of data cleaning is to ensure that the initial key data meets the expected format and standards, so as to obtain accurate target key data. The system automatically cleans the initial key data, including format conversion, deduplication, standardization and other processing to ensure that the file is compatible with the review model library.

[0094] Step a2: extract the target key data to obtain key features.

[0095] Data extraction is to select and extract features or indicators useful for the review model from the target key data, namely key features. Extract key data points from the cleaned data, and these features are the basis for the review model to evaluate. Specifically, identify and select key features related to the review target. For example, extract specific parameters from technical specifications, or extract prices from quotation information.

[0096] Step a3, input the key features into the review model library to obtain the review results.

[0097] The extracted key features are provided as input to the review model. The review model will use these features for calculation and analysis. The model is used to evaluate the performance of the bid document and generate the corresponding review results. Specifically, according to the review strategy and feature type, a suitable model is selected from the review model library. For example, if the feature is a technical specification, a technical evaluation model can be selected. The key features are input into the selected model, and the model is calculated according to the preset rules and algorithms to obtain the review results corresponding to each bid document. For example, the review results can include scores, ratings, etc.

[0098] In the above implementation, data cleaning can remove duplicate, erroneous or inconsistent data, ensure that the data used is accurate and reliable, and thus improve the quality of the review results. Through the cleaning process, irrelevant or unimportant information is eliminated, noise is reduced, and only relevant key data is used during analysis and review, thereby improving the accuracy of the analysis. Cleaning data helps to standardize the format and normalize information, so that the data remains consistent in different stages and different systems, and improves the availability and consistency of the data. Using the cleaned and sorted target key data for review ensures that the decision is based on high-quality and high-accuracy data, thereby improving the reliability and scientificity of the decision. By extracting the key features from the initial key data, the review process can focus more on the most important information, avoid the interference of redundant data, and improve the pertinence and efficiency of the review. The extracted key features are input into the review model library, and the preset review model is used for analysis, which ensures the systematicness and standardization of the review process and reduces the influence of human subjectivity. Automatic extraction of key features and input into the model library greatly improves the processing speed and review efficiency. Review based on the actual extracted key features can more accurately reflect the actual situation of the bidding documents, ensure that the decision is based on data, and thus improve the scientificity and reliability of the decision. Using the review model library for review ensures consistency and reliability of the results. All bid documents are evaluated according to the same criteria, reducing the variability of the review results.

[0099] In some optional implementations, after the above step S203, the system further includes: verifying and adjusting the review results in combination with the opinions of the expert reviewers to ensure the accuracy and fairness of the review results.

[0100] Step S204: Determine the target bidding document for bidding based on the evaluation results. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0101] Step S205: determine the first bid determination result of the target bidding document.

[0102] The first bid evaluation result is the final evaluation result of the target bid document, indicating the performance of the bid document in the evaluation. For example, the first bid evaluation result may include a score, a ranking, an evaluation opinion, etc., which is used to show the comprehensive performance of the target bid document.

[0103] Step S206 : in response to the selection operation on the display form of the first calibration result, determining the target display form of the first calibration result.

[0104] The presentation format refers to how to present the first calibration results in a visual way. The choice of presentation format usually depends on the target audience and the purpose of the presentation. For example, a variety of presentation formats can be selected, including charts, tables, summary reports, dashboards, etc. The target presentation format is a determined and suitable presentation format to ensure that the results can be clearly and intuitively communicated to the target audience. Specifically, the most appropriate presentation format is selected based on user needs, audience background, and the purpose of the presentation. For example, management requires a concise summary report, while the technical review team requires detailed charts and data analysis.

[0105] Step S207: Visually display the first calibration result in a target display format.

[0106] Visualization presentation is the process of presenting the first calibration result graphically or graphically according to the previously determined target presentation form. Use appropriate tools (such as data visualization software, chart generator) to convert the first calibration result into a chart, graph or other visualization format. Specifically, generate the final visualization result according to the target presentation form. For example, if the chart presentation form is selected, create the relevant chart; if the report form is selected, compile the relevant report.

[0107] Furthermore, users can view the review results to understand the pros and cons of the bidding documents and the direction of improvement. At the same time, the system can also collect user feedback to further optimize the intelligent review algorithm and model. Based on user feedback and new data, the system can iteratively optimize the intelligent review algorithms and models included in the review model library to improve the accuracy and efficiency of the review. The system can regularly update model parameters, add new features, or improve the algorithm structure to adapt to the ever-changing review needs and market environment.

[0108] The intelligent calibration method provided by the embodiment of the present invention can determine the display mode according to different needs and user preferences in response to the selection operation of the display form of the first calibration result, so that the result presentation is more in line with the needs of the audience. By visually displaying the first calibration result according to the target display form, complex data and results are easier to understand and interpret, reducing the difficulty of information processing. Visual display can reveal trends and patterns in the data, helping users to better analyze and interpret the results, so as to make more informed decisions.

