Purchase review management and control method, device and system

Abstract

The invention discloses a purchase review management and control method, device and system, and the method comprises the steps: carrying out the character recognition of a to-be-reviewed file, and obtaining a file text; based on a keyword library, performing keyword identification on the file text to obtain review information; based on a qualification certificate review rule base, analyzing whether each piece of qualification information meets a qualification condition, and obtaining a qualification review result; determining a response review result based on a comparison result between different page contents of the same response file and a comparison result between the page contents of different response files; obtaining a negative review result based on the supplier negative list; based on the qualification review result of the supplier, the response review result and the negative review result, generating a review conclusion in combination with a review conclusion statement library; based on the standard report template, generating a review report; and notifying experts in the expert database to review the review report so as to complete the purchase review task. The method can help enterprise users to improve the efficiency and level of purchase review.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a procurement review and control method, device and system. Background Art

[0002] Nowadays, the review of the results of procurement projects by enterprises basically involves the establishment of an expert group, the division of responsibilities for the review items, and the final summary of opinions to fill in the report and submit it to the meeting. In the above process, the establishment of the expert group, the experts’ implementation of each information verification in accordance with the procurement review work instructions, and the preparation and review of the report on the results are all difficult to organize and inefficient. At the same time, too much repeated filling of forms and mechanical verification work can easily lead to a waste of expert resources. Once there is a human system error in the review results, the work of the review experts is not only time-consuming and laborious, but also has the problem of lax control leading to inaccurate procurement results, which has a great negative impact on both the company and the participating suppliers.

[0003] Under the existing procurement review model, it takes about 20 minutes to fill out the basic template of the review report for open inquiry procurement, and about 30 minutes to fill out the competitive negotiation report. The average time from the establishment of the review expert group to the finalization of the procurement results is about 1-2 days (excluding the online bidding process). During this period, the analysis of subjective bid rigging and collusion in the documents is often easily overwhelmed by other objective result verification work, and sometimes even becomes a formality. The resources and capabilities that the review experts should exert are improperly allocated.

[0004] Driven by multiple factors such as corporate review compliance requirements, improving procurement efficiency, and the urgent need to optimize the allocation of human expert resources, modern enterprises are in urgent need of a procurement review control system and method based on evaluation rule algorithms to achieve innovative optimization and precise control of the procurement review process, thereby improving procurement management level and overall competitiveness, and ultimately giving the enterprise itself a higher level of intelligent strategic advantage. Summary of the invention

[0005] The present application provides a procurement review management method, device and system, the purpose of which is to help enterprise users improve the efficiency and level of procurement review.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] A procurement review control method, comprising:

[0008] Obtaining the documents to be reviewed corresponding to the procurement review application; the documents to be reviewed include the procurement document and the qualification document and response document of at least one supplier;

[0009] Performing text recognition on the document to be reviewed to obtain the document text; the document text includes the purchase order text, and the qualification text and response text of each supplier;

[0010] Based on the keyword library, keyword recognition is performed on the document text to obtain evaluation information; the evaluation information at least includes the qualification conditions shown in the purchase document, the qualification information shown in each of the qualification documents, and the page content shown in each of the response documents;

[0011] Based on the qualification certificate review rule base, analyze whether each of the qualification information meets the qualification conditions to obtain the qualification review results of each of the suppliers;

[0012] Determine the response review results of each of the suppliers based on the comparison results between the contents of different pages in the same response file and the comparison results between the contents of pages of different response files;

[0013] Based on the supplier negative list, negative information of each supplier is obtained and proofread to obtain negative review results of each supplier;

[0014] Based on the qualification review results, response review results and negative review results of each supplier, combined with the review conclusion statement library, generate the review conclusion of each supplier;

[0015] Generate a review report for each review conclusion based on a standard report template;

[0016] Notify the experts in the expert database to review the evaluation report to complete the procurement review task indicated in the procurement review application.

[0017] Optionally, the documents to be reviewed also include quotation documents of each supplier. Based on the qualification review results, response review results and negative review results of each supplier, combined with the review conclusion statement library, the review conclusion of each supplier is generated, including:

[0018] If the procurement review task indicated by the procurement review application is a competitive negotiation review, obtaining price information indicated by each quotation document; the price information is obtained by performing keyword recognition on the quotation text of the quotation document based on the keyword library;

[0019] Performing data analysis on each of the price information to obtain price review results for each of the suppliers;

[0020] Based on the qualification review results, response review results, price review results and negative review results of each of the suppliers, combined with the review conclusion statement library, the review conclusion of each of the suppliers is generated.

