Intelligent auxiliary review method and system based on standardization rule, medium and equipment

Abstract

The invention discloses an intelligent auxiliary review method and system based on a standardized rule, a medium and equipment, and the method comprises the steps: constructing a rule configuration model, selecting an applicable rule configuration model according to the content of review terms, and setting a corresponding review rule according to the selected rule configuration model. Integrating the set review rules into a purchase file, then automatically extracting response data of a bidder for the structured data editing item, generating score calculation rules corresponding to the review rules through score calculation processing logic corresponding to each rule configuration model pre-deployed on the review system, and performing review on the review rules according to the score calculation rules. And then carrying out combined operation on the extracted response data based on a score calculation rule, and automatically generating a pre-review conclusion and an auxiliary reference score. According to the scheme, review personnel can be assisted to quickly and efficiently complete review work, and the review work efficiency and quality are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of automatic review of tender documents, and particularly to an intelligent auxiliary review method, system, medium and device based on standardized rules. Background Art

[0002] With the development of computer network technology, the application of network technology in the field of electronic tendering and bidding is becoming more and more extensive. People can complete the entire tendering and bidding process through computers and networks, including various procurement execution processes such as online tender preparation, bidding, bid opening, bid evaluation, and bid determination.

[0003] Currently, the bid evaluation link in electronic tendering and bidding is mainly divided into two stages: preliminary review and detailed review. In the preliminary review stage, the reviewers review the response content in the bidders' tender documents according to the review terms requirements in the procurement documents to determine whether they are eligible to enter the detailed review stage. In the detailed review stage, the reviewers conduct specific scoring on the bidders' tender documents that enter the detailed review stage in terms of technology, commerce, price, etc. according to the review terms and their corresponding scoring rules in the procurement documents, and the scoring results will directly affect the winning result of the procurement project.

[0004] In the existing field of electronic tendering and bidding, when conducting the review work, the traditional manual scoring method is still adopted. The reviewers mainly check the corresponding response content in the bidders' tender documents according to the review terms requirements in the procurement documents, and perform offline manual calculations according to the scoring rules of the corresponding review terms and then fill in and input the scoring results. Adopting the manual review method requires the reviewers to fully understand the calculation logic of the scoring rules, and there are tasks such as horizontal comparison of response content and calculation of review scores, which not only consumes labor costs, but also cannot effectively guarantee the accuracy of the scoring results. Summary of the Invention

[0005] In view of the above problems, the present invention provides a technical solution for intelligent auxiliary review based on standardized rules to solve the problems of large workload, low efficiency, and poor accuracy in the existing review method of tender documents.

[0006] To solve the above problems, in the first aspect, the present application provides an intelligent auxiliary review method based on standardized rules, and the method includes:

[0007] Pre-establish a rule configuration model library, which contains a variety of rule configuration models;

[0008] Select the applicable rule configuration model from the rule configuration model library according to the review term content requirements, and set the corresponding review rules according to the selected rule configuration model, and integrate the set review rules into the procurement documents;

[0009] Automatically obtain the evaluation rules in the procurement document, and generate corresponding structured data editing items according to the obtained evaluation rule requirements;

[0010] Receive the response data of each bidder for the structured data editing items, verify the response data according to the response specifications of the current evaluation rules, extract the response data in the bid documents of each bidder after the verification passes, store the extracted response data in the bid documents and perform encryption processing, and upload the encrypted bid documents to the evaluation system;

[0011] The evaluation system pre-deploys the score calculation processing logic corresponding to each rule configuration model. When starting the evaluation of the procurement project, the evaluation system automatically obtains the evaluation rules set in the procurement document and the corresponding rule configuration model adopted, and matches them with the score calculation processing logic corresponding to the rule configuration model to determine the score calculation rules corresponding to each evaluation rule in the current procurement document;

[0012] After the evaluation system performs combined operations on the response data in the bid documents of the bidders extracted according to the score calculation rules corresponding to each evaluation rule, it automatically generates a preliminary evaluation conclusion and auxiliary reference scores.

[0013] Further, the method includes:

[0014] Receive the operation instructions of the evaluation personnel for the preliminary evaluation conclusion and the auxiliary reference scores, and execute the operations corresponding to the operation instructions. The operation instructions include any one of a confirmation instruction, a modification instruction, and an editing instruction;

[0015] When the operation instruction is an editing instruction, the method includes:

[0016] Receive the determination conclusion text of the evaluation personnel for the preliminary evaluation conclusion and the auxiliary reference scores, and automatically correct the response data in the bid documents of the bidders according to the determination conclusion text;

[0017] After performing combined operations on the corrected response data again according to the score calculation rules corresponding to each evaluation rule, output the corrected preliminary evaluation conclusion and the corrected auxiliary reference scores.