[0109] In some optional embodiments, the calibration system includes a dynamic rule configuration module, a rule matching engine module, a custom extension interface module, an intelligent review algorithm module and a model management module. The dynamic rule configuration module is responsible for storing, managing and updating calibration rules. These rules can be conditional statements based on business logic, laws and regulations or expert experience. The rule matching engine module automatically matches the corresponding rules according to the input calibration request and outputs the matching results. The custom extension interface module provides an API or SDK, allowing developers to expand the functions of the system by writing plug-ins or codes. The intelligent review algorithm module uses machine learning and deep learning algorithms to intelligently analyze and evaluate calibration requests. The model management module is responsible for model training, storage, updating and calling. The relational database mysql is used to store data such as rules, model parameters and calibration results. Remote procedure call (RPC) technology is used to realize communication and data transmission between the modules of the system.

[0110] The dynamic rule configuration module is responsible for storing, managing and updating calibration rules. It provides a friendly rule editing interface, allowing business personnel or experts to modify rules directly. It loads and parses the latest rule configuration in real time.

[0111] The rule configuration interface is used to add, modify, and delete calibration rules, and usually receives configuration data in JSON or XML format. The rule query interface provides rule query functions and returns a list or detailed information of rules under specific conditions. The rule validation interface provides rule validation functions when adding or modifying rules to ensure the validity and correctness of the rules.

[0112] Rule matching engine module such as Figure 3 As shown in the figure, according to the input bidding request, the corresponding rules are automatically matched. The matching results are output, including the matched rules, condition satisfaction, etc. The rule matching interface receives the bidding request (such as bidding document information) and returns the matched rule list and matching results. The result query interface provides the query function for the previous matching results.

[0113] Customized extension interface modules such as Figure 4 As shown, an API or SDK is provided to allow developers to extend the functions of the system by writing plug-ins or codes. The registration, loading and unloading of plug-ins or codes are managed. The plug-in registration interface allows developers to register new plug-ins or codes, and provide basic information and functional descriptions of the plug-ins. The plug-in loading interface loads registered plug-ins or codes to make them effective in the system. The plug-in unloading interface unloads plug-ins or codes that are no longer needed.

[0114] The intelligent review algorithm module uses machine learning and deep learning algorithms to perform intelligent analysis and evaluation on calibration requests. According to the algorithm output results and rule configuration, the final score or calibration result is calculated comprehensively. The model training interface receives training data, uses the selected algorithm to train the model, and saves the trained model. The model call interface loads the trained model, performs intelligent review on the input calibration request, and returns the review result. The model evaluation interface provides the function of evaluating model performance, such as the calculation of accuracy, recall and other indicators.

[0115] The model management module is responsible for model training, storage, update and call. Monitor the running status and performance of the model. The model storage interface saves the trained model to a specified location (such as a database, file system). The model loading interface loads the model from a specified location for use by the intelligent review algorithm module. The model update interface retrains the model with new training data and updates the stored model. The model monitoring interface provides monitoring functions for the running status of the model, such as viewing the model running log, performance indicators, etc.

[0116] In this embodiment, it is assumed that a procurement system needs to purchase a batch of network equipment, and suppliers have submitted their respective bidding documents. The system needs to determine which suppliers are qualified based on a series of rules and intelligent review algorithms, and give a comprehensive score scenario, which is illustrated by example.

[0117] The rules include: suppliers must provide financial statements for the past three years and have an average annual revenue of no less than RMB 100 million. The bidding documents must include product technical specifications and at least five key performance indicators (KPIs). Suppliers must have relevant industry certifications (such as ISO 9001).

[0118] Specifically, the system receives the supplier's bidding documents. The rule matching engine obtains the above rules from the rule base and automatically checks the bidding documents. The engine verifies the existence of the documents and confirms whether the average annual revenue meets the requirements. The engine parses the technical specifications and calculates the number of KPIs in them. The engine verifies whether the supplier has provided the required certification documents. If the bidding document does not meet any of the rules, the supplier will be preliminarily excluded. If the bidding document meets all the rules, the engine passes key information (such as financial data, technical specifications, etc.) to the intelligent review module.

[0119] The intelligent review module uses a machine learning model trained based on historical data to predict the supplier's service quality (such as on-time delivery rate, after-sales service response speed, etc.). The deep learning model is used to analyze the text content in the bidding documents and evaluate the supplier's understanding of the requirements and innovation capabilities. Specifically, the intelligent review module receives supplier information and key data from the rule matching engine. Extract key features such as financial data, technical specifications, historical service records, etc. from the received data. Use the machine learning model to predict the supplier's service quality score. Use the deep learning model to analyze the text content in the bidding documents and give an innovation capability score. The service quality score, innovation capability score, and possible other indicators (such as price, brand reputation, etc.) are weighted and summed according to the preset weights to obtain the supplier's comprehensive score. Output the comprehensive score and ranking information to the system for the final bidding decision.