[0021] Optionally, the qualification information includes a qualification certificate and a business license. Based on the qualification certificate review rule base, analyzing whether each of the qualification information meets the qualification conditions to obtain the qualification review results of each of the suppliers includes:

[0022] Obtain certificate review rules and license review rules from the qualification certificate review rule library;

[0023] Based on the certificate review rules, analyzing whether the content shown in each of the qualification certificates meets the qualification conditions, so as to obtain the certificate review results of each of the suppliers;

[0024] Based on the license review rules, analyzing whether the contents shown in each of the business licenses are valid to obtain the license review results of each of the suppliers;

[0025] Based on the certificate review results and license review results of each of the suppliers, the qualification review results of each of the suppliers are determined.

[0026] Optionally, notifying experts in the expert database to review the review report to complete the procurement review task indicated in the procurement review application, including:

[0027] Extracting experts from the expert database according to expert extraction rules; the expert extraction rules include extraction probabilities of experts at different levels;

[0028] The selected experts review the review report to complete the procurement review task indicated in the procurement review application.

[0029] A procurement review control device, comprising:

[0030] A file acquisition unit, used to obtain the to-be-reviewed files corresponding to the procurement review application; the to-be-reviewed files include a procurement book file and at least one supplier's qualification file and response file;

[0031] A text recognition unit performs text recognition on the document to be reviewed to obtain a document text; the document text includes a purchase order text, and qualification texts and response texts of each supplier;

[0032] A keyword recognition unit, used to perform keyword recognition on the document text based on a keyword library to obtain review information; the review information at least includes the qualification conditions shown in the purchase document, the qualification information shown in each of the qualification documents, and the page content shown in each of the response documents;

[0033] A qualification review unit, used to analyze whether each of the qualification information meets the qualification conditions based on the qualification certificate review rule base, so as to obtain the qualification review results of each of the suppliers;

[0034] A response review unit, configured to determine the response review result of each of the suppliers based on the comparison results between the contents of different pages in the same response file and the comparison results between the contents of pages of different response files;

[0035] A negative verification unit, used to obtain and proofread the negative information of each supplier based on the supplier negative list to obtain the negative review results of each supplier;

[0036] A conclusion generating unit, used to generate a review conclusion for each supplier based on the qualification review result, response review result and negative review result of each supplier, combined with a review conclusion statement library;

[0037] A report generating unit, used for generating a review report of each review conclusion based on a standard report template;

[0038] The expert review unit is used to notify experts in the expert database to review the review report to complete the procurement review task indicated in the procurement review application.

[0039] Optionally, the document to be reviewed further includes quotation documents of each of the suppliers, and the device further includes a price review unit;

[0040] The price review unit is used to: if the procurement review task indicated by the procurement review application is a competitive negotiation review, obtain the price information indicated by each quotation document; the price information is obtained by performing keyword recognition on the quotation text of the quotation document based on the keyword library; perform data analysis on each of the price information to obtain the price review result of each of the suppliers;

[0041] The conclusion generating unit is specifically used to generate the evaluation conclusion of each supplier based on the qualification evaluation results, response evaluation results, price evaluation results and negative evaluation results of each supplier in combination with the evaluation conclusion statement library.

[0042] Optionally, the qualification information includes a qualification certificate and a business license, and the qualification review unit is specifically used to:

[0043] Obtain certificate review rules and license review rules from the qualification certificate review rule library;

[0044] Based on the certificate review rules, analyzing whether the content shown in each of the qualification certificates meets the qualification conditions, so as to obtain the certificate review results of each of the suppliers;

[0045] Based on the license review rules, analyzing whether the contents shown in each of the business licenses are valid to obtain the license review results of each of the suppliers;

[0046] Based on the certificate review results and license review results of each of the suppliers, the qualification review results of each of the suppliers are determined.

[0047] Optionally, the expert review unit is specifically used for:

[0048] Extracting experts from the expert database according to expert extraction rules; the expert extraction rules include extraction probabilities of experts at different levels;

[0049] The selected experts review the review report to complete the procurement review task indicated in the procurement review application.

[0050] A procurement review management and control system, including a procurement review module, a rule management module, an expert management module, a template management module and a role management module;

[0051] Among them, the procurement review module is used to execute the procurement review control method, the rule management module is used to maintain the keyword library, the qualification certificate review rule library, the review conclusion statement library and the supplier negative list, the expert management module is used to maintain the expert library, the template management module is used to maintain the standard report template, and the role management module is used to maintain the permissions of various types of users.

[0052] A storage medium includes a stored program, wherein the program executes the procurement review and control method when executed by a processor.

