Intelligent auxiliary bid evaluation method and device, equipment, storage medium and program product

Abstract

The invention relates to the technical field of bidding and tendering review, and discloses an intelligent auxiliary bidding and tendering review method, device and equipment, a storage medium and a program product, and the method comprises the steps: obtaining a bidding and tendering file review rule and a to-be-reviewed target bidding and tendering file; analyzing the target bidding and tendering file to obtain a review parameter corresponding to the target bidding and tendering file; and reviewing the target bidding and tendering file according to the bidding and tendering file reviewing rule and the reviewing parameter, and generating a reviewing result for the target bidding and tendering file. By implementing the technical scheme of the invention, the error rate of the review object is reduced, the bid evaluation process can be completed in a shorter time, and the review efficiency and the review accuracy of the bidding and tendering document are improved.

Description

Technical Field

[0001] The present invention relates to the field of bidding and tendering evaluation technology, and specifically to intelligent auxiliary bidding evaluation methods, devices, equipment, storage media and program products. Background Art

[0002] With the development of computer technology, for the bidding documents received by the bidding system, the verified bidding documents are usually transmitted to the bid evaluation system, and the judges conduct online evaluation based on the evaluation coefficient. The current bid evaluation system can provide each judge with a personalized bid evaluation interface to optimize the document display method according to the judges' preferences and habits. The judges can score the bidding documents according to the standardized scoring template provided by the bid evaluation system to reduce the subjective errors of the judges. However, when there are many bidding documents entering the review stage, this increases the time for the judges to read a large number of original bids and the risk of errors, thereby affecting the review efficiency and accuracy of the bidding documents. Summary of the invention

[0003] In view of this, the present invention provides an intelligent assisted bid evaluation method, device, equipment, storage medium and program product to solve the problem of low evaluation efficiency and evaluation accuracy of bidding documents.

[0004] In a first aspect, the present invention provides an intelligent assisted bid evaluation method, comprising: obtaining bidding document evaluation rules and a target bidding document to be evaluated; parsing the target bidding document to obtain evaluation parameters corresponding to the target bidding document; evaluating the target bidding document according to the bidding document evaluation rules and evaluation parameters, and generating an evaluation result for the target bidding document.

[0005] The intelligent assisted bid evaluation method provided by the embodiment of the present invention analyzes the target bidding document to determine its corresponding evaluation parameters, and evaluates the target bidding document according to the evaluation parameters and the bidding document evaluation rules set based on actual needs to obtain the corresponding evaluation results. As a result, the target bidding document can be automatically evaluated without the need for the evaluation personnel to read a large number of original bid documents, thus reducing the error rate of the evaluation object, and at the same time, the bid evaluation process can be completed in a shorter time, thereby improving the evaluation efficiency and evaluation accuracy of the bidding document.

[0006] In an optional embodiment, obtaining bidding document review rules includes: responding to a rule parameter configuration operation for document review to obtain atomic parameters for document review; responding to a first rule configuration operation based on the atomic parameters to obtain atomic rules for document review; responding to a second rule configuration operation based on the atomic rules to obtain business rules for document review; the bidding document review rules include atomic rules and business rules.

[0007] The intelligent assisted bid evaluation method provided by the embodiment of the present invention supports the adjustment of atomic rules and business rules according to actual evaluation needs, without modifying the core code of the bid evaluation system, greatly improving the configuration flexibility of the bidding document evaluation rules, and at the same time reducing the development and maintenance costs. By configuring the business rules, the bidding document evaluation rules can support the combination and nesting of multiple business rules to adapt to a wider range of evaluation application scenarios and meet the personalized needs of different evaluation projects, which is beneficial to improving the adaptability and scalability of the bid evaluation system. The visualization and editability of the bidding document evaluation rules configuration make maintenance more convenient and reduce the skill requirements and workload of maintenance personnel.

[0008] In an optional embodiment, the method further includes: determining a target comparison dimension of the atomic rule in response to a configuration operation on a comparison dimension of the atomic rule; and / or determining a target comparison method of the atomic rule in response to a configuration operation on a comparison method of the atomic rule.

[0009] The intelligent assisted bid evaluation method provided by the embodiment of the present invention supports the configuration of comparison dimensions and comparison methods for atomic rules, which can reduce the demand for hard coding and customized development and reduce development and maintenance costs.

[0010] In an optional implementation, obtaining the target bidding document to be reviewed includes: obtaining an initial bidding document to be reviewed; and performing structured processing on the initial bidding document to be reviewed to generate the target bidding document to be reviewed.

[0011] The intelligent assisted bid evaluation method provided in the embodiment of the present invention performs structured processing on the initial bidding documents to be evaluated so that the evaluation documents meet the evaluation format requirements, facilitates the extraction of evaluation-related information from the evaluation documents, and is beneficial to improving the evaluation accuracy and efficiency.

[0012] In an optional implementation, before obtaining the bidding document review rules and the target bidding document to be reviewed, it also includes: obtaining a bidding document review request, the bidding document review request carries first signature information, and the first signature information is generated based on a preset signature method; decrypting the signature information to obtain decrypted data, and signing the decrypted data according to the preset signature method to generate second signature information; if the first signature information and the second signature information are consistent, issuing the review authority to the initiator of the bidding document review request.

[0013] The intelligent assisted bid evaluation method provided by the embodiment of the present invention ensures the security of the evaluation, avoids leakage of evaluation data, and prevents unauthorized access and malicious attacks by verifying the consistency of the first signature information and the second signature information.

[0014] In an optional implementation, the target bidding document is reviewed according to the bidding document review rules and review parameters to generate a review result for the target bidding document, including: obtaining a rule expression corresponding to the bidding document review rules, and converting the rule expression into a syntax tree; based on the recursive structure of the syntax tree, the target bidding document is recursively reviewed according to the review parameters to generate a review result corresponding to the target bidding document.

[0015] The intelligent assisted bid evaluation method provided by the embodiment of the present invention converts the syntax tree according to the regular expression to perform recursive evaluation according to the recursive structure of the syntax tree, thereby improving the evaluation execution efficiency and execution accuracy.

[0016] In an optional implementation, generating evaluation results corresponding to the target bidding documents includes: visually displaying the evaluation results of the target bidding documents in the evaluation interface; entering the evaluation results into the evaluation interface in response to a confirmation operation on the evaluation results; and summarizing and verifying the evaluation results to generate evaluation results corresponding to the target bidding documents.

[0017] The intelligent assisted bid evaluation method provided by the embodiment of the present invention supports one-key entry of evaluation results, reduces manual entry by reviewers, and thus reduces the input error rate. The evaluation results are summarized and verified to ensure the accuracy and rationality of the summary results.

[0018] In an optional implementation, the method further includes: comparing each target bidding document to determine the similarity between different target bidding documents; and locating similar contents of different target bidding documents based on the similarity.

