Method, device and system for identifying serial bidding behavior

CN119006131APending Publication Date: 2024-11-22国网江西省电力有限公司综合服务中心
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411019106.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

[0004]鉴于上述问题,提出了本申请以便提供一种克服上述问题或者至少部分地解决上述问题的一种串通投标行为的辨识方法、装置及系统、电子设备、存储介质及计算机程序产品,能够准确和高效地辨识串通投标行为,解决人工查阅投标文件效率低,且难以发现隐蔽的投标人串通投标行为的问题

Benefits of technology

[0054]借由上述技术方案,本申请提供的串通投标行为的辨识方法、装置及系统、电子设备、存储介质及计算机程序产品,该方法批量提取多个投标文件的非结构化数据,获取投标文件信息及人员信息,存入数据库;挖掘数据库中投标文件信息及人员信息之间的异常关联关系,辨识投标人串通投标行为;将投标人串通投标行为辨识结果发送至展示单元集中展示。可以看到,本申请通过批量提取多个投标文件的非结构化数据,获取投标文件信息及人员信息,存入数据库;进而挖掘数据库中投标文件信息及人员信息之间的异常关联关系,辨识投标人串通投标行为,能够准确和高效地辨识串通投标行为,解决人工查阅投标文件效率低,且难以发现隐蔽的投标人串通投标行为的问题;并且,本申请可以将投标人串通投标行为辨识结果发送至展示单元集中展示,方便查阅串通投标行为。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006131A_ABST
    Figure CN119006131A_ABST
Patent Text Reader

Abstract

The invention provides a serial bidding behavior identification method, device and system, electronic equipment, a storage medium and a computer program product, and relates to the technical field of bidding and bidding. The method comprises the following steps: extracting unstructured data of a plurality of bidding files in batches to obtain bidding file information and personnel information, and storing the bidding file information and personnel information into a database; the method comprises the following steps of: acquiring the bidding document information in a database, mining an abnormal association relationship between the bidding document information and personnel information in the database, identifying the serial bidding behavior of the bidder, accurately and efficiently identifying the serial bidding behavior, and solving the problems that the efficiency of manually looking up the bidding document is low and the hidden serial bidding behavior of the bidder is difficult to discover; moreover, the identification result of the serial bidding behavior of the bidder can be sent to the display unit for centralized display, so that the serial bidding behavior can be conveniently looked up.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of bidding and tendering, and in particular to a method, device and system, electronic device, storage medium and computer program product for identifying collusive bidding. Background Art

[0002] In the context of the rapid development of the market economy, bidding activities, as an important way of resource allocation, play an irreplaceable role in promoting the healthy development of the economy. However, with the intensification of market competition, some unfair competition behaviors have gradually surfaced, among which the collusion between bidders is a prominent problem. The Regulations on the Implementation of the Tendering and Bidding Law of the People's Republic of China clearly prohibits such behavior in order to maintain the fairness and transparency of the bidding market.

[0003] The bidding collusion among bidders is hidden. Currently, the bidding documents are mainly read, recorded and analyzed manually, lacking unified collection and application, which is inefficient and brings great troubles to the standardization of bidding management and the maintenance of fair competition. Based on this, the identification of bidding collusion among bidders has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of the above problems, the present application is proposed to provide a method, device and system for identifying bid rigging that overcomes the above problems or at least partially solves the above problems, and can accurately and efficiently identify bid rigging, solve the problem that manual review of bidding documents is inefficient and difficult to discover hidden bidders' bid rigging. The technical solution is as follows:

[0005] In a first aspect, a method for identifying bid rigging is provided, the method comprising:

[0006] Extract unstructured data from multiple bidding documents in batches, obtain bidding document information and personnel information, and store them in the database;

[0007] Mining the abnormal correlation between bidding document information and personnel information in the database to identify bidders’ collusion in bidding;

[0008] The results of identifying the bidders' collusion in bidding are sent to the display unit for centralized display.