[0018] Further, the method includes:

[0019] When receiving the confirmation instruction of the evaluation personnel for the preliminary evaluation conclusion and the auxiliary reference scores, calculate the first hash value according to the confirmed preliminary evaluation conclusion, auxiliary reference scores, evaluation opinions, signatures of the evaluation personnel, and evaluation confirmation time;

[0020] Pack the calculated first hash value and the confirmed content into a transaction record, and after verification by nodes, add it to the blockchain to form an immutable review result record.

[0021] Further, the method includes:

[0022] After the review rules are determined, perform a hash calculation on the first metadata to obtain a second hash value, and pack the first metadata and the second hash value together into a transaction record of the blockchain. After verification by each node, write it into the blockchain. The first metadata includes the content of the review rules, the time when the review rules are formulated, and the identity identification information of the personnel who formulate the review rules;

[0023] And / or, before uploading the encrypted bid documents to the review system, the method includes: perform a hash calculation on the second metadata to obtain a third hash value, and pack the second metadata and the third hash value together into a transaction record of the blockchain. After verification by each node, write it into the blockchain. The second metadata includes the encrypted bid documents, the upload time of the bid documents, and the identity information of the bidders;

[0024] If the bid documents are modified, generate new hash values for the content of each modified bid document, the revision time, and the reviser, and record the modified metadata and the new hash values on the chain.

[0025] Further, the method includes:

[0026] Receive an objection feedback instruction for the winning bid result. The objection feedback instruction includes bidder information and objection content information;

[0027] According to the bidder information, obtain the relevant data stored by the bidder on the blockchain from the blockchain, and parse the relevant data to restore the modification process and review process of the current bidder's bid documents in chronological order;

[0028] Input the objection content information, the modification process and review process of the bid documents into a large model to obtain an objection feedback result for the objection content information, and send the objection feedback result to the bidder.

[0029] Further, obtaining the relevant data stored by the bidder on the blockchain according to the bidder information includes:

[0030] Perform semantic analysis on the objection content information to obtain the objection appeal information of the bidder;

[0031] Determine the time interval range of the relevant data that needs to be obtained from the blockchain according to the objection requirement information, and obtain all the relevant data uploaded by the bidder on the blockchain within the time interval range stored by the bidder on the blockchain according to the bidder information.

[0032] In a second aspect, the present application provides an intelligent assisted review system based on standardized rules. The system includes:

[0033] A model configuration module, configured to pre-establish a rule configuration model library, and the rule configuration model library contains multiple rule configuration models;

[0034] A review rule setting module, configured to select the applicable rule configuration model from the rule configuration model library according to the content requirements of the review terms, set the corresponding review rules according to the selected rule configuration model, and integrate the set review rules into the procurement document;

[0035] An edit item generation module, configured to automatically obtain the review rules in the procurement document and generate corresponding structured data edit items according to the obtained review rule requirements;

[0036] A response data parsing module, configured to receive the response data of each bidder for the structured data edit item, verify the response data according to the response specification of the current review rule, extract the response data in the bid documents of each bidder after passing the verification, store the extracted response data in the bid document and perform encryption processing, and upload the encrypted bid document to the review system;

[0037] An assisted review module, including a review system, the review system is configured to pre-deploy the score calculation processing logic corresponding to each rule configuration model. When starting the review of the procurement project, the review system is further configured to automatically obtain the review rules set in the procurement document and the corresponding rule configuration model adopted, and match with the score calculation processing logic corresponding to the rule configuration model to determine the score calculation rules corresponding to each review rule in the current procurement document;

[0038] The review system is further configured to perform combined operations on the response data in the bid documents of the extracted bidders respectively according to the score calculation rules corresponding to each review rule, and automatically generate a preliminary review conclusion and an auxiliary reference score.

[0039] Further, the rule configuration model includes any one or more of a judgment calculation model, a matching item calculation model, an addition and subtraction item calculation model, a ranking increasing or decreasing calculation model, and a ranking increasing or decreasing calculation model based on the review amount as a benchmark.

[0040] In a third aspect, the present invention further provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described in the first aspect is implemented.

[0041] In a fourth aspect, the present invention further provides an electronic device, including a memory and a processor, where the memory is used to store one or more computer program instructions, and wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0042] Different from the prior art, the above solution provides an intelligent assisted review method, system, medium and device based on standardized rules. This method constructs a rule configuration model, selects the applicable rule configuration model according to the content of the review terms, sets the corresponding review rules according to the selected rule configuration model, integrates the set review rules into the procurement document, then automatically extracts the response data of the bidder for the structured data editing items, and generates the score calculation rules corresponding to each review rule through the score calculation processing logic corresponding to each rule configuration model pre-deployed on the review system, and then performs a combined operation on the extracted response data based on the score calculation rules to automatically generate a preliminary review conclusion and an auxiliary reference score. The above solution can assist the review personnel to complete the review work quickly and efficiently, and effectively improve the efficiency and quality of the review work.