[0019] The intelligent assisted bid evaluation method provided by the embodiment of the present invention can help quickly identify the similarities, differences and potential risk factors between different target bidding documents by comparing the similarities of different target bidding documents, thereby making the evaluation effect more reliable.

[0020] In an optional implementation, the method further includes: obtaining a review priority of the target bidding document; and reviewing the target bidding document according to the review priority.

[0021] The intelligent assisted bid evaluation method provided by the embodiment of the present invention performs evaluation according to evaluation priorities, so that target bidding documents with higher evaluation priorities can be evaluated first, thereby further improving the evaluation effect of the bidding documents.

[0022] In an optional implementation, the method further includes: obtaining repeated review tasks in the target bidding document review process; and caching task review results corresponding to the repeated review tasks when the repeated review tasks are executed for the first time.

[0023] The intelligent assisted bid evaluation method provided by the embodiment of the present invention caches the task evaluation results corresponding to the repeated evaluation tasks to avoid repeated execution of the repeated evaluation tasks, thereby saving evaluation time and further improving the evaluation efficiency.

[0024] In an optional embodiment, the method further includes: obtaining a review object database, the review object database including at least one document review object; extracting the document review objects from the review object database to obtain at least one target review object; counting the recommendation data generated for each target review object, and determining the target responsible object from the at least one target review object.

[0025] The intelligent assisted bid evaluation method provided by the embodiment of the present invention extracts target evaluation objects and recommends target responsible objects so as to supervise the evaluation results and ensure the credibility and rationality of the evaluation results.

[0026] In a second aspect, the present invention provides an intelligent assisted bid evaluation device, comprising: an acquisition module, used to obtain bidding document evaluation rules and a target bidding document to be evaluated; a parsing module, used to parse the target bidding document and obtain evaluation parameters corresponding to the target bidding document; and an evaluation module, used to evaluate the target bidding document according to the bidding document evaluation rules and evaluation parameters, and generate an evaluation result for the target bidding document.

[0027] 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 assisted bid evaluation method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0028] 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 assisted bid evaluation method of the first aspect or any corresponding embodiment thereof.

[0029] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, which are used to enable a computer to execute the intelligent assisted bid evaluation method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] 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.

[0031] Figure 1 is a schematic diagram of a flow chart of an intelligent assisted bid evaluation method according to an embodiment of the present invention;

[0032] Figure 2 is a comparison selection diagram of a calculation rule engine according to an embodiment of the present invention;

[0033] Figure 3 is a flow chart of another intelligent assisted bid evaluation method according to an embodiment of the present invention;

[0034] Figure 4 is a flow chart of another intelligent assisted bid evaluation method according to an embodiment of the present invention;

[0035] Figure 5 is a schematic diagram of a syntax tree according to an embodiment of the present invention;

[0036] Figure 6 is a structural block diagram of an intelligent auxiliary bid evaluation device according to an embodiment of the present invention;

[0037] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] 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.

[0039] The current bid evaluation system can provide each judge with a personalized bid evaluation interface to optimize the document display method according to the judge's preferences and habits. The judge can score the bidding documents according to the standardized scoring template provided by the bid evaluation system to reduce the judge's subjective errors. However, when there are many bidding documents entering the evaluation stage, this increases the time for the judges to read a large number of original bids and the risk of errors, thus affecting the efficiency and accuracy of the bidding document evaluation.

[0040] Based on this, the present invention provides an intelligent review service to assist the bid evaluation process, improve the review efficiency of objective items by reviewers, and reduce the human error rate. Specifically, the core capabilities of the intelligent review service can be encapsulated as an independent microservice, maintaining loose coupling with the bid evaluation system and being able to be assigned to other bid evaluation systems. For the review service, a standardized API document can be defined using the RESTful API standardized protocol to ensure the clarity and versatility of the review service interface.

[0041] When the bid evaluation system reaches the intelligent review step, it will asynchronously call the review service to create a review task. The review service can perform the document review task according to the configured bidding document review rules and return the result to the caller (i.e. the bid evaluation system). The bid evaluation system can display the review results to the reviewers for easy review and adoption.

[0042] According to an embodiment of the present invention, an embodiment of an intelligent assisted bid evaluation 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.

[0043] In this embodiment, an intelligent assisted bid evaluation method is provided, which can be used in computer devices, such as computers, mobile phones, tablet computers, etc. A bid evaluation system is deployed in the computer device, and the bid evaluation system calls the evaluation service to perform intelligent evaluation on the bidding documents. Figure 1 is a flow chart of an intelligent assisted bid evaluation method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0044] Step S101, obtaining bidding document review rules and target bidding documents to be reviewed.

[0045] The target bidding document to be reviewed is a structured bidding document that enters the bid evaluation system. The bidding document review rules are pre-set review rules for bidding documents, and the bidding document review rules are provided with a plurality of rule parameters, which can be determined based on basic data such as dictionaries and parameters corresponding to the bidding documents.

[0046] Among them, the dictionary is a file data management method used to improve the efficiency and accuracy of the preparation of bidding documents. That is, the fixed enumerated data such as specific qualifications, financial requirements and qualifications of key personnel required for bidding are integrated into a centralized "dictionary" for management to simplify the data entry process, ensure the consistency and reusability of data, and provide convenient support for subsequent business operations. The data in the dictionary needs to be updated or adjusted regularly, and support the modification, deletion and addition of existing data to ensure the timeliness and accuracy of the data.

[0047] Among them, parameters are rule parameters related to bid evaluation. The bid evaluation system adopts a centralized rule parameter management mechanism to ensure that all rule parameters related to bid evaluation can be managed by a unified platform, which greatly improves the convenience and accuracy of parameter management.

[0048] Specifically, the review system calls the review service through an interface, and uses the rule configuration interface provided by the review service to configure the bidding document review rules. When the bidding documents enter the evaluation system, the evaluation system can call the review service to obtain the bidding document review rules corresponding to the target bidding documents, and review the target bidding documents according to the bidding document review rules.

[0049] The rule configuration interface provided by the review service allows reviewers to directly modify the bidding document review rules without writing code, and the rule calculation engine can load and parse the latest bidding document review rule configuration in real time. Figure 2 As shown, from the perspectives of expression engine, high performance, lightweight, and support for custom extensions, Aviator can be chosen as the calculation rule engine. The calculation rule engine is responsible for parsing the evaluation rules of bidding documents, managing the registration and calling of execution functions, and other core functions. A function library is built into the calculation rule engine, which contains a series of predefined execution functions that can cover common review business scenarios. In addition, the calculation rule engine provides a second extension interface with clear interface specifications, including input parameters, output format, and error handling mechanisms, and provides development documentation to help developers quickly understand and use the extension interface to customize the execution function to meet the personalized needs of the review business. At the same time, the calculation rule engine can enable the compilation cache mechanism to avoid repeated compilation of rule expressions to improve computing performance.