[0053] The technical solution provided by this application performs text recognition on the documents to be reviewed to obtain the document text. Based on the keyword library, the document text is subjected to keyword recognition to obtain the review information. Based on the qualification certificate review rule library, analyze whether each qualification information meets the qualification conditions to obtain the qualification review results. Based on the comparison results between the contents of different pages in the same response file and the comparison results between the page contents of different response files, determine the response review results. Based on the supplier negative list, negative information is obtained and proofread to obtain the negative review results of each supplier. Based on the qualification review results, response review results and negative review results of each supplier, combined with the review conclusion sentence library, each review conclusion is generated. Based on the standard report template, a review report is generated. Notify the experts in the expert library to review the review report to complete the procurement review task. This application realizes the generation of review reports and expert review through text recognition and keyword recognition of the documents to be reviewed, combined with the qualification certificate review rule library and the supplier negative list, thereby effectively helping enterprise users improve the efficiency and level of procurement review. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A flowchart of a procurement review and control method provided in an embodiment of the present application;

[0056] Figure 2 A flowchart of another procurement review and control method provided in an embodiment of the present application;

[0057] Figure 3 A schematic diagram of the architecture of a procurement review and control system provided in an embodiment of the present application;

[0058] Figure 4 A schematic diagram of the architecture of a procurement review and control device provided in an embodiment of the present application;

[0059] Figure 5 A logic diagram of an open inquiry review provided for an embodiment of the present application;

[0060] Figure 6 A competitive negotiation review logic diagram provided for an embodiment of the present application;

[0061] Figure 7 A schematic diagram of a login interface provided in an embodiment of the present application;

[0062] Figure 8 A schematic diagram of a supplier management page provided in an embodiment of the present application;

[0063] Fig. 9 A schematic diagram of a review rule management page provided in an embodiment of the present application;

[0064] Fig.10 A schematic diagram of a review result history record page provided in an embodiment of the present application;

[0065] Fig.11 A schematic diagram of a page for generating a review report format provided in an embodiment of the present application;

[0066] Fig.12 A schematic diagram of a system role management page provided in an embodiment of the present application;

[0067] Fig.13 A schematic diagram of a system home page provided in an embodiment of the present application;

[0068] Fig.14 A schematic diagram of an account permission page provided in an embodiment of the present application;

[0069] Fig.15 A schematic diagram of an expert database management page provided in an embodiment of the present application;

[0070] Fig.16 A schematic diagram of a qualification certificate review keyword setting page provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0072] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0073] like Figure 1 As shown, it is a flow chart of a procurement review and control method provided in an embodiment of the present application, including the following steps.

[0074] S101: Obtain the documents to be reviewed corresponding to the procurement review application.

[0075] Among them, the documents to be reviewed include the purchase order documents and the qualification documents and response documents of at least one supplier.

[0076] In some examples, a procurement review application may be initiated by an authorized user, or may be issued by an upstream business system.

[0077] The so-called response document is a bidding document prepared by the social capital party or bidder participating in government procurement activities in accordance with the requirements of the bidding documents, negotiation documents, consultation documents, inquiry notice, etc.

[0078] It should be noted that the types of procurement reviews include open inquiry reviews (which can be further divided into simple goods reviews and regular inquiry reviews) and competitive negotiation reviews. Accordingly, the documents to be reviewed for open inquiry reviews are different from those for competitive negotiation reviews. Generally speaking, the documents to be reviewed for competitive negotiation reviews will additionally include quotation documents from each supplier.

[0079] It is understandable that if the procurement review task indicated in the procurement review application is a competitive negotiation review, the documents to be reviewed also include the quotation documents of each supplier. Generally speaking, the focus of the public inquiry review and the competitive negotiation review is whether the supplier can meet the qualification requirements of the procurement documents, whether the response documents do not contain bid rigging or collusion, and whether the price information is regular and accurate.

[0080] In some examples, purchase documents, qualification documents, response documents, and quotation documents are usually electronic scans of paper documents, or image files, etc., which are file types that cannot be changed again, in order to ensure the validity of each document.

[0081] S102: Perform text recognition on the document to be reviewed to obtain the document text.

[0082] Among them, the document text includes the purchase order text, as well as the qualification text and response text of each supplier.

[0083] In some examples, OCR (Optical Character Recognition) may be used to perform text recognition on a purchase document to obtain a purchase document text, to perform text recognition on a qualification document to obtain a qualification text, and to perform text recognition on a response document to obtain a response text.

[0084] In some examples, if the document to be reviewed also includes a quotation document of a supplier, text recognition is performed on the quotation document to obtain the quotation text.

[0085] S103: Based on the keyword library, perform keyword recognition on the document text to obtain review information.

[0086] The review information includes at least the qualification conditions shown in the purchase document, the qualification information shown in each qualification document, and the page content shown in each response document.

[0087] It should be noted that the keyword library is pre-configured with a first keyword related to qualification conditions, a second keyword related to qualification information, a third keyword related to page content, and a fourth keyword related to price information.

[0088] In a possible implementation, based on the first keyword (such as project name, on schedule, quotation instructions, special qualification conditions, etc.), keyword recognition is performed on the purchase document text to obtain the corresponding qualification conditions.

[0089] In a possible implementation manner, based on a second keyword (such as a power of attorney, a business license, a qualification certificate, etc.), keyword recognition is performed on the qualification text to obtain corresponding qualification information.