[0120] Finally, suppose three suppliers submit bid documents. After preliminary screening by the rule matching engine, two suppliers meet all the rules and are passed to the intelligent review module. The intelligent review module gives the two suppliers a comprehensive score based on its algorithm and model, and ranks them. Finally, the system can make bidding decisions based on these scores and rankings.

[0121] The intelligent calibration method provided by the embodiment of the present invention allows the user or system administrator to dynamically configure and adjust the rules of the calibration system according to actual needs. By providing an intuitive and easy-to-use configuration interface or API, the threshold for using the system is lowered, and the flexibility and adaptability of the system are improved. An efficient and intelligent rule matching algorithm is designed, which can quickly and accurately process data according to the configured rules. By optimizing the algorithm structure and introducing machine learning technology, efficient processing of complex data structures and rules is achieved. The system architecture adopts a modular design, which is convenient for functional expansion and upgrading according to needs in the later stage. It supports a variety of data interfaces and protocols and can be seamlessly connected with different external systems. During the rule configuration process, it can automatically detect potential rule conflicts and provide solutions or suggestions. The risk of system errors and performance degradation caused by improper rule configuration is reduced. The system has a built-in real-time performance monitoring module that can continuously track and analyze the operating status of the system. Through the intelligent optimization algorithm, the system parameters and resource allocation are automatically adjusted to ensure that the system always runs in the best state. Provide a wealth of visualization tools to display the calibration results to users in the form of charts, reports, etc. It is convenient for users to intuitively understand the calibration effect and provide strong support for decision-making. A comprehensive user rights management system is designed to ensure that different users can only access and operate resources within their authorized scope. Multiple security verification mechanisms are introduced, such as password encryption and access log records, to ensure the security and integrity of system data. An open API interface is provided to allow users to customize extension functions according to their needs. The user community is encouraged to participate in system extension development to form a healthy ecosystem.

[0122] In this embodiment, an intelligent calibration device is also provided, which is used to implement the above embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0123] This embodiment provides an intelligent calibration device, such as Figure 5 As shown, including:

[0124] An acquisition module 301 is used to acquire at least one bidding document to be determined and preset bidding rules;

[0125] A screening module 302 is used to screen each bidding document according to a preset bidding rule to determine a candidate bidding document;

[0126] An analysis module 303 is used to analyze the candidate bidding documents according to a preset evaluation strategy to obtain a corresponding evaluation result. The preset evaluation strategy is predetermined based on historical bidding data and corresponding historical calibration data;

[0127] The first determination module 304 is used to determine the target bidding document for the bid according to the evaluation result.

[0128] In some optional implementations, the screening module 302 includes:

[0129] A parsing submodule, used to parse at least one bidding document and determine corresponding first indicator data;

[0130] A query submodule, used to query a pre-established rule base according to the first indicator data to determine a corresponding target rule set; wherein the rule base is a set of target rule conditions defined by the user through a rule configuration interface;

[0131] A checking submodule, configured to check the first indicator data according to the target rule set to determine whether the first indicator data meets the first rule condition included in the target rule set;

[0132] The first determination submodule is used to determine the bidding documents that meet the first rule conditions as candidate bidding documents.

[0133] In some optional implementations, the analysis module 303 includes:

[0134] An identification submodule, used to identify whether the first indicator data includes initial key data, where the initial key data is data that requires a preset review strategy to be reviewed;

[0135] The second analysis submodule is used to analyze the candidate bidding documents according to the review model library to obtain corresponding review results when it is determined that the first indicator data includes initial key data.

[0136] In some optional embodiments, the second analysis submodule includes:

[0137] An extraction unit, used to extract the initial key data to obtain key features;

[0138] The input unit is used to input key features into the review model library to obtain review results.

[0139] In some optional embodiments, the second analysis submodule further includes:

[0140] The cleaning unit is used to clean the initial key data to obtain the target key data.

[0141] In some optional implementations, the intelligent calibration device further includes:

[0142] A second determination module, used to determine a first determination result of the target bidding document;

[0143] A third determination module, configured to determine a target presentation form of the first calibration result in response to a selection operation on a presentation form of the first calibration result;

[0144] The display module is used to visually display the first calibration result according to the target display form.

[0145] In some optional implementations, the analysis module 303 includes:

[0146] The first acquisition submodule is used to acquire at least one sample bidding document and evaluation opinion data corresponding to the at least one sample bidding document; the evaluation opinion data is used to represent the evaluation opinions put forward by the bid evaluation personnel after evaluating the at least one sample bidding document according to the preset evaluation criteria;

[0147] The second determination submodule is used to determine at least one sample bidding document and evaluation opinion data as historical bidding data.