[0050] Of course, we can also add a large model module based on the configuration of the calculation rule engine, so that the bid evaluation system can autonomously learn and optimize the calculation rule engine. By analyzing historical data and user feedback, the bid evaluation system can continuously adjust and improve the bidding document review rules and the calculation rule engine to adapt to more complex and changeable review application scenarios.

[0051] Step S102, parsing the target bidding document to obtain the evaluation parameters corresponding to the target bidding document.

[0052] The evaluation parameters are the rule parameters of the target bidding document, such as the bidding unit, business license, business term, name, establishment date, etc. The structured target bidding document is parsed to extract multiple parameter fields carried by the target bidding document, determine the parameters corresponding to each parameter field, and determine the parameters corresponding to each parameter field as the evaluation parameters.

[0053] Step S103, reviewing the target bidding document according to the bidding document review rules and review parameters, and generating a review result for the target bidding document.

[0054] The evaluation parameters are compared with the rule parameters set in the bidding document evaluation rules to determine whether the evaluation parameters meet the rule parameters in the bidding document evaluation rules. If the evaluation parameters all meet the rule parameters in the bidding document evaluation rules, the target bidding document is judged to have passed the evaluation, and the generated evaluation results are fed back to the bid evaluation system, which will display the evaluation results to the evaluation object for the evaluation object to confirm the evaluation results.

[0055] The review data generated during the review process can be stored in the database for subsequent verification. For example, a relational database is used to store data such as the review rules for bidding documents, target bidding documents, and review results; cache technology is used to cache the review terms, rule information, and response data of the target bidding documents to the corresponding database (such as the Redis library). This can reduce the frequency of access to the database, thereby speeding up data retrieval and reducing the load on the bid evaluation system.

[0056] The intelligent assisted bid evaluation method provided in this embodiment analyzes the target bidding document to determine its corresponding evaluation parameters, and evaluates the target bidding document according to the evaluation parameters and the bidding document evaluation rules set based on actual needs to obtain the corresponding evaluation results. As a result, the target bidding document can be automatically evaluated without the need for the evaluation personnel to read a large number of original bid documents, reducing the error rate of the evaluation object, and at the same time, the bid evaluation process can be completed in a shorter time, thereby improving the evaluation efficiency and evaluation accuracy of the bidding document.

[0057] In this embodiment, an intelligent assisted bid evaluation method is provided, which can be used in computer devices, such as computers, mobile phones, tablet computers, etc. A bid evaluation system is deployed in the computer device, and the bid evaluation system calls the evaluation service to perform intelligent evaluation on the bidding documents. Figure 3 is a flow chart of an intelligent assisted bid evaluation method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0058] Step S201, obtaining bidding document review rules and target bidding documents to be reviewed.

[0059] Specifically, the bidding document review rules include atomic rules and business rules. Among them, atomic rules are the most basic and indivisible rules. Each atomic rule is composed of two parameters and an operator. The operator supports equal, not equal, contain, not contain, greater than, greater than or equal to, less than, less than or equal to, empty, not empty, etc., to meet the needs of different bid evaluation rules. The structure of atomic rules ensures the directness and efficiency of rule execution, and can provide a solid foundation for complex bid evaluation processes.

[0060] Among them, business rules are rules set based on the bid evaluation business needs, which are composed of one or more atomic rules. As a result, the structure of business rules is not only flexible and changeable, but also able to efficiently meet complex and diversified business needs, ensuring the accuracy and efficiency of the bid evaluation process.

[0061] Accordingly, the above step S201 includes:

[0062] Step S2011, in response to the rule parameter configuration operation for the file review, obtain the atomic parameters of the file review.

[0063] Atomic parameters are file attribute parameters required for reviewing target bidding documents. The review service provides a rule parameter configuration interface, in which multiple rule parameter configuration fields are set. Reviewers can configure rule parameters in the rule configuration interface. Accordingly, the review service can respond to reviewers' rule parameter configuration operations for file review and determine the atomic parameters used for file review.

[0064] In a specific example, the structured target bidding document carries a business license. By decomposing the structured business license, multiple fields are decomposed from it: unified social credit code, legal representative, name, registered capital, type, establishment date, business term, business scope, domicile, registration authority, and issuance date. The parameters corresponding to each field are used as atomic parameters.

[0065] Through the rule parameter configuration interface provided by the evaluation service, the reviewers can add, modify, delete and query various rule parameters required for bid evaluation. Parameter types support text type, date type, numeric type, Boolean type, composite type, etc. to meet the needs of different bid evaluation rules.

[0066] It should be noted that when the parameter type is a composite type, there are at least one or more combinations of adding atomic parameters, and the corresponding attribute name and attribute type (such as text type, date type, numeric type, Boolean type, etc.) are entered in each atomic parameter. After completing the addition of atomic parameters, reference the atomic parameters in the atomic formula to configure the atomic rules.

[0067] Step S2012, in response to the first rule configuration operation based on the atomic parameter, obtain the atomic rule for the file review.

[0068] The review service provides an atomic rule configuration interface. The first rule configuration operation is the operation performed by the reviewer in the atomic rule configuration interface. For example, the reviewer can perform the first rule configuration operations such as adding, modifying, deleting and querying by dragging or filling out a form. Accordingly, the review service can respond to the first rule configuration operation performed by the reviewer based on the atomic parameters to obtain the atomic rules required for the document review.

[0069] In some optional implementations, the above method further includes:

[0070] Step a1, in response to a configuration operation on a comparison dimension of an atomic rule, determining a target comparison dimension of the atomic rule.

[0071] The comparison dimension of atomic rules supports comparison between bidding and tendering, comparison between tendering and tendering, comparison between tendering and bid opening / evaluation, etc. The target comparison dimension is the comparison dimension required for the current review service. A comparison dimension configuration component is set in the atomic rule configuration interface. Reviewers can perform configuration operations on the comparison dimension by triggering the comparison dimension configuration component. Correspondingly, the review service can respond to the reviewer's comparison dimension configuration operation and obtain the target comparison dimension of the current review service.

[0072] Among them, the comparison between bidding and tendering is a requirement set for the bidding agent, which requires the response of the bidding unit. In the case of the comparison between bidding and tendering, it is necessary to compare whether the bidding and tendering meet the requirements. In a specific example, the atomic rule requirement under this comparison dimension can be: the license type of the safety production assessment certificate meets the requirements. The atomic rule example is as follows: [Bidding] -> [Safety Production Assessment Certificate] -> [Safety Production Assessment Certificate] -> [License Type] is equal to [Bidding] -> [Safety Production Assessment Certificate] -> [Safety Production Assessment Certificate] -> [License Type].

[0073] Among them, when comparing bids, if they are different fields, they are compared within the same bidding document; if they are the same fields, one bidding document is compared with the same field in all other bidding documents. In a specific example, the atomic rule requirement under this comparison dimension can be: the business license company name meets the requirements. The atomic rule example is as follows: [Bidding] -> [Business License] -> [Business License] -> [Company Name] is equal to [Bidding] -> [Bidder Basic Information] -> [Bidder Basic Information] -> [Bidder Name].