[0043] The above relevant records of the invention content are only an overview of the technical solution of the present invention. In order to enable those of ordinary skill in the art to more clearly understand the technical solution of the present invention, and then can be implemented according to the content recorded in the description and the drawings, and in order to make the above objects, other objects, features and advantages of the present invention more easily understood, the following is described in conjunction with the specific embodiments and drawings of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings are only used to illustrate the principles, implementation methods, applications, features and effects of the specific embodiments of the present invention and other related contents, and should not be considered as a limitation to the present invention.

[0045] In the accompanying drawings of the specification:

[0046] Figure 1 is a flowchart of an intelligent assisted review method based on standardized rules according to the first exemplary embodiment of the present invention;

[0047] Figure 2 is a flowchart of an intelligent assisted review method based on standardized rules according to the second exemplary embodiment of the present invention;

[0048] Figure 3Flowchart of the intelligent assisted review method based on standardization rules according to the third exemplary embodiment of the present invention;

[0049] Figure 4 Flowchart of the intelligent assisted review method based on standardization rules according to the fourth exemplary embodiment of the present invention;

[0050] Figure 5 Flowchart of the intelligent assisted review method based on standardization rules according to the fifth exemplary embodiment of the present invention;

[0051] Figure 6 Schematic diagram of the modules of the intelligent assisted review system based on standardization rules according to an exemplary embodiment of the present invention;

[0052] Figure 7 Schematic diagram of the modules of the electronic device related to the present invention;

[0053] The descriptions of the reference numerals involved in the above respective drawings are as follows:

[0054] 10. Electronic device;

[0055] 101. Processor;

[0056] 102. Storage medium.

[0057] 20. Intelligent assisted review system based on standardization rules;

[0058] 201. Model configuration module;

[0059] 202. Review rule setting module;

[0060] 203. Edit item generation module;

[0061] 204. Response data parsing module;

[0062] 205. Assisted review module;

[0063] 2051. Review system. Detailed implementation manners

[0064] To describe in detail the possible application scenarios, technical principles, specific implementable solutions, achievable objectives and effects, etc. of the present invention, the following is described in detail in conjunction with the specific embodiments listed and the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present invention, and thus are only examples and cannot be used to limit the protection scope of the present invention.

[0065] As used herein, the term "embodiment" means that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present invention. The term "embodiment" appearing at various positions in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or relevance to other embodiments. In principle, in the present invention, as long as there is no technical contradiction or conflict, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.

[0066] Unless otherwise defined, the meanings of the technical terms used herein are the same as those commonly understood by those skilled in the technical field to which the present invention pertains; the use of the relevant terms herein is only for describing specific embodiments and is not intended to limit the present invention.

[0067] In the description of the present invention, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: the existence of A, the existence of B, and the simultaneous existence of both A and B. Additionally, the character " / " in this text generally represents an "or" logical relationship between the associated objects before and after.

[0068] In the present invention, terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantitative, primary-secondary, or sequential relationships between these entities or operations.

[0069] Without further limitation, in the present invention, the open-ended expressions such as "comprising", "including", "having", or other similar expressions used in a statement are intended to cover non-exclusive inclusion. These expressions do not exclude the possibility that there may be additional elements in the process, method, or product including the stated elements, such that the process, method, or product including a series of elements may not only include those defined elements, but also include other elements not explicitly listed, or elements inherent to such process, method, or product.

[0070] In the present invention, expressions such as "greater than", "less than", "exceeding", etc. are understood not to include the recited number; expressions such as "above", "below", "within", etc. are understood to include the recited number. In addition, in the description of the embodiments of the present invention, the meaning of "multiple" is two or more (including two), and similar expressions related to "many", such as "multiple groups", "multiple times", etc., are understood in the same way, unless otherwise specifically defined.

[0071] In a first aspect, as Figure 1 shown, the present application provides an intelligent assisted review method based on standardized rules, and the method includes:

[0072] Step S101: Pre - establish a rule configuration model library;

[0073] Step S102: Select the applicable rule configuration model from the rule configuration model library according to the content requirements of the review terms, set the corresponding review rules according to the selected rule configuration model, and integrate the set review rules into the procurement document;

[0074] Step S103: Automatically obtain the review rules in the procurement document, and generate corresponding structured data editing items according to the requirements of the obtained review rules;

[0075] Step S104: Receive the response data of each bidder for the structured data editing items, verify the response data according to the response specifications of the current review rules, extract the response data in the bid documents of each bidder after the verification passes, store the extracted response data in the bid documents and perform encryption processing, and upload the encrypted bid documents to the review system;

[0076] Step S105: The review system pre - deploys the score calculation processing logic corresponding to each rule configuration model. When starting the procurement project review, the review system automatically obtains the review rules set in the procurement document and the corresponding rule configuration model adopted, and matches them with the score calculation processing logic corresponding to the rule configuration model to determine the score calculation rules corresponding to each review rule in the current procurement document;

[0077] Step S106: The review system performs combined operations on the response data in the bid documents of the bidders extracted according to the score calculation rules corresponding to each review rule, and automatically generates a preliminary review conclusion and auxiliary reference scores.