[0009] In a possible implementation, the multiple bidding documents are scanned copies in PDF format;

[0010] The batch extraction of unstructured data of multiple bidding documents, obtaining bidding document information and personnel information, and storing them in a database includes:

[0011] Calling the unstructured data extraction program of PDF bidding documents to realize large-scale data extraction; wherein, the unstructured data extraction program of PDF bidding documents parses the bidding document structure through a python program, extracts the tables and pictures in the PDF file, and then performs OCR recognition to obtain text data;

[0012] Execute the unstructured data extraction program of the PDF bidding documents, extract the unstructured data of multiple bidding documents in batches, and obtain the bidding document information and personnel information;

[0013] The bidding document information and personnel information are stored in the database as structured data, which serves as the basis for further data analysis.

[0014] In a possible implementation, the bidding document information includes the bidding batch, the bid package name, the bid package number, and the bidder name; the personnel information includes the name and ID number of the personnel, and the personnel include the legal representative, the authorized agent, the contact person, the project leader, and the project members;

[0015] The mining of abnormal correlations between bidding document information and personnel information in the database to identify bidders' bidding collusion behavior includes:

[0016] Using the structured analysis capabilities of the SQL language, we built a bidder collusion behavior identification model, and deeply analyzed the relationship between the bidding batch, bid package name, bid package number, bidder name, legal representative, entrusted agent, contact person, project leader, and project members;

[0017] Among them, the bidders' collusion bidding behavior identification model is:

[0018] For different bidding documents of the same bid package, at least one of the names and ID numbers of the legal representative, authorized agent, contact person, project leader, and project member stated in each bidding document has a non-empty intersection. The formula is as follows:

[0019]

[0020] In formula (1), F A 、F B , F are bidder A, bidder B and the collection of all bidders, respectively, and all have the attributes of the name and ID number of the legal representative, the authorized agent, the contact person, the project leader and the project members; F AB is the intersection of the attributes of bidder A and bidder B; Φ is an empty set;

[0021] When formula (1) is satisfied, it is identified that bidders A and B have engaged in bidding collusion, which constitutes a bidding collusion situation.

[0022] In a possible implementation, executing the PDF bidding document unstructured data extraction program, batch extracting unstructured data of multiple bidding documents, and obtaining bidding document information and personnel information includes:

[0023] Store the image bytes stream data in the form of memory variables;

[0024] Get multiple bidding documents and build a bidding document list;

[0025] file_list=[file_1,file_2,...,file_n] (2)

[0026] In formula (2), file_list is the bidding document list; file_1, file_2, ..., file_n are bidding documents;

[0027] Input PDF file, output image bytes stream, get the image bytes stream of PDF file;

[0028]

[0029] In formula (3), pdffile is the bidding file variable, i.e., PDF file; file_list is the pdffile collection; function_pdftobytes is the function that converts pdffile into a picture bytes stream;

[0030] Obtain the OCR recognition results of the image bytes stream and extract the bidding document information and personnel information data;

[0031] pdf_json{pdffile}=[data_a,data_b] (4)

[0032] In formula (4), pdf_json{pdffile} is the OCR recognition result of the image bytes stream; data_a is the bidding batch, bid package name, bid package number, and bidder name; data_b is the name and ID number of the legal representative, authorized agent, contact person, project leader, and project member;

[0033] By using the multi-core concurrent mechanism and giving full play to the computing power of multi-core CPUs, equations (3) and (4) are calculated in multi-core concurrent manner to improve the efficiency of data extraction from bidding documents.

[0034] The bidding document information and personnel information are stored in the database as structured data, including:

[0035] Connect to the database and write the data of pdf_json{pdffile} into the database.

[0036] In a possible implementation, the abnormal correlation between the bidding document information and the personnel information in the database is mined to identify the bidders' bidding collusion behavior, including:

[0037] Based on the bidding batch, bid package name, bid package number, and bidder name, the names and ID numbers of the legal representative, entrusted agent, contact person, project leader, and project members are aggregated and calculated. The SQL model formula is as follows:

[0038]

[0039] In formula (5), name is the name of the legal representative, authorized agent, contact person, project leader, and project member recorded in data_b; id_card is the ID number of the legal representative, authorized agent, contact person, project leader, and project member recorded in data_b; f count (data_a) is an aggregation function that counts personnel information; Formula (5) means that for the same bid package, if the number of bid documents that have been deduplicated and are associated with a certain name or ID number exceeds 1, then the name or ID number appears in different bid documents, indicating that the legal representative, or the authorized agent, or the contact person, or the project leader, or the project member stated in the bid documents of different bidders is the same person;

[0040] When formula (5) is satisfied, the bidders’ collusion in bidding is identified, which constitutes a situation of bidders’ collusion in bidding;

[0041] The SQL model described in formula (5) is a data analysis method for presenting the bidder collusion behavior identification model described in formula (1).