[0074] Among them, when comparing bidding with bid opening / evaluation, it is necessary to compare the field values ​​of the bidding unit with the field values ​​of the bid opening and evaluation system to see if they meet the requirements. In a specific example, the atomic rule requirement under this comparison dimension can be: within the validity period of enterprise qualifications. The atomic rule example is as follows: [Bidding] -> [Enterprise Qualification] -> [Enterprise Qualification] -> [Validity Period] is greater than [Bid Evaluation] -> [Project Basic Information] -> [Bid Evaluation Date].

[0075] Step a2, in response to the configuration operation of the comparison mode for the atomic rule, determining the target comparison mode for the atomic rule.

[0076] The comparison method of atomic rules supports simple type comparison, Boolean comparison, identification field correspondence comparison, compound parameter comparison, etc. The target comparison method is the comparison method required for the current review service. A comparison method configuration component is set in the atomic rule configuration interface. Reviewers can trigger the comparison method configuration component to perform comparison method configuration operations. Correspondingly, the review service can respond to the reviewer's comparison method configuration operation and obtain the target comparison method of the current review service.

[0077] In a specific example, an atomic rule for simple type comparison is as follows: [Business License]-[Name] is equal to [Safety Production License]-[Unit Name].

[0078] In a specific example, the evaluation item of the commitment system can be of Boolean type, and its field is a constant such as [Yes] / [No]. The specific example is as follows: [Tender Opening] -> [Deposit] -> [Whether to submit deposit] is equal to yes.

[0079] In a specific example, the identification field correspondence comparison can be used to compare the fields of different certificates. Specifically, for the safety production assessment certificate, different positions require different certificates. For example, the legal representative must provide certificate A, but there is no independent field in the certificate to prove that this certificate is A. A must be identified from the [Certificate Number] field and compared with the legal representative.

[0080] In a specific example, the composite parameter comparison needs to satisfy all the attributes in the parameter. If the composite parameter is: qualification requirements {qualification major, qualification category, qualification type}, the atomic rule established is: [Bidding.Qualification] equals [Tendering.Qualification Requirements]. Then the checkpoints set can be: [Bidding.Qualification.Qualification Major] equals [Tendering.Qualification Requirements.Qualification Major] and [Bidding.Qualification.Qualification Category] equals [Tendering.Qualification Requirements.Qualification Category] and [Bidding.Qualification.Qualification Type] equals [Tendering.Qualification Requirements.Qualification Type]. Only when all of the above are met can the atomic rule be satisfied.

[0081] It should be noted that the properties of composite parameters can also be compared. The specific examples are as follows:

[0082] If the composite parameter is: qualification requirements {qualification major, qualification category, qualification type}, then the atomic rule established can be: [Bidding.Qualification.Qualification Major] is equal to [Tendering.Qualification Requirements.Qualification Major].

[0083] By supporting the configuration of comparison dimensions and comparison methods for atomic rules, the need for hard coding and customized development can be reduced, reducing development and maintenance costs.

[0084] Step S2013, in response to the second rule configuration operation based on the atomic rule, obtain the business rules for the file review.

[0085] The review service provides a business rule configuration interface. The second rule configuration operation is the operation that the reviewer performs on the business rule configuration interface. For example, the reviewer can perform the second rule configuration operations such as adding, modifying, deleting and querying by dragging or filling out a form. Specifically, you can use "#" to query the atomic rule list, and then enter the atomic rule name to perform a keyword search to select the rule name.

[0086] Business rules can be composed of one or more atomic rules, and multiple atomic rules are linked through the logical relationship symbols of business rules (such as and, or, if, (), etc.). When the reviewer configures the business rules in the business rule configuration interface, the review service can respond to the reviewer's second rule configuration operation based on the atomic rules to obtain the business rules required for document review.

[0087] In a specific example, the business rule is configured as: business license is valid; the business rule is composed of: [the legal representative of the business license meets the bidding requirements] and [the date of the business license is valid] and [the name of the bidder of the business license meets the requirements]. Among them, the "and" connected are the names of atomic rules.

[0088] Before selecting an atomic rule each time, you need to enter "#" and then enter the atomic rule name to perform a keyword search to select the rule name. Logical relationship symbols are used to represent the logical relationship between atomic rules, including: (1) ||: or, indicating that the selected atomic rules do not have to be satisfied at the same time. Satisfying one of them means that the business rules are met; (2) &: and, indicating that the selected atomic rules must be satisfied at the same time to be considered as meeting the business rules; (3) if (1, 2, 3): when...then...else..., indicating that when a certain rule 1 is met, it is processed according to rule 2, otherwise, it is processed according to rule 3; (4) (): brackets, expressing priority. For example, #atomic rule 1||#atomic rule 2||(#atomic rule 3&#atomic rule 4), it means that the review can be passed if atomic rule 1 or atomic rule 2 is satisfied or atomic rule 3 and atomic rule 4 are satisfied at the same time.

[0089] Step S2014, obtaining the initial bidding documents to be reviewed.

[0090] The initial bidding documents to be reviewed are the bidding documents prepared by the bidding unit according to the bidding requirements, which include the bid documents required for the bidding and qualification documents such as business licenses. Specifically, the bid evaluation system is provided with a file interface for review documents. The initial bidding documents to be reviewed are uploaded by the bidding unit through the file interface provided by the bid evaluation system, or can be selected by jumping to the file storage space through the file interface. Of course, the initial bidding documents to be reviewed can also be obtained by other means, which are not specifically limited here.

[0091] Step S2015, structurally processing the initial bidding documents to be reviewed to generate target bidding documents to be reviewed.

[0092] Parse the format and structure of the initial bidding documents to be reviewed, and determine the contents of the bid chapters, paragraphs, titles, and qualification documents in the initial bidding documents to be reviewed. Create structured rules based on the characteristics of the initial bidding documents to be reviewed and the requirements of the current review, including creating chapter titles, subtitles, paragraph marks, etc. Extract key information related to the review from the initial bidding documents to be reviewed, such as review criteria, problem descriptions, suggestions, etc. Organize and sort the extracted key information according to the created structured rules, and use appropriate tags or formats to distinguish different parts. Save the structured information as the target bidding document to be reviewed in a preset format, where the preset format can be XML format, PDF format, Word format, etc., and the saving format of the target bidding document is not limited here.

[0093] In some optional implementations, after the target bidding document is generated, necessary metadata, such as file name, date, etc., may be added to the target bidding document according to actual business needs to facilitate management and tracking of the target bidding document.

[0094] In some optional implementations, after the target bidding document is generated, a preliminary check may be performed on the target bidding document to ensure the accuracy and completeness of the information. For example, whether the structure is as expected, whether the key information is correctly extracted and organized, etc. If the preliminary check is correct, the target bidding document is stored in the review database.