[0090] In a possible implementation manner, based on the third keyword (eg, technical business response letter, difference table, etc.), keyword recognition is performed on the response text to obtain the corresponding page content.

[0091] In a possible implementation, based on a fourth keyword (such as item unit price, quantity, tax rate, total price, etc.), keyword recognition is performed on the quotation text to obtain corresponding price information.

[0092] In some examples, in addition to configuring keywords such as "License for Installation (Repair and Testing) of Power Facilities", license category and level, validity period, etc., the keyword library can also set keyword categories, such as certificate name, certificate content, document template, etc., and set keyword levels (for example, the highest level is level 1, the lowest level is level 7, etc., which represents the step in which different keywords are checked during the review. For example, the keyword on the difference table page is a level 1 keyword, which can be placed in the first step for identification query. If the keyword is not found, the program will be stopped directly and the corresponding text content will be displayed). In addition, the keyword status can also be set (for example, whether it is effective, etc.).

[0093] S104: Based on the qualification certificate review rule base, analyze whether each qualification information meets the qualification conditions to obtain the qualification review results of each supplier.

[0094] Among them, the qualification information includes qualification certificates and business licenses. Correspondingly, the qualification certificate review rule base includes certificate review rules and license review rules. Specifically, the certificate review rules are used to analyze whether the qualification certificates are compliant, and the license review rules are used to analyze whether the business licenses are compliant.

[0095] Optionally, based on the qualification certificate review rule base, analyze whether each qualification information meets the qualification conditions to obtain the qualification review results of each supplier. For details, see Figure 2 The steps are shown and the corresponding explanations.

[0096] S105: Determine the response review results of each supplier based on the comparison results between different page contents in the same response file and the comparison results between page contents of different response files.

[0097] Among them, based on the comparison results between the contents of different pages in the same response file, and the comparison results between the page contents of different response files, it is possible to implement bid rigging analysis of the response files of various suppliers.

[0098] The so-called bid rigging and collusion refers to the illegal behavior of excluding other bidders and making the intended bidder win the bid through offensive and defensive alliances among bidders or secret collusion between bidders and the tenderer (including the tendering agency and evaluation experts) during the bidding process, which damages the national interest, social public interest or the legitimate rights and interests of others.

[0099] In some examples, the page content in the response file may include information such as the project entrusting authorizer, the name, phone number and company seal of the quoter, a difference table, and a document response letter.

[0100] In a possible implementation, the comparison between the contents of different pages in the same response file can be understood as a vertical comparison check, that is, checking whether there are different contents in the page contents of different pages in the same response file. Specifically, whether different names appear in the contents of different pages in the same response file. If the names are consistent, it means that the authorized person of the supplier is the same person. If the names are inconsistent, further contact and verification by manual experts is required to verify who is responsible for this project of the supplier and represent the company's opinion.

[0101] In a possible implementation, the comparison between the page contents of different response files can be understood as a horizontal comparison check, that is, checking whether the page contents of different response files have the same content. Specifically, comparing whether different suppliers have the same name. If so, it is determined that the supplier has colluded in bidding.

[0102] S106: Based on the supplier negative list, negative information of each supplier is obtained and proofread to obtain negative review results of each supplier.

[0103] Among them, the supplier negative list includes the negative information of suppliers obtained regularly from the integrated business management platform. The supplier negative data includes the blacklist period, blacklist level (for example, if the level is 1, transactions are prohibited, and if the level is 2, it is an associated transaction), and current status (for example, modification, removal, etc.) of each supplier.

[0104] It should be noted that obtaining negative information about each supplier based on the supplier negative list can assist in checking whether each supplier has engaged in bid rigging or collusion. In a possible implementation, the modification time of supplier documents (such as qualification documents, response documents, and quotation documents) is compared with the blacklist period to determine whether the supplier has engaged in bid rigging or collusion.

[0105] S107: Based on the qualification review results, response review results and negative review results of each supplier, combined with the review conclusion statement library, generate the review conclusion of each supplier.

[0106] Among them, the review conclusion sentence library includes the sentence content required when issuing a review report.

[0107] Optionally, if the procurement review task indicated in the procurement review application is a competitive negotiation review, a big data analysis is performed on the price information shown in the quotation documents of each supplier to obtain the price review results of each supplier. Finally, based on the qualification review results, response review results, price review results and negative review results of each supplier, combined with the review conclusion sentence library, a review conclusion for each supplier is generated.

[0108] In some examples, big data analysis may include: checking whether the individual quotations are accurate, whether the total price corresponds to the total price, whether the quoted tax rates are consistent, whether there are any errors or omissions, whether there is any regularity in the quotations from different suppliers, and other analysis situations.

[0109] S108: Generate a review report for each review conclusion based on the standard report template.

[0110] Among them, the design of the standard report template not only meets the review work needs of various procurement projects, but also reduces the workload of manual review experts and improves the accuracy of objective reviews.