[0042] In a second aspect, a device for identifying bid rigging is provided, the device comprising:

[0043] The acquisition module is used to batch extract the unstructured data of multiple bidding documents, obtain the bidding document information and personnel information, and store them in the database;

[0044] Identification module, used to mine the abnormal correlation between bidding document information and personnel information in the database, and identify the bidding collusion behavior of bidders;

[0045] The display module is used to send the results of identifying the bidders' collusion in bidding to the display unit for centralized display.

[0046] In a third aspect, a system for identifying bid rigging is provided, the system comprising:

[0047] A network connection unit, used for establishing a network connection with a database server;

[0048] Storage unit, used to store data and programs;

[0049] The execution unit is used to read and execute the program of the storage unit, batch extract the unstructured data of multiple bidding documents, obtain the bidding document information and personnel information, and store them in the database; mine the abnormal correlation between the bidding document information and personnel information in the database, and identify the bidding collusion behavior of bidders;

[0050] The display unit is used to display the results of identifying the bidders' collusion in bidding.

[0051] In a fourth aspect, an electronic device is provided, comprising a memory, a processor, and a display, wherein the memory stores a computer program, the processor executes the computer program, and the display displays the results of identifying collusive bidding behavior among bidders; when the computer program is executed by the processor, the method for identifying collusive bidding behavior described in any one of the above items is implemented.

[0052] In a fifth aspect, a storage medium is provided, wherein a computer program is stored in the storage medium, wherein the computer program is configured to execute any of the above-mentioned methods for identifying collusive bidding when running.

[0053] In a sixth aspect, a computer program product is provided, comprising a computer program, wherein the computer program is configured to execute any of the above-mentioned methods for identifying collusive bidding when running.

[0054] By means of the above technical scheme, the present application provides a method, device and system for identifying collusive bidding, an electronic device, a storage medium and a computer program product, which extracts unstructured data of multiple bidding documents in batches, obtains bidding document information and personnel information, and stores them in a database; mines the abnormal correlation between the bidding document information and personnel information in the database, identifies the collusive bidding behavior of bidders; and sends the identification results of the collusive bidding behavior of bidders to a display unit for centralized display. It can be seen that the present application extracts unstructured data of multiple bidding documents in batches, obtains bidding document information and personnel information, and stores them in a database; then mines the abnormal correlation between the bidding document information and personnel information in the database, identifies the collusive bidding behavior of bidders, and can accurately and efficiently identify the collusive bidding behavior, solve the problem of low efficiency in manually reviewing bidding documents and difficulty in discovering hidden collusive bidding behavior of bidders; and the present application can send the identification results of the collusive bidding behavior of bidders to a display unit for centralized display, which is convenient for reviewing the collusive bidding behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0056] Figure 1 A flow chart showing a method for identifying bidding rigging provided in an embodiment of the present application is shown;

[0057] Figure 2 A structural diagram of a bidding rigging identification device provided in an embodiment of the present application is shown;

[0058] Figure 3 A structural diagram of a bidding rigging identification system provided in an embodiment of the present application is shown;

[0059] Figure 4 A flow chart showing a method for identifying bidding rigging provided by another embodiment of the present application is shown;

[0060] Figure 5 A structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0061] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0062] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such use is interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to".

[0063] In order to solve the above technical problems, the present application provides a method for identifying bidding collusion, such as Figure 1 As shown, the method for identifying bid rigging behavior may include the following steps S101 to S103:

[0064] Step S101, extracting unstructured data of multiple bidding documents in batches, obtaining bidding document information and personnel information, and storing them in a database;

[0065] Step S102, mining the abnormal correlation between the bidding document information and the personnel information in the database to identify the bidding collusion behavior of the bidders;

[0066] Step S103, sending the bidders' collusion bidding behavior identification results to the display unit for centralized display.