[0078] In step S101, the rule configuration model library contains multiple rule configuration models. Different rule configuration models can be applicable to the requirements of different review scenarios. The setting items of the rule configuration model include but are not limited to: review index content, review parameters, plus - minus score sorting type, enumeration type, standard score, maximum score, minimum score, score per unit, benchmark amount, score difference, digital operators, and amount units, etc., and can be freely combined according to different model types.

[0079] After analyzing, summarizing, and sorting out the scoring rules of the review terms for procurement projects, this application focuses on extracting and forming key model parameters, including but not limited to: review index content, review parameters, benchmark amounts, digital operators, etc. Then, through the combination of various model parameters, a clear standard operation model is provided to users. Through unified calculation methods and rules, it is ensured that the results obtained by different users in the same calculation are consistent, guaranteeing the accuracy and reliability of the calculation results. Each user can not only intuitively view the composition and operation logic of the model but also adjust and combine different rule configuration models according to actual demands to enhance the applicable scenarios.

[0080] For example, the matching item calculation model directly provided by this application clarifies the review index content X and the corresponding score Y. Users can customize and set the review indexes X1, X2, X3... and the corresponding scores Y1, Y2, Y3.... Bidders (suppliers) can obtain the corresponding review scores for the review indexes they respond to, which is simple and clear.

[0081] Generally, a review term contains two key parts: review calculation rules and calculation formulas. The final score result of the supplier is jointly determined by these two parts. However, only the review calculation rules can be seen from the review term, and the calculation formula cannot be visualized. At the same time, the weights, conditions, and priorities in the rules will also affect the design of the formula.

[0082] For example, the content of the review term is "Review and score according to the average asset-liability ratio of the supplier in the past five years. If the average liability ratio of the supplier in the past five years is less than 35%, the score is 2 points. For the remaining suppliers, the scores are sorted from low to high according to the liability ratio, and 0.1 point is deducted successively, with the lowest score being 0 points". The following information can be obtained from this review term content:

[0083] 1. Factors determining the score:

[0084] ① The highest score (i.e., the base score) is 2 points, and the lowest score is 0 points.

[0085] ② If the average liability ratio in the past five years is less than 35%, the score is 2 points.

[0086] ③ If the average liability ratio in the past five years is greater than or equal to 35%, sort according to the liability ratio from low to high, and 0.1 point is deducted successively (i.e., the ranking deduction weight).

[0087] 2. Judgment condition rules:

[0088] ① The highest priority is to judge whether the average liability ratio of the supplier in the past five years is less than 35%.

[0089] ② The second highest priority is to judge whether the average liability ratio of the supplier in the past five years is greater than or equal to 35%.

[0090] 3. Calculation rules:

[0091] ① When the highest priority condition is met, the supplier gets 2 points.

[0092] ② When the second-highest priority condition is met, first sort the debt ratios of the suppliers from low to high to form a debt ratio ranking RN, and then calculate the score. Finally, the supplier gets 2 - Rn × 0.1 points.

[0093] 4. Calculation formula

[0094] ① When the supplier's debt ratio value < 35%, the score = basic score.

[0095] ② When the supplier's debt ratio value ≥ 35%, the score = basic score - (ranking × ranking deduction weight).

[0096] According to the above example, after extracting relevant variables, mathematical symbols, and operators, a "calculation model for increasing or decreasing the benchmark ranking of the review amount" is formed, and the following rule setting parameters are provided: type of addition or subtraction score (plus / minus), whether there is a benchmark amount (yes / no), benchmark amount, relationship with the benchmark amount (greater than or equal to / less than or equal to), relationship score (highest score / lowest score), highest score, lowest score, score difference and unit. And to meet the diverse changes in review terms, it supports users to adjust the combination by themselves, and the following changes can be formed:

[0097] 1. Type of addition or subtraction score (plus), whether there is a benchmark amount (no), highest score, lowest score, score difference, unit.

[0098] 2. Type of addition or subtraction score (minus), whether there is a benchmark amount (no), highest score, lowest score, score difference, unit.