[0095] In some optional implementations, the bid evaluation system may provide an interface for calling the review service, and the bid evaluation system may call the review service through the interface, and use the review service to automatically review the bidding documents received by the bid evaluation system. Accordingly, before the bid evaluation system executes step S201, the following steps are also included:

[0096] Step b1, obtaining a request for review of bidding documents, wherein the request for review of bidding documents carries first signature information, and the first signature information is generated based on a preset signature method.

[0097] The bidding document review request is a request for review personnel to initiate a review task through the review service interface. Specifically, the bidding document review request includes a request protocol, a request method, an encoding method, a response format, a request header, and a response body.

[0098] The request protocol is HTTP / HTTPS, the request method is POST, the encoding method is UTF-8, the response format is JSON, the request header is shown in Table 1, and the response body is shown in Figure 2 shown.

[0099] Table 1 Request header

[0100] Field Name type Required describe appId String(0,30] yes Authorization ID. It is uniformly allocated by the file service system. timestamp Long(0,20] yes Request timestamp. sign String(0,200] yes Signature value. Used for authentication.

[0101] Table 2 Response body

[0102]

[0103] The first signature information is carried in the bidding document review request so that the review service can verify the legal identity of the bidding document review request based on the first signature information. Specifically, the first signature information can be generated based on a preset signature method. For example, the first signature information is generated using the SM3 algorithm for the plain text data of the bidding document review request message, combined with the access identifier and the key. The detailed signature format of the first signature information is: SM3 ({appId}&{timestamp}&{secretKey}).

[0104] Step b2, decrypt the signature information to obtain decrypted data, and sign the decrypted data according to a preset signature method to generate second signature information.

[0105] After receiving the request for review of the bidding documents, the review service first decrypts the request message data of the bidding documents into plain text, and then signs the decrypted plain text data using a preset signature method to obtain the corresponding second signature information. Specifically, taking the use of the SM3 algorithm to generate the first signature information as an example, after receiving the request for review of the bidding documents, it is decrypted, and the decrypted plain text data is signed using the SM3 algorithm. The specific signature method is "(appId)+&+(timestamp)+&+(secretKey)". Among them, appId and secretKey provide identity identification for the review service, which is used to identify the identities of both parties, and the signature key pair is provided by the review service.

[0106] Step b3: If the first signature information and the second signature information are consistent, the review authority is issued to the initiator of the bidding document review request.

[0107] The first signature information is compared with the second signature information to determine whether the first signature information is consistent with the second signature information. If the first signature information and the second signature information are consistent, it means that the request for review of the bidding documents is a legitimate request. At this time, the review service can open the review authority to the initiator of the request for review of the bidding documents, so that it can review the target bidding documents according to actual needs.

[0108] By verifying the consistency between the first signature information and the second signature information, the security of the review is ensured, the leakage of review data is avoided, and unauthorized access and malicious attacks are prevented.

[0109] Of course, mechanisms such as data encryption, access control, and error handling can also be used to strengthen the security and reliability of the bidding document review rule configuration provided by the review service to ensure the stable operation of the evaluation process and data security, and to prevent malicious access and malicious attacks.

[0110] Step S202: parse the target bidding document to obtain the evaluation parameters corresponding to the target bidding document. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0111] Step S203, review the target bidding document according to the bidding document review rules and review parameters, and generate the review result for the target bidding document. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0112] The intelligent assisted bid evaluation method provided in this embodiment supports the adjustment of atomic rules and business rules according to actual review needs, without modifying the core code of the bid evaluation system, which greatly improves the configuration flexibility of the bidding document review rules and reduces the development and maintenance costs. By configuring business rules, the bidding document review rules can support the combination and nesting of multiple business rules to adapt to a wider range of review application scenarios and meet the personalized needs of different review projects, which is beneficial to improving the adaptability and scalability of the bid evaluation system. The visualization and editability of the bidding document review rule configuration make maintenance more convenient and reduce the skill requirements and workload of maintenance personnel. By structuring the initial bidding documents to be reviewed so that the review documents meet the review format requirements, it is convenient to extract review-related information from the review documents, which is beneficial to improving the review accuracy and review efficiency.

[0113] In this embodiment, an intelligent assisted bid evaluation method is provided, which can be used in computer devices, such as computers, mobile phones, tablet computers, etc. A bid evaluation system is deployed in the computer device, and the bid evaluation system calls the evaluation service to perform intelligent evaluation on the bidding documents. Figure 4 is a flow chart of an intelligent assisted bid evaluation method according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0114] Step S301, obtain the bidding document review rules and the target bidding document to be reviewed. Figure 3 Step S201 of the illustrated embodiment will not be described in detail here.

[0115] Step S302: parse the target bidding document to obtain the evaluation parameters corresponding to the target bidding document. Figure 3 Step S202 of the illustrated embodiment will not be described in detail here.

[0116] Step S303, reviewing the target bidding document according to the bidding document review rules and review parameters, and generating a review result for the target bidding document.

[0117] Specifically, the above step S303 includes:

[0118] Step S3031, obtain the rule expression corresponding to the bidding document review rule, and convert the rule expression into a syntax tree.

[0119] The rule expression is an expression formed based on the bidding document review rules, which includes atomic rules and business rules. The bid evaluation system parses the target bidding document it receives, determines the bidding document review rules corresponding to the target bidding document, decodes the rule expression generated by the bidding document review rules and saves it to the corresponding database.

[0120] When the bid evaluation system initiates an evaluation of a target bidding document, the bid evaluation system queries the database to retrieve the rule expression corresponding to the target bidding document to be evaluated, converts the rule expression, and generates a syntax tree corresponding to the rule expression.

[0121] Specifically, the parameter assembly interface and query cache mechanism are designed according to the parameters involved in the business rules. To obtain the parameter identifiers corresponding to the various rule parameters in the bidding document review rules, the parameter identifiers involved in the business rules need to implement the interface on the business side of the bid evaluation system to query the corresponding data source data, for example, the bid evaluation date parameter: [Basic Project Information] -> [Bid Evaluation Date]; the structured business rule data of the bidding needs to implement the interface on the business side of the bid evaluation system, for example, the structured data of the bidding unit: [Bid] -> [Business License] -> [Business License] -> [Company Name]; For frequently accessed parameter identifiers, a cache mechanism needs to be implemented to avoid repeated queries of the interface implementation class.

[0122] Therefore, a specific implementation class instance is created according to the rule parameter identifier to form a corresponding syntax tree, such as Figure 5 In a specific example, a factory pattern or a dependency injection (DI) framework can be used to create an implementation class instance, so that the correct implementation class instance can be created dynamically according to the parameter identifier at runtime without having to judge based on the hard-coded type in the code.

[0123] In a specific example, the syntax tree after the regular expression is converted is as follows:

[0124] {

[0125] "atoms":[{

[0126] "expression":"Business license_valid until>bid evaluation date",

[0127] "paramList":[{

[0128] "attributeList":[{

[0129] "attributeName":"Valid until"}],

[0130] "paramName":"Business License"},

[0131] {"paramName":"Evaluation Date"}]}, ...