[0111] In some examples, standard report templates are divided into two categories: inquiry reports (for public inquiry reviews) and competitive negotiation reports (for competitive negotiation reviews). Standard report templates can be pre-stored in the background, providing report conclusion output text and online review to meet complex procurement needs. When reviewing standard report templates online, the standard report templates cannot be modified and are used as original backup data for the supervisory department to check the standardization of procurement reviews. The output review report can be used by review experts to add manual verification of some conclusions based on automatic detection.

[0112] S109: Notify the experts in the expert database to review the review report to complete the procurement review task indicated in the procurement review application.

[0113] Among them, the experts in the expert database can be pre-configured by the user so as to select appropriate experts to participate in the review of the evaluation report.

[0114] In some examples, the expert database is divided into sub-professional databases such as gas turbine expert database, steam turbine expert database, boiler expert database, hydropower expert database, new energy expert database, and business expert database according to the different professions of the experts. The expert database supports manual addition of experts and can also import the expert list at one time. Each expert can set the name of the review expert, the unit where the review expert is located, the review expert level (such as senior, intermediate, and primary), and the current status (such as modified, removed, etc.).

[0115] Optionally, the experts in the expert database are notified to review the evaluation report to complete the implementation process of the procurement review task shown in the procurement review application. The implementation process may be as follows: experts are extracted from the expert database according to expert extraction rules; the expert extraction rules include extraction probabilities of experts at different levels; the extracted experts review the evaluation report to complete the procurement review task shown in the procurement review application.

[0116] In a possible implementation, the expert selection rules can be: random selection from each professional database; 50% probability of selecting senior experts, 30% probability of selecting intermediate experts, and 20% probability of selecting junior experts. In addition, the expert selection rules will also require confirmation of whether the expert belongs to the project owner unit. Except for the review team leader, the review members are only selected from experts from other units other than the owner unit.

[0117] Based on the process shown in S101-S109, it can be applied to Figure 3 The procurement review control system shown includes a procurement review module 301 , a rule management module 302 , an expert management module 303 , a template management module 304 and a role management module 305 .

[0118] Specifically, the procurement review module is used to execute the procurement review control method provided by the process shown in S101-S109, the rule management module is used to maintain the keyword library, the qualification certificate review rule library, the review conclusion statement library and the supplier negative list, the expert management module is used to maintain the expert library, the template management module is used to maintain the standard report template, and the role management module is used to maintain the permissions of various users.

[0119] In some examples, the role management module gives different operating permissions to personnel at all levels in each company, with three levels from high to low: administrator, procurement business expert, and review expert, which can be used to modify different ranges of content in the procurement review management and control system.

[0120] In a possible implementation method, the administrator can operate and modify all the contents of the platform. This is a top-level authority assigned to the comprehensive director and procurement supervisor of the centralized procurement center and the leaders in charge of departments. This type of account will change the content of system modules according to the updates of the procurement system and work needs, and simultaneously cooperate with the external supervision department to review all data records of the platform's business, and regularly connect with the platform development company to update the system version.

[0121] In a possible implementation method, procurement business experts can perform specific business function maintenance, such as qualification review rules, review conclusion statement library, supplier negative list, expert library, etc.

[0122] In a possible implementation, the review expert may only review the review report and has no other authority.

[0123] In some examples, based on the use of the procurement review control system, the process of implementing the public inquiry review can be seen in Figure 5 As shown, the process of implementing competitive negotiation review can be found in Figure 6 shown.

[0124] In a possible implementation, the procurement review and control system may preset multiple UI interfaces, for example, Figure 7 The login interface shown, Figure 8 The supplier management page shown, Fig. 9 The review rules management page shown. Fig.10 The review result history page shown, Fig.11 Generate review report format page as shown, Fig.12 The system role management page shown is Fig.13 The system main page is shown. Fig.14 The account permissions page shown. Fig.15 The expert database management page shown, and Fig.16 The qualification certificate review keyword setting page is shown.

[0125] It should be noted that the use of the procurement review and control system can achieve the following beneficial effects: First, greatly improve the efficiency of review work: after the system is put into operation, the time for inquiry and procurement review is shortened from several hours to several minutes, and the time for competitive negotiation review is shortened from half a day to about ten minutes, and the review time rate is increased by 70%-90%. The pace of enterprise material procurement operation has been significantly accelerated; second, improve the reliability of review results, refer to the rule statements formed by industry experts and laws and regulations, eliminate the errors of manual review, strictly search for sensitive words in the statement, and trigger according to the rules, greatly improve the accuracy and reliability of the review; third, easy to operate, the system is simple to use, only need to follow the prompts to import the procurement book file and quotation table to be checked, automatically read and generate the participating supplier options, and provide the operation of uploading response files and quotation files under each item, which can be uploaded on demand. At the same time, each expert database, supplier negative list, qualification certificate, etc. can be updated in real time; fourth, the promotion benefit is huge, the underlying review rules of the system are general rules in the procurement field, which can be transformed and used according to the specific system scenarios of each company, and have broad application and promotion value. Different regions can be directly authorized for promotion, and cross-company can be authorized for secondary development, with huge benefits.