[0067] In this embodiment, unstructured data refers to data that does not conform to a fixed format or pattern. Unlike structured data, unstructured data has no predefined data model, so it is difficult to represent it using a database table.

[0068] This embodiment obtains bidding document information and personnel information by batch extracting unstructured data of multiple bidding documents, and stores them in a database; then it mines the abnormal correlation between the bidding document information and personnel information in the database, identifies the bidders' collusion in bidding, and can accurately and efficiently identify the collusion in bidding, thereby solving the problem of low efficiency in manually reviewing bidding documents and difficulty in discovering hidden collusion in bidding by bidders; moreover, this application can send the bidders' collusion in bidding behavior identification results to a display unit for centralized display, thereby facilitating the review of collusion in bidding.

[0069] The present application provides a possible implementation method. The multiple bidding documents mentioned in step S101 above are scanned copies in PDF format. The full name of PDF here is Portable Document Format, which is a portable document format used to display documents, including text, images, tables, styles and layouts. PDF files can maintain the original format and content of the file, so that it is consistent on different devices and operating systems.

[0070] The above step S101 extracts unstructured data of multiple bidding documents in batches, obtains bidding document information and personnel information, and stores them in a database, which may specifically include the following steps A1 to A3:

[0071] Step A1, calling the PDF bidding document unstructured data extraction program to achieve large-scale data extraction; wherein, the PDF bidding document unstructured data extraction program parses the bidding document structure through a python program, extracts tables and pictures in the PDF file, and then performs OCR recognition to obtain text data;

[0072] Step A2, executing the PDF bidding document unstructured data extraction program, batch extracting unstructured data of multiple bidding documents, and obtaining bidding document information and personnel information;

[0073] Step A3: Store the bidding document information and personnel information as structured data in the database as a basis for further data analysis.

[0074] In this embodiment, Python is a widely used high-level programming language that supports multiple programming paradigms, such as object-oriented, imperative, functional, and procedural programming.

[0075] OCR stands for Optical Character Recognition, which is a technology that converts text in an image into machine-readable text. Through OCR technology, the text content in scanned documents, photos or other images can be converted into editable and searchable text format.

[0076] This embodiment executes the unstructured data extraction program of the PDF bidding document, identifies and extracts the tables and pictures in the PDF file by parsing the structure of the bidding document; then, the program executes the OCR technology to convert the text data in the picture into an editable and searchable text format, which improves the accuracy and efficiency of data extraction.

[0077] A possible implementation method is provided in an embodiment of the present application. The bidding document information mentioned in the above embodiment may include bidding batches, bid package names, bid package numbers, bidder names, etc. The personnel information may include the names of the personnel and the ID numbers of the personnel. The personnel may include legal representatives, authorized agents, contacts, project leaders, project members, etc., and this embodiment does not impose any restrictions on this.

[0078] The above step S102 mines the abnormal correlation between the bidding document information and the personnel information in the database to identify the bidders' bidding collusion behavior, which may specifically include the following steps B1:

[0079] Step B1: Use the structured analysis capabilities of the SQL language to build a bidder collusion behavior identification model, and deeply analyze the relationship between the bidding batch, bid package name, bid package number, bidder name, legal representative, entrusted agent, contact person, project leader, and project members;

[0080] Among them, the bidders' collusion bidding behavior identification model is:

[0081] For different bidding documents of the same bid package, at least one of the names and ID numbers of the legal representative, authorized agent, contact person, project leader, and project member stated in each bidding document has a non-empty intersection. The formula is as follows:

[0082]

[0083] In formula (1), F A 、F B , F are bidder A, bidder B and the collection of all bidders, respectively, and all have the attributes of the name and ID number of the legal representative, the authorized agent, the contact person, the project leader and the project members; F AB is the intersection of the attributes of bidder A and bidder B; Φ is an empty set;

[0084] When formula (1) is satisfied, it is identified that bidders A and B have engaged in bidding collusion, which constitutes a bidding collusion situation.