[0133] ...],

[0134] "operation":"and"}.

[0135] Step S3032, based on the recursive structure of the syntax tree, recursively review the target bidding document according to the review parameters, and generate the review result corresponding to the target bidding document.

[0136] The recursive structure is used to characterize the calling order of the rules or parameters of each node of the syntax tree. Specifically, the syntax tree can use tail recursion or iteration instead of direct recursive calls to reduce the use of stack space and possible stack overflow problems. For subtrees that can be executed in parallel, the recursive syntax tree can use a multi-threaded concurrent execution mechanism to improve execution efficiency. According to the hierarchy of the syntax tree, the rules or parameters corresponding to each node of the syntax tree are spliced ​​into bidding document review rules, and the rule calculation is performed on the target bidding document. The entire syntax tree is executed in this way to obtain the final review result.

[0137] The intelligent assisted bid evaluation method provided by the embodiment of the present invention converts the syntax tree according to the regular expression to perform recursive evaluation according to the recursive structure of the syntax tree, thereby improving the evaluation execution efficiency and execution accuracy.

[0138] In some optional implementations, the step of generating the evaluation result corresponding to the target bidding document includes:

[0139] Step c1, visually displaying the review results of the target bidding documents in the review interface.

[0140] Step c2: in response to the confirmation operation on the review result, the review result is entered into the review interface.

[0141] Step c3, summarize the evaluation results and generate the evaluation results corresponding to the target bidding documents.

[0142] The bid evaluation system has an evaluation interface, and the evaluation results of the target bidding documents can be displayed visually on the evaluation interface. A confirmation component is set in the evaluation interface, and the reviewer checks the evaluation results on the evaluation interface to determine whether to adopt the evaluation results generated for the target bidding documents. If the reviewer adopts the evaluation result, it can trigger the confirmation component in the evaluation interface, and the bid evaluation system will respond to the confirmation operation triggered by the reviewer on the evaluation result, and enter the evaluation result into the evaluation interface with one click. In this way, the time and errors of manual input can be reduced.

[0143] After the reviewers have completed the entry of the review results, the review service will push the review process to the next review node, and the reviewers at the next review node will review the target bidding documents and asynchronously generate review reports. After all reviewers have completed the review of the target bidding documents, the review service automatically summarizes the review results given by each reviewer for the target bidding documents. At the same time, it performs logical verification and anomaly detection on each review result to ensure the accuracy and rationality of the summary result, and uses the summarized review result as the final review result.

[0144] The intelligent assisted bid evaluation method provided by the embodiment of the present invention supports one-key entry of evaluation results, reduces manual entry by reviewers, and thus reduces the input error rate. The evaluation results are summarized and verified to ensure the accuracy and rationality of the summary results.

[0145] In some optional implementations, the above method further includes:

[0146] Step d1, comparing each target bidding document to determine the similarity between different target bidding documents.

[0147] Step d2, locating similar contents of different target bidding documents based on similarity.

[0148] The review service can compare the review items (such as enterprise qualifications, financial status, etc.) of each target bidding document to determine the similarity of each target bidding document in the review items. After the similarity of the target bidding documents is determined, they will be displayed on the review interface so that the reviewers can quickly understand the similarities, differences and potential risk factors between the target bidding documents.

[0149] Similar contents between different target bidding documents can be marked, for example, similar contents between different target bidding documents can be marked in red font. Different similarities can have different marks, for example, similar contents with high similarity (for example, similarity over 90%) can be marked in red, similar contents with low similarity (for example, similarity below 50%) can be marked in green, and similar contents with medium similarity (for example, 50% to 90%) can be marked in yellow. Thus, similar contents in different target bidding documents can be located using marks. At the same time, file display supports paging to improve file query performance.

[0150] In an optional implementation, when the reviewer clicks on a content in a target bidding document, if the content is similar to other target bidding documents, a similar mark may be displayed at the content. When the reviewer clicks on the review mark, other target bidding documents that are similar to the content may be displayed on the review interface.

[0151] The intelligent assisted bid evaluation method provided by the embodiment of the present invention can help quickly identify the similarities, differences and potential risk factors between different target bidding documents by comparing the similarities of different target bidding documents, thereby making the evaluation effect more reliable.

[0152] In some optional implementations, the above method further includes:

[0153] Step e1, obtaining the review priority of the target bidding document.

[0154] Step e2, review the target bidding documents according to the review priority.

[0155] The review priority is used to characterize the review importance of the target bidding document. The greater the review importance, the higher the review priority of the target bidding document. The review priorities of each target bidding document are sorted, and the target bidding documents with higher review priorities are reviewed first. Specifically, a priority-based task scheduling algorithm is deployed in the review service, which can intelligently allocate review resources based on factors such as the urgency of the review task, resource requirements, and dependencies, to ensure that high-priority review tasks are executed first.

[0156] In some optional implementations, the target bidding documents may also be sorted according to the resource consumption required for review, and review tasks with low resource consumption may be given priority.

[0157] The intelligent assisted bid evaluation method provided by the embodiment of the present invention performs evaluation according to evaluation priorities, so that target bidding documents with higher evaluation priorities can be evaluated first, thereby further improving the evaluation effect of the bidding documents.

[0158] In some optional implementations, the above method further includes:

[0159] Step f1, obtaining repeated review tasks in the target bidding document review process.

[0160] Step f2: when the repeated review task is executed for the first time, the task review result corresponding to the repeated review task is cached.

[0161] Repeated review tasks are repeated reviews that exist in the review process of the target bidding documents, that is, repeated reviews of certain review items. When executing the review process for the target bidding documents, the review process of the target bidding documents is disassembled to determine whether there are repeated review tasks.

[0162] If there are repeated review tasks, the repeated review tasks can be marked. After the repeated review task is executed for the first time to generate the task review result, the task review result or the intermediate state of executing the repeated review task can be cached to reduce subsequent repeated calculations for the repeated review task and improve review efficiency.

[0163] In some optional implementations, the above method further includes: monitoring the server load in real time during the review process, dynamically adjusting the allocation strategy of the review task, avoiding resource overload or idleness, and improving resource utilization. Making full use of multi-core CPU and distributed computing resources, splitting the review task into multiple subtasks, processing in parallel, and reducing the total processing time. Using message queue (such as RabbitMQ) technology to achieve asynchronous processing and load balancing of tasks, and improving the throughput and response speed of the bid evaluation system.

[0164] The intelligent assisted bid evaluation method provided by the embodiment of the present invention caches the task evaluation results corresponding to the repeated evaluation tasks to avoid repeated execution of the repeated evaluation tasks, thereby saving evaluation time and further improving the evaluation efficiency.

[0165] In some optional implementations, the above method further includes:

[0166] Step g1, obtaining a review object database, wherein the review object database includes at least one document review object.