[0126] The process shown in S101-S109 above realizes the generation of review reports and expert review through text recognition and keyword recognition of the documents to be reviewed, combined with the qualification certificate review rule library and the supplier negative list, thereby effectively helping corporate users improve the efficiency and level of procurement review.

[0127] like Figure 2 As shown, it is a flow chart of another procurement review and control method provided in an embodiment of the present application, including the following steps.

[0128] S201: Obtain certificate review rules and license review rules from a qualification certificate review rule library.

[0129] Among them, both the certificate review rules and the license review rules are configured with multi-level detection steps. When using the certificate review rules and the license review rules for analysis, the analysis is usually performed according to the multi-level detection steps.

[0130] In some examples, certificate review rules can support displaying certificate classification (that is, the name of each certificate), certificate comparison (determining whether the certificate level is higher than or equal to, or lower than, or whether the sub-item exists. Specifically, for example, the installation certificate has five levels as the lowest and one level as the highest. The comparison rule is set to "higher than or equal to". The detected supplier qualification level needs to be higher or equal to the level shown in the qualification conditions required in the procurement documents in order to be determined to be passed), validity period comparison (needs to be at least 1 month greater than the current review time), status setting (such as enabling or hiding), modifying and deleting rules, and other functions.

[0131] In some examples, the license review rules may be used to verify the company name, type, and validity period shown on the business license.

[0132] In a possible implementation, the steps for testing the business license using the license review rules may be as follows: in the first level step, first search for the keyword "business license", if not found, display "lack of corresponding license, failed", and jump to the second level step; in the second level step, search for the keywords "limited liability company" and "joint stock company" in the license content, if found, jump to the third level step, if not found, output "company type alarm, manual inspection, failed"; in the third level step, search for keywords such as "business term" or "validity period", "validity period", etc., if found, further search the fourth level step, if not found, directly display "Tianyancha, National Enterprise Information Credit Information Publicity System, Credit China Query, passed"; in the fourth level step, retrieve "long-term", "irregular", "indefinite", "specific date > today's date + 30 days", if specified keywords are found, directly display "Tianyancha, National Enterprise Credit Publicity System, Credit China Query, passed", otherwise display "business term expectation, manual inspection, failed".

[0133] In a possible implementation, the steps for testing the legal person certificate of an institution using the certificate review rules may be as follows: in the first level, first search for the keyword "legal person certificate of an institution", if not found, display "lack of corresponding license, failed", if found, jump to the second level; in the second level, search for keywords such as "business term" or "validity period", "validity period", etc., if found, further search the third level, if not, directly display "Tianyancha, National Enterprise Credit Information Publicity System, Credit China Query, passed"; in the third level, search for "long-term", "irregular", "indefinite", "specific date>today's date+30 days", if specified keywords exist, directly display "Tianyancha, National Enterprise Credit Publicity System, Credit China Query, passed", otherwise display "business term expectation, manual inspection, failed".

[0134] In a possible implementation, the qualification condition detection steps using the certificate review rules can be: the first level step is to first retrieve the name of the qualification certificate in the qualification requirement part of the purchase document. If not, " / " is directly displayed. If yes, further search whether the name of the qualification certificate exists in the imported supplier file (such as the qualification file). If yes, further search the second level step. If not, display "No valid qualifications were retrieved, manual inspection, failed"; the second level step is to retrieve whether the qualifications provided in the supplier file can match the different types of certificate information maintained in the system qualification review keyword maintenance page. If yes, display "Read the certificate qualification information, passed"; if not, display "No certificate qualification information was read, failed".

[0135] S202: Based on the certificate review rules, analyze whether the content shown in each qualification certificate meets the qualification conditions to obtain the certificate review results of each supplier.

[0136] Among them, the certificate review results can represent the review of the qualification certificate.

[0137] S203: Based on the license review rules, analyze whether the content shown in each business license is valid to obtain the license review results of each supplier.

[0138] Among them, the license review results can represent the review of the business license.

[0139] S204: Determine the qualification review results of each supplier based on the certificate review results and license review results of each supplier.

[0140] Among them, based on the supplier's certificate review results and license review results, the supplier's qualification review results are determined to achieve effective review of the supplier's qualification documents.

[0141] The process shown in S201-S204 above uses the certificate review rules to determine the corresponding certificate review results, and uses the license review rules to determine the corresponding license review results, thereby achieving effective review of the supplier's qualification documents.

[0142] like Figure 4 As shown, it is a schematic diagram of the architecture of a procurement review device provided in an embodiment of the present application, which includes the following units.