[0099] 3. Type of addition or subtraction score (plus), whether there is a benchmark amount (yes), benchmark amount, relationship with the benchmark amount (greater than or equal to), relationship score (highest score), highest score, lowest score, score difference, unit.

[0100] 4. Type of addition or subtraction score (plus), whether there is a benchmark amount (yes), benchmark amount, relationship with the benchmark amount (less than or equal to), relationship score (lowest score), highest score, lowest score, score difference, unit.

[0101] 5. Type of addition or subtraction score (minus), whether there is a benchmark amount (yes), benchmark amount, relationship with the benchmark amount (greater than or equal to), relationship score (lowest score), highest score, lowest score, score difference, unit.

[0102] 6. Type of addition or subtraction score (minus), whether there is a benchmark amount (yes), benchmark amount, relationship with the benchmark amount (less than or equal to), relationship score (highest score), highest score, lowest score, score difference, unit.

[0103] The differences between different rule configuration models lie in the different scoring rules applicable to the review terms, which are as follows:

[0104] 1. If the review terms require judging whether the content of the supplier's response meets a certain indicator, the "judgment calculation model" can be used. Example: If the supplier has not had any contract violations in government procurement activities in the past three years, the supplier gets 2 points; otherwise, 0 points.

[0105] 2. If the review terms specify clear review indicators and the supplier's response content matches the indicators, corresponding scores can be obtained, and the "configuration item calculation model" can be used. Example: If the supplier has obtained the "Contract-abiding and Creditworthy" enterprise certificate issued by the Market Supervision and Administration Bureau in the past three years, 2 points are obtained for the certificate issued by the provincial Market Supervision and Administration Bureau, 1 point for the certificate issued by the municipal Market Supervision and Administration Bureau, and 0 points otherwise.

[0106] 3. If the review terms specify clear review indicators and the supplier's response content matches the indicators, and the scores can be obtained according to the number of responses, the "plus-minus item calculation model" can be used. Example: For the number of times the supplier has been punished for violations in government procurement activities in the past three years, 0.5 points are deducted for each time, with a maximum deduction of 2 points.

[0107] Through this application, users can flexibly adjust and custom-select the appropriate rule configuration model to generate scoring rules according to the requirements of the procurement project. In addition to being able to intuitively display the composition and calculation logic of the scoring rules on the front-end page, suppliers do not need to pre-maintain various bid data. They only need to respond according to the scoring rules when making a bid response, which improves timeliness and reduces the bid cost of suppliers. This method is applicable in various industries and fields of bidding and tendering.

[0108] The above solution sets the standardized review rules by establishing a rule configuration model, and combines with an intelligent auxiliary review system to assist the review personnel to complete the review work quickly and efficiently, effectively improving the efficiency and quality of the review work. At the same time, through intelligent auxiliary review, the requirements for the review experts to understand the calculation logic of the scoring rules are reduced, the time for horizontally comparing the response data of bidders and the workload of manually calculating scores are reduced, thereby shortening the review work duration of the review personnel and effectively reducing the consumption of review resources.

[0109] In some embodiments, the method includes:

[0110] Receiving an operation instruction from the review personnel for the pre-review conclusion and the auxiliary reference score, and performing the operation corresponding to the operation instruction, where the operation instruction includes any one of a confirmation instruction, a modification instruction, and an editing instruction;

[0111] When the operation instruction is an editing instruction, such asFigure 2 As shown, the method includes:

[0112] Step S201: Receive the conclusion text of the reviewer regarding the preliminary review conclusion and the auxiliary reference score, and automatically correct the response data in the bid document of the bidder according to the conclusion text.

[0113] Step S202: After recombining and calculating the corrected response data according to the score calculation rules corresponding to each review rule, output the corrected preliminary review conclusion and the corrected auxiliary reference score.

[0114] In short, after the review system outputs the preliminary review conclusion and the auxiliary reference score, the reviewer can perform operations such as confirmation, modification, and editing on the output preliminary review conclusion and auxiliary reference score. When the reviewer has doubts about the preliminary review score result, they can input the conclusion determined by the reviewer (the conclusion may include the numerical value of the corrected response data), and then automatically correct the response data in the bid document of the bidder by parsing the content in the reviewer's conclusion, and input the corrected response data into the review system for re-calculation to output the corrected preliminary review conclusion and the corrected auxiliary reference score. Through this method, it is possible to perform a secondary verification on the review result and improve the accuracy of the final review result.

[0115] In some embodiments, as Figure 3 shown, the method includes:

[0116] Step S301: When receiving the confirmation instruction of the reviewer regarding the preliminary review conclusion and the auxiliary reference score, calculate the first hash value according to the confirmed preliminary review conclusion, auxiliary reference score, review opinion, reviewer's signature, and review confirmation time.