[0085] In this embodiment, the full name of SQL is Structured Query Language, which is a standard programming language for managing and operating relational databases. It allows users to query, update, insert and delete data in the database.

[0086] This embodiment uses the bidder collusion behavior identification model to reliably, accurately and efficiently identify collusion in bidding, thereby solving the problem of low efficiency in manually reviewing bidding documents and difficulty in discovering hidden collusion in bidding.

[0087] In the embodiment of the present application, a possible implementation method is provided. In the above step A2, the unstructured data extraction program of the PDF bidding document is executed to batch extract the unstructured data of multiple bidding documents to obtain the bidding document information and personnel information. Specifically, the following steps A21 to A24 may be included:

[0088] Step A21, storing the picture bytes stream data in the form of a memory variable;

[0089] Step A22, obtaining multiple bidding documents and constructing a bidding document list;

[0090] file_list=[file_1,file_2,...,file_n] (2)

[0091] In formula (2), file_list is the bidding document list; file_1, file_2, ..., file_n are bidding documents;

[0092] Step A23, input the PDF file, output the picture bytes stream, and obtain the picture bytes stream of the PDF file;

[0093]

[0094] In formula (3), pdffile is the bidding file variable, i.e., PDF file; file_list is the pdffile collection; function_pdftobytes is the function that converts pdffile into a picture bytes stream;

[0095] Step A24, obtaining the OCR recognition result of the image bytes stream, and extracting the bidding document information and personnel information data;

[0096] pdf_json{pdffile}=[data_a,data_b] (4)

[0097] In formula (4), pdf_json{pdffile} is the OCR recognition result of the image bytes stream; data_a is the bidding batch, bid package name, bid package number, and bidder name; data_b is the name and ID number of the legal representative, authorized agent, contact person, project leader, and project member;

[0098] By using the multi-core concurrent mechanism and giving full play to the computing power of the multi-core CPU (Central Processing Unit), equations (3) and (4) are calculated in multi-core concurrent manner to improve the efficiency of data extraction from bidding documents.

[0099] In the above step A3, the bidding document information and personnel information are stored in the database as structured data, which may specifically include the following steps A31:

[0100] Step A31, connect to the database and write the data of pdf_json{pdffile} into the database.

[0101] In this embodiment, bytes is a basic unit of data storage and is generally used to measure the size of data, such as file size, memory capacity, etc.

[0102] This embodiment can realize the automatic processing of large quantities of PDF bidding documents, saving the time and cost of manual data extraction.

[0103] The present application provides a possible implementation method. The above step S102 mines the abnormal correlation between the bidding document information and the personnel information in the database to identify the bidders' collusion in bidding, which may specifically include the following steps C1:

[0104] Step C1, based on the bidding batch, bid package name, bid package number, and bidder name, aggregate calculation is performed on the names and ID numbers of the legal representative, entrusted agent, contact person, project leader, and project members. The SQL model formula is as follows:

[0105]

[0106] In formula (5), name is the name of the legal representative, authorized agent, contact person, project leader, and project member recorded in data_b; id_card is the ID number of the legal representative, authorized agent, contact person, project leader, and project member recorded in data_b; f count(data_a) is an aggregation function that counts personnel information; Formula (5) means that for the same bid package, if the number of bid documents that have been deduplicated and are associated with a certain name or ID number exceeds 1, then the name or ID number appears in different bid documents, indicating that the legal representative, or the authorized agent, or the contact person, or the project leader, or the project member stated in the bid documents of different bidders is the same person;

[0107] When formula (5) is satisfied, the bidders’ collusion in bidding is identified, which constitutes a situation of bidders’ collusion in bidding;

[0108] The SQL model described in formula (5) is a data analysis method for presenting the bidder collusion behavior identification model described in formula (1).

[0109] This embodiment uses the SQL model to reliably, accurately and efficiently identify bidding collusion, and solves the problem that manual review of bidding documents is inefficient and difficult to discover hidden bidding collusion among bidders.