[0143] The file acquisition unit 100 is used to obtain the files to be reviewed corresponding to the procurement review application; the files to be reviewed include a procurement document file and at least one supplier's qualification document and response document.

[0144] Optionally, the documents to be reviewed also include quotation documents from various suppliers.

[0145] The text recognition unit 200 performs text recognition on the document to be reviewed to obtain the document text; the document text includes the purchase order text, as well as the qualification text and response text of each supplier.

[0146] The keyword recognition unit 300 is used to perform keyword recognition on the file text based on the keyword library to obtain review information; the review information at least includes the qualification conditions shown in the purchase document, the qualification information shown in each qualification document, and the page content shown in each response document.

[0147] The qualification review unit 400 is used to analyze whether each qualification information meets the qualification conditions based on the qualification certificate review rule base to obtain the qualification review results of each supplier.

[0148] Optionally, the qualification information includes a qualification certificate and a business license, and the qualification review unit 400 is specifically used to: obtain certificate review rules and license review rules from a qualification certificate review rule library; based on the certificate review rules, analyze whether the content shown in each qualification certificate meets the qualification conditions to obtain the certificate review results of each supplier; based on the license review rules, analyze whether the content shown in each business license is valid to obtain the license review results of each supplier; based on the certificate review results and license review results of each supplier, determine the qualification review results of each supplier.

[0149] The response review unit 500 is used to determine the response review result of each supplier based on the comparison result between different page contents in the same response file and the comparison result between page contents of different response files.

[0150] The price review unit 600 is used for: if the procurement review task indicated in the procurement review application is a competitive negotiation review, obtaining the price information indicated in each quotation document; the price information is obtained by performing keyword recognition on the quotation text of the quotation document based on a keyword library; performing data analysis on each price information to obtain the price review result of each supplier; the conclusion generation unit is specifically used for: based on the qualification review results, response review results, price review results and negative review results of each supplier, combined with the review conclusion sentence library, generating the review conclusion of each supplier.

[0151] The negative verification unit 700 is used to obtain negative information of each supplier based on the supplier negative list and perform proofreading to obtain negative review results of each supplier.

[0152] The conclusion generating unit 800 is used to generate the review conclusion of each supplier based on the qualification review result, response review result and negative review result of each supplier in combination with the review conclusion sentence library.

[0153] The report generating unit 900 is used to generate a review report of each review conclusion based on a standard report template.

[0154] The expert review unit 1000 is used to notify the experts in the expert database to review the review report to complete the procurement review task indicated in the procurement review application.

[0155] Optionally, the expert review unit 1000 is specifically used to: extract experts from the expert database according to expert extraction rules; the expert extraction rules include extraction probabilities of experts at different levels; and review the review report by the extracted experts to complete the procurement review task indicated in the procurement review application.

[0156] Each of the above-mentioned units, through text recognition and keyword recognition of the documents to be reviewed, combined with the qualification certificate review rule base and the supplier negative list, realizes the generation of review reports and expert review, thereby effectively helping corporate users improve the efficiency and level of procurement review.

[0157] The present application also provides a computer-readable storage medium, which includes a stored program, wherein the program executes the procurement review method provided by the present application.

[0158] In addition, the functions described above in the embodiments of the present application may be at least partially performed by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0159] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present application. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0160] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A procurement review control method, characterized in that: include: Obtain the documents to be reviewed corresponding to the procurement review application; The documents to be reviewed include the purchase order document and the qualification document and response document of at least one supplier; Performing text recognition on the document to be reviewed to obtain the document text; the document text includes the purchase order text, and the qualification text and response text of each supplier; Based on the keyword library, keyword recognition is performed on the document text to obtain evaluation information; the evaluation information at least includes the qualification conditions shown in the purchase document, the qualification information shown in each of the qualification documents, and the page content shown in each of the response documents; Based on the qualification certificate review rule base, analyze whether each of the qualification information meets the qualification conditions to obtain the qualification review results of each of the suppliers; Determine the response review results of each of the suppliers based on the comparison results between the contents of different pages in the same response file and the comparison results between the contents of pages of different response files; Based on the supplier negative list, negative information of each supplier is obtained and proofread to obtain negative review results of each supplier; Based on the qualification review results, response review results and negative review results of each supplier, combined with the review conclusion statement library, generate the review conclusion of each supplier; Generate a review report for each review conclusion based on a standard report template; Notify the experts in the expert database to review the evaluation report to complete the procurement review task indicated in the procurement review application.