[0117] Step S302: Package the calculated first hash value and the confirmed content into a transaction record, and add it to the blockchain after being verified by the node to form an immutable review result record.

[0118] In short, after the final confirmation of each review result, by generating a hash value from the confirmed review conclusion, auxiliary reference score, review opinion, reviewer's signature, and review confirmation time, and storing the hash value and metadata on the chain, it is possible to improve the immutability of the review conclusion and facilitate traceability during subsequent investigations.

[0119] In some embodiments, the method includes:

[0120] After the review rules are determined, a hash calculation is performed on the first metadata to obtain a second hash value. The first metadata and the second hash value are packaged together into a transaction record of the blockchain and written into the blockchain after being verified by each node. The first metadata includes the content of the review rules, the time when the review rules are formulated, and the identity information of the personnel who formulate the review rules;

[0121] And / or, before uploading the encrypted bid documents to the review system, the method includes: performing a hash calculation on the second metadata to obtain a third hash value, packaging the second metadata and the third hash value together into a transaction record of the blockchain, and writing it into the blockchain after being verified by each node. The second metadata includes the encrypted bid documents, the upload time of the bid documents, and the identity information of the bidder;

[0122] If the bid document is modified, new hash values will be generated for the content of the modified bid document each time, the revision time, and the reviser, and the modified metadata and the new hash values will be recorded on the chain.

[0123] In short, after the review rules are confirmed and / or after the bid documents are generated, hash values can be calculated according to the corresponding metadata, and the hash values and the corresponding metadata are stored on the chain to form immutable relevant data. If the content of the relevant data is adjusted, new hash values will be generated according to the content of each modification, and the new hash values and the metadata to be modified will be stored on the chain to facilitate subsequent tracing of the modification history of each data.

[0124] In some embodiments, as Figure 4 shown, the method includes:

[0125] Step S401: Receive an objection feedback instruction to the winning bid result. The objection feedback instruction includes bidder information and objection content information;

[0126] Step S402: Obtain the relevant data stored by the bidder on the blockchain from the blockchain according to the bidder information, and parse the relevant data to restore the modification process and review process of the current bidder's bid documents this time in chronological order;

[0127] Step S403: Input the objection content information, the modification process and review process of the bid documents into the large model to obtain an objection feedback result for the objection content information, and send the objection feedback result to the bidder.

[0128] In short, when a bidder has an objection to the evaluation conclusion of himself or others, an objection feedback instruction can be initiated. The objection feedback instruction contains the information of the bidder being objected to and the information of the objection content. After receiving the objection feedback instruction, relevant data can be obtained from the blockchain to restore the evaluation process of the bidder's tender document being objected to. Then, based on the evaluation process, an objection feedback result is generated and sent to the bidder who initiated the objection. By establishing an objection feedback mechanism and combining the characteristics of the blockchain that cannot be tampered with and is convenient for tracing, the fairness and accuracy of the evaluation result can be effectively guaranteed.

[0129] In some embodiments, as Figure 5 shown, obtaining the relevant data stored by the bidder on the blockchain according to the bidder information includes:

[0130] Step S501: Perform semantic analysis on the objection content information to obtain the objection request information of the bidder;

[0131] Step S502: Determine the time interval range of the relevant data that needs to be obtained from the blockchain according to the objection requirement information, and obtain all the relevant data uploaded by the bidder on the blockchain within the time interval range according to the bidder information.

[0132] In short, during the bidding process of each bidder, a large amount of data is stored on the chain. If all data needs to be obtained every time there is an objection, the efficiency of objection response will decrease due to the large amount of data obtained. Therefore, in this embodiment, by further analyzing the objection content information, the objection request of the objection initiator is determined, and then data is obtained from the blockchain based on the objection request, which can effectively narrow the data range obtained and improve the objection feedback efficiency. For example, by analyzing the objection content information, it is found that the content objected to by the objection initiator mainly focuses on the modification process of the bidder's tender document. Then, only the tender documents modified and uploaded by the bidder being objected to need to be obtained to restore the modification process of the tender document, and after re-verification, an objection feedback conclusion is generated, and the data related to the evaluation rules part does not need to be obtained.