[0167] Step g2, extracting the document review objects from the review object database to obtain at least one target review object.

[0168] Step g3, counting the recommendation data generated for each target review object, and determining the target responsible object from at least one target review object.

[0169] The review object database is a database that stores reviewers in various fields. Review objects are reviewers used to review target bidding documents. Before reviewing the target bidding documents, review objects in the relevant fields are randomly selected from the review object database as reviewers for the field in which the target bidding documents are located. The selected review objects are manually screened to screen out review objects that have a relationship with the units corresponding to the target bidding documents. For the review object's recusation application and confirmation, the bid evaluation system can automatically save the data and archive it for future reference.

[0170] Each review object can select a target responsible object for the current review task, so that the review results generated for the target bidding documents can be sent to the target responsible object for verification. Specifically, the recommendation of the target responsible object can be carried out by online voting, so that each review object has the opportunity to participate in the decision-making of the target responsible object. After the voting is completed, the bid evaluation system can automatically count the recommendation data generated by each review object, determine the target responsible object of the current review task based on the recommendation data, and announce the recommendation results of the target responsible object to each review object. The bid evaluation system can archive the recommendation data generated by the entire recommendation process for future reference.

[0171] The intelligent assisted bid evaluation method provided in this embodiment extracts target evaluation objects and recommends target responsible objects so as to supervise the evaluation results and ensure the credibility and rationality of the evaluation results.

[0172] As a specific application example of an embodiment of the present invention, the above-mentioned intelligent assisted bid evaluation method is described in combination with the bidding application scenario of subway construction. Specifically, the application scenario is set as the bidding for the design and construction of Metro Line X. After the public resource trading center announces it, each construction unit prepares a bid document to bid. The bid evaluation system calls the review service to calculate the review results based on a series of business rules and the calculation rule engine corresponding to the review service. The target responsible person of the review can then select qualified bidding units based on the review results.

[0173] The specific implementation of the intelligent assisted bid evaluation method is as follows:

[0174] (1) Configuration of bidding document review rules: 1) The bidding unit has a valid safety production license; 2) The business license, safety production license, and enterprise qualifications in the bidding documents must be consistent; 3) Neither the bidder nor the enterprise has been included in the blacklist or the defaulter.

[0175] (2) The user or bid evaluation system administrator enters the dictionary and parameter information.

[0176] (3) According to the requirements of the bidding document review rules, new atomic rules are added (such as the name of the safety production license is consistent and the safety production license is within the validity period), and the parameter assembly interface is implemented.

[0177] (4) Based on the combination of atomic rules, new business rules (such as having a valid safety production license) are added for use by the bid preparation system and the bid evaluation system.

[0178] Among them, the bid preparation system is used to prepare bidding documents, set bidding requirements, and reference the business rules in the rule base corresponding to the review service. Multiple business rules are combined into a bidding document review rule, and the structured data is generated into an XML file, and finally the bidding document to be reviewed is generated. The bidding document is uploaded to the transaction system for download by the bidding tool and bid opening and evaluation.

[0179] Among them, the bidding tool is used by each bidding unit to prepare bidding documents based on the bidding documents, respond to the bidding requirements, generate XML files from structured data, and finally generate bidding documents to be reviewed. The bidding documents are uploaded to the trading system for downloading and evaluation.

[0180] (5) The bid evaluation system synchronizes the evaluable bidding documents, analyzes the bidding documents, and stores the bidding documents in the database after verification.

[0181] (6) Synchronize the review object information, form a review team, and recommend target responsible persons.

[0182] (7) Start the bid evaluation process. Specifically, the bid evaluation system asynchronously calls the review service to create a document review task. The review service can preload the calculation rule engine, parse the rule expression corresponding to the bidding document review rule, and convert the rule expression into an executable syntax tree.

[0183] (8) Recursively execute the atomic rules (the name of the safety production license is consistent and the safety production license is within the validity period) under the business rules (having a valid safety production license) of the syntax tree, and combine the execution results of the two atomic rules into a new rule. The result of the execution calculation is the business rule value. And so on, the execution of the entire syntax tree is the final evaluation result value.

[0184] (9) Combine and execute multiple business rules, combine the results into a new rule, and execute the calculation again.

[0185] (10) The evaluation results are returned to the bid evaluation system that calls the evaluation service.

[0186] (11) Input and summary of review results. Specifically, the review object reviews the bidding and tendering documents, compares the documents with the review results, and adopts the results if it agrees. The review results can also be adjusted based on its review opinions.

[0187] (12) The bid evaluation system assists the target responsible party to summarize the scores of each evaluation object and calculate the final evaluation result. An example of the evaluation result is as follows: Assuming that five bidders have submitted bid documents, the calculation rule engine of the evaluation service determines that four bidders meet all the rules in the bidding document evaluation rules. The evaluation team can then give the final evaluation result based on the evaluation results of the evaluation service, and the bid evaluation system makes the evaluation conclusion based on the summary results.

[0188] In this embodiment, an intelligent assisted bid evaluation 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.

[0189] This embodiment provides an intelligent auxiliary bid evaluation device, such as Figure 6 As shown, including:

[0190] The acquisition module 401 is used to acquire the bidding document review rules and the target bidding document to be reviewed.

[0191] The parsing module 402 is used to parse the target bidding document to obtain the evaluation parameters corresponding to the target bidding document.

[0192] The review module 403 is used to review the target bidding document according to the bidding document review rules and review parameters, and generate a review result for the target bidding document.

[0193] In some optional implementations, the acquisition module 401 includes:

[0194] The parameter configuration unit is used to obtain the atomic parameters of the file review in response to the rule parameter configuration operation for the file review.

[0195] The atomic rule configuration unit is used to obtain the atomic rule of the file review in response to the first rule configuration operation based on the atomic parameter.

[0196] The business rule configuration unit is used to obtain the business rule of the document review in response to the second rule configuration operation based on the atomic rule.

[0197] In some optional implementations, the atomic rule configuration unit includes:

[0198] The comparison dimension configuration subunit is used to determine the target comparison dimension of the atomic rule in response to the configuration operation of the comparison dimension of the atomic rule.

[0199] The comparison mode configuration subunit is used to determine the target comparison mode of the atomic rule in response to the configuration operation of the comparison mode of the atomic rule.

[0200] In some optional implementations, the acquisition module 401 further includes:

[0201] The document acquisition unit is used to acquire the initial bidding documents to be reviewed.

[0202] The document structuring unit is used to structure the initial bidding documents to be reviewed and generate target bidding documents to be reviewed.

[0203] In some optional embodiments, the above device further includes:

[0204] The review request acquisition unit is used to obtain a review request for a bidding document, wherein the review request for the bidding document carries first signature information, and the first signature information is generated based on a preset signature method.

[0205] The decryption unit is used to decrypt the signature information to obtain decrypted data, and sign the decrypted data according to a preset signature method to generate second signature information.