[0110] It should be noted that the size of the sequence number of each step in the above embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. In practical applications, all the above possible implementation methods can be combined in any way to form possible embodiments of the present application, which will not be described one by one here.

[0111] Based on the methods for identifying collusive bidding provided in the above embodiments, and based on the same inventive concept, an embodiment of the present application also provides a device for identifying collusive bidding.

[0112] Figure 2 is a structural diagram of a bidding rigging identification device provided in an embodiment of the present application. Figure 2 As shown, the device for identifying bid rigging behavior may specifically include an acquisition module 210 , an identification module 220 and a display module 230 .

[0113] The acquisition module 210 is used to batch extract the unstructured data of multiple bidding documents, obtain the bidding document information and personnel information, and store them in the database;

[0114] Identification module 220, used to mine abnormal correlations between bidding document information and personnel information in the database, and identify bidders' collusion in bidding;

[0115] The display module 230 is used to send the results of identifying the bidders' collusion in bidding to the display unit for centralized display.

[0116] In an embodiment of the present application, a possible implementation method is provided, where the multiple bidding documents are scanned copies in PDF format; the acquisition module 210 is further used to:

[0117] Calling the unstructured data extraction program of PDF bidding documents to realize large-scale data extraction; wherein, the unstructured data extraction program of PDF bidding documents parses the bidding document structure through a python program, extracts the tables and pictures in the PDF file, and then performs OCR recognition to obtain text data;

[0118] Execute the unstructured data extraction program of the PDF bidding documents, extract the unstructured data of multiple bidding documents in batches, and obtain the bidding document information and personnel information;

[0119] The bidding document information and personnel information are stored in the database as structured data, which serves as the basis for further data analysis.

[0120] In the embodiment of the present application, a possible implementation method is provided, in which the bidding document information includes the bidding batch, the bid package name, the bid package number, and the bidder name; the personnel information includes the name and ID number of the personnel, and the personnel include the legal representative, the authorized agent, the contact person, the project leader, and the project member; the identification module 220 is also used for:

[0121] Using the structured analysis capabilities of the SQL language, we built a bidder collusion behavior identification model, and deeply analyzed the relationship between the bidding batch, bid package name, bid package number, bidder name, legal representative, entrusted agent, contact person, project leader, and project members;

[0122] Among them, the bidders' collusion bidding behavior identification model is:

[0123] For different bidding documents of the same bid package, at least one of the names and ID numbers of the legal representative, authorized agent, contact person, project leader, and project member stated in each bidding document has a non-empty intersection. The formula is as follows:

[0124]

[0125] In formula (1), F A 、F B , F are bidder A, bidder B and the collection of all bidders, respectively, and all have the attributes of the name and ID number of the legal representative, the authorized agent, the contact person, the project leader and the project members; F AB is the intersection of the attributes of bidder A and bidder B; Φ is an empty set;

[0126] When formula (1) is satisfied, it is identified that bidders A and B have engaged in bidding collusion, which constitutes a bidding collusion situation.

[0127] A possible implementation method is provided in an embodiment of the present application, wherein the acquisition module 210 is further configured to:

[0128] Store the image bytes stream data in the form of memory variables;

[0129] Get multiple bidding documents and build a bidding document list;

[0130] file_list=[file_1,file_2,...,file_n] (2)

[0131] In formula (2), file_list is the bidding document list; file_1, file_2, ..., file_n are bidding documents;

[0132] Input PDF file, output image bytes stream, get the image bytes stream of PDF file;

[0133]

[0134] In formula (3), pdffile is the bidding file variable, i.e., PDF file; file_list is the pdffile collection; function_pdftobytes is the function that converts pdffile into a picture bytes stream;

[0135] Obtain the OCR recognition results of the image bytes stream and extract the bidding document information and personnel information data;

[0136] pdf_json{pdffile}=[data_a,data_b] (4)

[0137] In formula (4), pdf_json{pdffile} is the OCR recognition result of the image bytes stream; data_a is the bidding batch, bid package name, bid package number, and bidder name; data_b is the name and ID number of the legal representative, authorized agent, contact person, project leader, and project member;

[0138] By using the multi-core concurrent mechanism and giving full play to the computing power of multi-core CPUs, equations (3) and (4) are calculated in multi-core concurrent manner to improve the efficiency of data extraction from bidding documents.