2. The method according to claim 1, characterized in that The documents to be reviewed also include quotation documents of each supplier. Based on the qualification review results, response review results and negative review results of each supplier, combined with the review conclusion statement library, the review conclusion of each supplier is generated, including: If the procurement review task indicated by the procurement review application is a competitive negotiation review, obtaining price information indicated by each quotation document; the price information is obtained by performing keyword recognition on the quotation text of the quotation document based on the keyword library; Performing data analysis on each of the price information to obtain price review results for each of the suppliers; Based on the qualification review results, response review results, price review results and negative review results of each of the suppliers, combined with the review conclusion statement library, the review conclusion of each of the suppliers is generated.

3. The method according to claim 1, characterized in that The qualification information includes a qualification certificate and a business license. Based on the qualification certificate review rule base, each of the qualification information is analyzed to see whether it meets the qualification conditions, so as to obtain the qualification review results of each of the suppliers, including: Obtain certificate review rules and license review rules from the qualification certificate review rule library; Based on the certificate review rules, analyzing whether the content shown in each of the qualification certificates meets the qualification conditions, so as to obtain the certificate review results of each of the suppliers; Based on the license review rules, analyzing whether the contents shown in each of the business licenses are valid to obtain the license review results of each of the suppliers; Based on the certificate review results and license review results of each of the suppliers, the qualification review results of each of the suppliers are determined.

4. The method according to claim 1, characterized in that Notify the experts in the expert pool to review the evaluation report to complete the procurement review tasks indicated in the procurement review application, including: Extracting experts from the expert database according to expert extraction rules; the expert extraction rules include extraction probabilities of experts at different levels; The selected experts review the review report to complete the procurement review task indicated in the procurement review application.

5. A procurement review control device, characterized in that: include: A document acquisition unit, used to obtain the documents to be reviewed corresponding to the procurement review application; The documents to be reviewed include the purchase order document and the qualification document and response document of at least one supplier; A text recognition unit performs text recognition on the document to be reviewed to obtain a document text; the document text includes a purchase order text, and qualification texts and response texts of each supplier; A keyword recognition unit, used to perform keyword recognition on the document text based on a keyword library to obtain review information; the review information at least includes the qualification conditions shown in the purchase document, the qualification information shown in each of the qualification documents, and the page content shown in each of the response documents; A qualification review unit, used to analyze whether each of the qualification information meets the qualification conditions based on the qualification certificate review rule base, so as to obtain the qualification review results of each of the suppliers; A response review unit, configured to determine the response review result of each of the suppliers based on the comparison results between the contents of different pages in the same response file and the comparison results between the contents of pages of different response files; A negative verification unit, used to obtain and proofread the negative information of each supplier based on the supplier negative list to obtain the negative review results of each supplier; A conclusion generating unit, used to generate a review conclusion for each supplier based on the qualification review result, response review result and negative review result of each supplier, combined with a review conclusion statement library; A report generating unit, used for generating a review report of each review conclusion based on a standard report template; The expert review unit is used to notify experts in the expert database to review the review report to complete the procurement review task indicated in the procurement review application.

6. The device according to claim 5, characterized in that The documents to be reviewed also include quotation documents of each of the suppliers, and the device also includes a price review unit; The price review unit is used to: if the procurement review task indicated by the procurement review application is a competitive negotiation review, obtain the price information indicated by each quotation document; the price information is obtained by performing keyword recognition on the quotation text of the quotation document based on the keyword library; perform data analysis on each of the price information to obtain the price review result of each of the suppliers; The conclusion generating unit is specifically used to generate the evaluation conclusion of each supplier based on the qualification evaluation results, response evaluation results, price evaluation results and negative evaluation results of each supplier in combination with the evaluation conclusion statement library.

7. The device according to claim 5, characterized in that The qualification information includes a qualification certificate and a business license. The qualification review unit is specifically used to: Obtain certificate review rules and license review rules from the qualification certificate review rule library; Based on the certificate review rules, analyzing whether the content shown in each of the qualification certificates meets the qualification conditions, so as to obtain the certificate review results of each of the suppliers; Based on the license review rules, analyzing whether the contents shown in each of the business licenses are valid to obtain the license review results of each of the suppliers; Based on the certificate review results and license review results of each of the suppliers, the qualification review results of each of the suppliers are determined.

8. The device according to claim 5, characterized in that The expert review unit is specifically used for: Extracting experts from the expert database according to expert extraction rules; the expert extraction rules include extraction probabilities of experts at different levels; The selected experts review the review report to complete the procurement review task indicated in the procurement review application.

9. A procurement review and control system, characterized in that: It includes procurement review module, rule management module, expert management module, template management module and role management module; Among them, the procurement review module is used to execute the procurement review control method described in any one of claims 1-4, the rule management module is used to maintain a keyword library, a qualification certificate review rule library, a review conclusion statement library and a supplier negative list, the expert management module is used to maintain the expert library, the template management module is used to maintain standard report templates, and the role management module is used to maintain the permissions of various types of users.

10. A storage medium, characterized in that: The storage medium includes a stored program, wherein the program, when executed by a processor, executes the procurement review and control method described in any one of claims 1 to 4.

Images