[0133] In a second aspect, as Figure 6 shown, the present application provides an intelligent assisted evaluation system 20 based on standardized rules. The system includes:

[0134] A model configuration module 201, configured to pre-establish a rule configuration model library, and the rule configuration model library contains a variety of rule configuration models;

[0135] The review rule setting module 202 is configured to select an applicable rule configuration model from the rule configuration model library according to the requirements of the review clause content, set corresponding review rules according to the selected rule configuration model, and integrate the set review rules into the procurement document;

[0136] The editing item generation module 203 is configured to automatically obtain the review rules in the procurement document and generate corresponding structured data editing items according to the requirements of the obtained review rules;

[0137] The response data parsing module 204 is configured to receive the response data of each bidder for the structured data editing items, verify the response data according to the response specifications of the current review rules, extract the response data in the bid documents of each bidder after passing the verification, store the extracted response data in the bid documents and perform encryption processing, and upload the encrypted bid documents to the review system;

[0138] The auxiliary review module 205 includes a review system 2051. The review system 2051 is configured to pre-deploy the score calculation processing logic corresponding to each rule configuration model. When starting the procurement project review, the review system is further configured to automatically obtain the review rules set in the procurement document and the corresponding rule configuration model adopted, and match with the score calculation processing logic corresponding to the rule configuration model to determine the score calculation rules corresponding to each review rule in the current procurement document;

[0139] The review system 2051 is further configured to perform combined operations on the response data in the bid documents of the extracted bidders respectively according to the score calculation rules corresponding to each review rule, and automatically generate a preliminary review conclusion and auxiliary reference scores.

[0140] In some embodiments, the rule configuration model includes any one or more of a judgment calculation model, a matching item calculation model, an addition and subtraction item calculation model, a ranking increasing or decreasing calculation model, and a ranking increasing or decreasing calculation model based on the review amount as a benchmark.

[0141] The present invention provides an intelligent auxiliary review method and system based on standardized review rules. By collecting the scoring rules of technical, commercial and price review clauses in the procurement documents of typical procurement projects in recent years, summarizing in combination with the content of the responses in the bid documents of bidders, and through sorting, analyzing and summarizing, rule configuration models applicable to each review scenario are sorted out, and the response data extraction rules and review methods corresponding to each rule configuration model are designed to form standardization, which can assist reviewers to complete the review work quickly and efficiently.

[0142] In a third aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the intelligent assisted review method based on standardized rules as described in the first aspect of the present invention.

[0143] Among them, the computer-readable storage medium may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory.

[0144] The non-volatile memory may be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read Only Memory), an electrically erasable programmable read-only memory (EEPROM, Electrically Erasable Programmable Read Only Memory), a ferromagnetic random access memory (FRAM, ferromagnetic random access memory), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD ROM, Compact Disc Read Only Memory); the magnetic surface memory may be a disk memory or a tape memory.

[0145] The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link dynamic random access memory (SLDRAM), direct rambus random access memory (DRRAM). The computer-readable storage medium described in embodiments of the present invention is intended to include these and any other suitable types of memory.

[0146] As Figure 7 shown, in a fourth aspect, the present invention provides an electronic device 10, including a processor 101 and a storage medium 102, where a computer program is stored on the storage medium, and when the computer program is executed by the processor, it implements the intelligent assisted review method based on standardized rules as described in the first aspect of the present invention.

[0147] In some embodiments, the processor may be implemented by software, hardware, firmware, or a combination thereof, and may use circuitry, one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), central processing units (CPUs), controllers, microcontrollers, microprocessors, etc., such that the processor can execute some steps, all steps, or any combination of the steps of the intelligent assisted review method based on standardized rules in each embodiment of the present application.

[0148] Finally, it should be noted that although the above embodiments have been described in the text and drawings of the specification of the present invention, the patent protection scope of the present invention cannot be limited thereby. Any technical solutions obtained by equivalent structure or equivalent process substitution or modification using the content recorded in the text and drawings of the specification of the present invention based on the substantial concept of the present invention, as well as those directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, etc., are all included in the patent protection scope of the present invention.

Claims

1. An intelligent assisted review method based on standardized rules, characterized in that: The method comprises: Pre-establishing a rule configuration model library, wherein the rule configuration model library contains a variety of rule configuration models; Select an applicable rule configuration model from the rule configuration model library according to the review terms and conditions, set corresponding review rules according to the selected rule configuration model, and integrate the set review rules into the procurement documents; Automatically obtain the review rules in the procurement documents and generate corresponding structured data editing items according to the obtained review rules; Receiving response data from each bidder for the structured data editing item, verifying the response data according to the response specification of the current review rule, extracting the response data from the bid document of each bidder after the verification is passed, storing the extracted response data in the bid document and encrypting it, and uploading the encrypted bid document to the review system; The review system pre-deploys the score calculation processing logic corresponding to each rule configuration model. When the procurement project review is started, the review system automatically obtains the review rules set in the procurement document and the corresponding rule configuration model, and matches them with the score calculation processing logic corresponding to the rule configuration model to determine the score calculation rules corresponding to each review rule in the current procurement document; The review system automatically generates preliminary review conclusions and auxiliary reference scores after combining the response data extracted from the bidders' bid documents according to the score calculation rules corresponding to each review rule.