[0206] The signature comparison unit is used to issue the review authority to the initiator of the bidding document review request if the first signature information and the second signature information are consistent.

[0207] In some optional implementations, the review module 403 includes:

[0208] The rule conversion unit is used to obtain the rule expression corresponding to the bidding document review rule and convert the rule expression into a syntax tree.

[0209] The recursive review unit is used to recursively review the target bidding document according to the review parameters based on the recursive structure of the syntax tree, and generate the review result corresponding to the target bidding document.

[0210] In some optional implementations, the recursive review unit includes:

[0211] The display subunit is used to visually display the review results of the target bidding documents in the review interface.

[0212] The result entry subunit is used to enter the review result into the review interface in response to a confirmation operation on the review result.

[0213] The summary subunit is used to summarize the evaluation results and generate the evaluation results corresponding to the target bidding documents.

[0214] In some optional embodiments, the above device further includes:

[0215] The similarity determination module is used to compare various target bidding documents and determine the similarities between different target bidding documents.

[0216] The positioning module is used to locate similar contents of different target bidding documents based on similarity.

[0217] In some optional embodiments, the above device further includes:

[0218] The priority acquisition module is used to obtain the review priority of the target bidding document.

[0219] The priority review module is used to review the target bidding documents according to the review priority.

[0220] In some optional embodiments, the above device further includes:

[0221] The repeated identification module is used to obtain repeated review tasks in the review process of the target bidding documents.

[0222] The cache module is used to cache the task review results corresponding to the repeated review task when the repeated review task is executed for the first time.

[0223] In some optional embodiments, the above device further includes:

[0224] The object query module is used to obtain a review object database, which includes at least one document review object.

[0225] The object extraction module is used to extract the file review object from the review object database to obtain at least one target review object.

[0226] The object recommendation module is used to count the recommendation data generated for each target review object and determine the target responsible object from at least one target review object.

[0227] 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.

[0228] The intelligent assisted bid evaluation 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.

[0229] The intelligent assisted bid evaluation device provided in this embodiment analyzes the target bidding document to determine its corresponding evaluation parameters, and evaluates the target bidding document according to the evaluation parameters and the bidding document evaluation rules set based on actual needs to obtain the corresponding evaluation results. As a result, the target bidding document can be automatically evaluated without the need for the evaluation personnel to read a large number of original bid documents, reducing the error rate of the evaluation object, and at the same time, the bid evaluation process can be completed in a shorter time, thereby improving the evaluation efficiency and evaluation accuracy of the bidding document.

[0230] The embodiment of the present invention also provides a computer device having the above Figure 6 The intelligent assisted bid evaluation device shown.

[0231] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 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 7 A processor 10 is taken as an example.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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 7 The example of connecting through bus is taken in the following.

[0237] 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.

[0238] The computer device also includes a communication interface, which is used for the computer device to communicate with other devices or a communication network.

[0239] 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.

[0240] A part of the present disclosure 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 disclosure through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a 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 can be any available computer-readable storage medium or communication medium accessible to the computer.

[0241] 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 assisted bid evaluation method, characterized in that: The method comprises: Obtain the bidding document review rules and the target bidding documents to be reviewed; Parsing the target bidding document to obtain evaluation parameters corresponding to the target bidding document; The target bidding document is reviewed according to the bidding document review rules and the review parameters, and a review result for the target bidding document is generated.

2. The method according to claim 1, characterized in that Obtain the bidding document review rules, including: In response to the rule parameter configuration operation for the document review, obtaining the atomic parameters of the document review; In response to a first rule configuration operation based on the atomic parameter, obtaining an atomic rule for document review; In response to a second rule configuration operation based on the atomic rule, a business rule for document review is obtained; The bidding document review rules include the atomic rules and the business rules.

3. The method according to claim 2, characterized in that Also includes: In response to a configuration operation on the comparison dimension of the atomic rule, determining a target comparison dimension of the atomic rule; and / or, In response to the configuration operation for the comparison mode of the atomic rule, a target comparison mode of the atomic rule is determined.

4. The method according to claim 1, characterized in that: Obtain the target bidding documents to be reviewed, including: Obtain the initial bidding documents to be reviewed; The initial bidding document to be reviewed is structured to generate the target bidding document to be reviewed.

5. The method according to any one of claims 1 to 4, characterized in that: Before obtaining the bidding document review rules and the target bidding document to be reviewed, it also includes: Obtaining a bidding document review request, wherein the bidding document review request carries first signature information, and the first signature information is generated based on a preset signature method; Decrypting the signature information to obtain decrypted data, and signing the decrypted data according to the preset signature method to generate second signature information; If the first signature information and the second signature information are consistent, the review authority is issued to the initiator of the bidding document review request.

6. The method according to claim 1, characterized in that The step of reviewing the target bidding document according to the bidding document review rules and the review parameters to generate a review result for the target bidding document includes: Obtaining a regular expression corresponding to the bidding document review rule, and converting the regular expression into a syntax tree; Based on the recursive structure of the syntax tree, the target bidding document is recursively reviewed according to the review parameters to generate a review result corresponding to the target bidding document.

7. The method according to claim 6, characterized in that The generating of the evaluation result corresponding to the target bidding document includes: The review results of the target bidding documents are visually displayed in the review interface; In response to a confirmation operation on the review result, entering the review result into the review interface; The review results are summarized and verified to generate review results corresponding to the target bidding documents.

8. The method according to claim 6 or 7, characterized in that: Also includes: Comparing each of the target bidding documents to determine the similarity between different target bidding documents; Based on the similarity, similar contents of different target bidding documents are located.

9. The method according to claim 1, characterized in that: Also includes: Obtaining the review priority of the target bidding document; The target bidding documents are reviewed according to the review priority.

10. The method according to claim 1, characterized in that Also includes: Obtaining repeated review tasks in the review process of the target bidding document; When the repeated review task is executed for the first time, the task review result corresponding to the repeated review task is cached.

11. The method according to claim 1, characterized in that: Also includes: Acquire a review object database, wherein the review object database includes at least one document review object; Extracting the document review object from the review object database to obtain at least one target review object; The recommendation data generated for each of the target review objects is counted, and a target responsible object is determined from the at least one target review object.

12. An intelligent auxiliary bid evaluation device, characterized in that: The device comprises: An acquisition module is used to acquire the bidding document review rules and the target bidding document to be reviewed; A parsing module, used to parse the target bidding document to obtain the evaluation parameters corresponding to the target bidding document; The review module is used to review the target bidding document according to the bidding document review rules and the review parameters, and generate a review result for the target bidding document.

13. 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 assisted bid evaluation method according to any one of claims 1 to 11 by executing the computer instructions.

14. 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 assisted bid evaluation method according to any one of claims 1 to 11.

15. A computer program product, characterized in that It includes computer instructions, which are used to enable a computer to execute the intelligent assisted bid evaluation method described in any one of claims 1 to 11.

Images