[0148] In some optional implementations, the analysis module 303 further includes:

[0149] The second acquisition submodule is used to acquire a second calibration result corresponding to at least one sample bidding document; the second calibration result is used to represent the final bidding document selected by the tendering personnel from the at least one sample bidding document according to the evaluation opinion data;

[0150] The third determining submodule is used to determine the second calibration result as the historical calibration data.

[0151] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0152] The intelligent calibration device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0153] The intelligent calibration device provided by the embodiment of the present invention reduces manual intervention and improves the automation level of the evaluation process through preset rules and evaluation strategies. By using preset bidding rules and historical data for screening, candidate bidding documents can be determined more accurately, thereby improving the accuracy of screening. The evaluation strategy is based on historical bidding and calibration data, making the evaluation process more scientific and data-driven, and reducing subjectivity. Automated screening and analysis can greatly improve processing efficiency and shorten the time cycle of bid evaluation. The preset rules and strategies ensure the consistency of evaluation standards and avoid inconsistent evaluation results due to human factors.

[0154] The embodiment of the present invention also provides a computer device having the above Figure 5 The intelligent calibration device shown.

[0155] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0156] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0157] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0158] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0159] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0160] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0161] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0162] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0163] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0164] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. An intelligent calibration method, characterized in that: The method comprises: Obtaining at least one bidding document to be determined and preset bidding rules; Screening each of the bidding documents according to the preset bidding rules to determine candidate bidding documents; Analyzing the candidate bidding documents according to a preset evaluation strategy to obtain a corresponding evaluation result, wherein the preset evaluation strategy is predetermined based on historical bidding data and corresponding historical calibration data; The target bidding document for the bid is determined based on the evaluation results.

2. The method according to claim 1, characterized in that: The step of screening each of the bidding documents according to the preset bidding rules to determine candidate bidding documents includes: Parsing the at least one bidding document to determine corresponding first indicator data; According to the first indicator data, a pre-established rule base is queried to determine a corresponding target rule set; wherein the rule base is a set of target rule conditions defined by a user through a rule configuration interface; Checking the first indicator data according to the target rule set to determine whether the first indicator data meets the first rule condition included in the target rule set; The bidding document satisfying the first rule condition is determined as the candidate bidding document.

3. The method according to claim 2, characterized in that Preset review strategies include a library of pre-established review models; Analyze the candidate bidding documents according to the preset evaluation strategy to obtain corresponding evaluation results, including: Identify whether the first indicator data includes initial key data, where the initial key data is data that requires a preset review strategy to be reviewed; When it is determined that the first indicator data includes the initial key data, the candidate bidding documents are analyzed according to the evaluation model library to obtain corresponding evaluation results.

4. The method according to claim 3, characterized in that The analyzing the candidate bidding documents according to the evaluation model library to obtain corresponding evaluation results includes: Extracting the initial key data to obtain key features; The key features are input into the review model library to obtain the review results.

5. The method according to claim 4, characterized in that Before extracting the initial key data to obtain key features, the method further includes: The initial key data is cleaned to obtain target key data.

6. The method according to claim 1, characterized in that After determining the target bidding document for bidding according to the evaluation results, the method further includes: Determining a first bid determination result of the target bidding document; In response to a selection operation on a presentation form of the first calibration result, determining a target presentation form of the first calibration result; The first calibration result is visually displayed according to the target display format.

7. The method according to claim 1, characterized in that Determine the historical bidding data, including: Acquire at least one sample bidding document and evaluation opinion data corresponding to the at least one sample bidding document; the evaluation opinion data is used to represent the evaluation opinions put forward by the bid evaluation personnel after evaluating the at least one sample bidding document according to the preset evaluation criteria; The at least one sample bidding document and the review opinion data are determined as the historical bidding data.

8. The method according to claim 7, characterized in that Determine historical calibration data, including: Acquire a second calibration result corresponding to the at least one sample bidding document; the second calibration result is used to represent the final bidding document selected by the tendering personnel from the at least one sample bidding document according to the evaluation opinion data; The second calibration result is determined as the historical calibration data.

9. An intelligent calibration device, characterized in that: The device comprises: An acquisition module, used to acquire at least one bidding document to be determined and preset bidding rules; A screening module, used to screen each of the bidding documents according to the preset bidding rules to determine candidate bidding documents; An analysis module, used to analyze the candidate bidding documents according to a preset evaluation strategy to obtain a corresponding evaluation result, wherein the preset evaluation strategy is predetermined based on historical bidding data and corresponding historical calibration data; The first determination module is used to determine the target bidding document for the bid according to the evaluation result.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the intelligent calibration method according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the intelligent calibration method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the intelligent calibration method according to any one of claims 1 to 8.

Images