2. The intelligent assisted review method based on standardized rules as claimed in claim 1, characterized in that: The method comprises: Receive an operation instruction from the reviewer regarding the preliminary review conclusion and the auxiliary reference score, and perform an operation corresponding to the operation instruction, wherein the operation instruction includes any one of a confirmation instruction, a modification instruction, and an editing instruction; When the operation instruction is an editing instruction, the method includes: Receive the reviewer's conclusion text on the preliminary review conclusion and the auxiliary reference score, and automatically correct the response data in the bidder's bid document according to the conclusion text; After recombining the revised response data according to the score calculation rules corresponding to each review rule, the revised preliminary review conclusion and the revised auxiliary reference score are output.

3. The intelligent assisted review method based on standardized rules as claimed in claim 2, characterized in that: The method comprises: When receiving a confirmation instruction from the reviewer regarding the pre-review conclusion and the auxiliary reference score, calculating a first hash value according to the confirmed pre-review conclusion, the auxiliary reference score, the review opinion, the reviewer's signature, and the review confirmation time; The calculated first hash value and the confirmed content are packaged into a transaction record, which is added to the blockchain after verification by the node to form an unalterable record of the review results.

4. The intelligent assisted review method based on standardized rules as claimed in claim 3, characterized in that: The method comprises: After the review rules are determined, the first metadata is hashed to obtain a second hash value, and the first metadata and the second hash value are packaged together into a transaction record of the blockchain, which is written into the blockchain after verification by each node. The first metadata includes the content of the review rules, the time when the review rules are formulated, and the identity information of the person who formulated the review rules; And / or, before uploading the encrypted bidding document to the review system, the method includes: performing hash calculation on the second metadata to obtain a third hash value, packaging the second metadata and the third hash value together into a transaction record of the blockchain, and writing the record into the blockchain after verification by each node, wherein the second metadata includes the encrypted bidding document, the upload time of the bidding document, and the identity information of the bidder; If the bidding document is modified, a new hash value will be generated for each modification of the bidding document content, revision time, and reviser, and the modified metadata and new hash value will be recorded on the chain.

5. The intelligent assisted review method based on standardized rules as claimed in claim 4, characterized in that: The method comprises: Receiving an objection feedback instruction on the bidding result, wherein the objection feedback instruction includes bidder information and objection content information; According to the bidder information, relevant data stored by the bidder on the blockchain is obtained from the blockchain, and the relevant data is parsed to restore the modification process and review process of the current bidder's bid document in chronological order; The objection content information, the modification process and the review process of the bidding document are input into the big model, the objection feedback result for the objection content information is obtained, and the objection feedback result is sent to the bidder.

6. The intelligent assisted review method based on standardized rules as claimed in claim 5, characterized in that: The relevant data stored on the blockchain by the bidder is obtained from the blockchain according to the bidder information, including: Perform semantic analysis on the objection content information to obtain the bidder's objection claim information; The time interval range of the relevant data that needs to be obtained from the blockchain is determined according to the objection demand information, and all relevant data stored by the bidder on the blockchain within the time interval is obtained from the blockchain according to the bidder information.

7. An intelligent assisted review system based on standardized rules, characterized in that: The system comprises: A model configuration module is used to pre-establish a rule configuration model library, wherein the rule configuration model library contains a variety of rule configuration models; An evaluation rule setting module is used to select an applicable rule configuration model from the rule configuration model library according to the evaluation terms and conditions, set corresponding evaluation rules according to the selected rule configuration model, and integrate the set evaluation rules into the procurement documents; The editing item generation module is used to automatically obtain the review rules in the procurement documents and generate corresponding structured data editing items according to the obtained review rules; A response data parsing module is used to receive the response data of each bidder for the structured data editing item, verify the response data according to the response specification of the current evaluation rule, extract the response data in the bid document of each bidder after the verification, store the extracted response data in the bid document and encrypt it, and upload the encrypted bid document to the evaluation system; The auxiliary review module includes a review system, which is used to pre-deploy the score calculation processing logic corresponding to each rule configuration model. When the procurement project review is started, the review system is also used to automatically obtain the review rules set in the procurement document and the corresponding rule configuration model, and match them with the score calculation processing logic corresponding to the rule configuration model to determine the score calculation rule corresponding to each review rule in the current procurement document; The review system is also used to automatically generate a preliminary review conclusion and an auxiliary reference score after performing combined operations on the response data extracted from the bidder's bid document according to the score calculation rules corresponding to each review rule.

8. The intelligent assisted review system based on standardized rules as claimed in claim 7, characterized in that: The rule configuration model includes any one or more of a judgment calculation model, a matching item calculation model, an addition and subtraction item calculation model, a ranking ascending or descending calculation model, and a ranking ascending or descending calculation model based on the review amount.

9. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method of any one of claims 1 to 8 when executed by a processor.

10. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 8.

Images