[0139] Connect to the database and write the data of pdf_json{pdffile} into the database.

[0140] A possible implementation method is provided in an embodiment of the present application, wherein the identification module 220 is further configured to:

[0141] Based on the bidding batch, bid package name, bid package number, and bidder name, the names and ID numbers of the legal representative, entrusted agent, contact person, project leader, and project members are aggregated and calculated. The SQL model formula is as follows:

[0142]

[0143] In formula (5), name is the name of the legal representative, authorized agent, contact person, project leader, and project member recorded in data_b; id_card is the ID number of the legal representative, authorized agent, contact person, project leader, and project member recorded in data_b; f count (data_a) is an aggregation function that counts personnel information; Formula (5) means that for the same bid package, if the number of bid documents that have been deduplicated and are associated with a certain name or ID number exceeds 1, then the name or ID number appears in different bid documents, indicating that the legal representative, or the authorized agent, or the contact person, or the project leader, or the project member stated in the bid documents of different bidders is the same person;

[0144] When formula (5) is satisfied, the bidders’ collusion in bidding is identified, which constitutes a situation of bidders’ collusion in bidding;

[0145] The SQL model described in formula (5) is a data analysis method for presenting the bidder collusion behavior identification model described in formula (1).

[0146] Based on the same inventive concept, an embodiment of the present application also provides a system for identifying collusive bidding. Figure 3 is a structural diagram of a bidding rigging identification system provided in an embodiment of the present application. Figure 3 As shown, the bidding rigging identification system may specifically include a network connection unit 310 , a storage unit 320 , an execution unit 330 and a display unit 340 .

[0147] A network connection unit 310 is used to establish a network connection with a database server;

[0148] Storage unit 320, used for storing data and programs;

[0149] The execution unit 330 is used to read and execute the program of the storage unit, batch extract the unstructured data of multiple bidding documents, obtain the bidding document information and personnel information, and store them in the database; mine the abnormal correlation between the bidding document information and personnel information in the database, and identify the bidding collusion behavior of the bidders;

[0150] The display unit 340 is used to display the results of identifying the bidders' collusion in bidding.

[0151] In a specific embodiment, see Figure 4 , the identification method of bidding rigging behavior may include the following steps:

[0152] Step 1: Start the bidding rigging identification system;

[0153] Step 2, run the PDF bidding document unstructured data extraction program;

[0154] Step 3, obtaining bidding document information and personnel information, and storing them in the database;

[0155] Step 4, connect to the database server, interact with the database, obtain the bidding document information and personnel information in the database, and determine whether the connection is successful; if failed, end; if successful, continue to step 5;

[0156] Step 5: mining the abnormal correlation between the bidding document information and personnel information in the database to identify the bidding collusion behavior of bidders;

[0157] Step 6: Display the bidders’ collusion in bidding behavior identification result information.

[0158] This embodiment can accurately and efficiently identify collusive bidding behavior, solving the problem of low efficiency in manually reviewing bidding documents and difficulty in discovering hidden collusive bidding behavior among bidders; moreover, this embodiment can display the identification result information of the collusive bidding behavior of bidders, making it convenient to review the collusive bidding behavior.

[0159] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a display, wherein the memory stores a computer program, the processor executes the computer program, and the display displays the results of identifying collusive bidding behavior of bidders; when the computer program is executed by the processor, a method for identifying collusive bidding behavior of any of the above embodiments is implemented.

[0160] In an exemplary embodiment, an electronic device is provided, such as Figure 5 As shown, Figure 5 The electronic device 500 shown includes: a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the electronic device 500 may also include a transceiver 504. It should be noted that in actual applications, the transceiver 504 is not limited to one, and the structure of the electronic device 500 does not constitute a limitation on the embodiments of the present application.

[0161] Processor 501 may be a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0162] The bus 502 may include a path to transmit information between the above components. The bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0163] The memory 503 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0164] The memory 503 is used to store the computer program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the computer program code stored in the memory 503 to implement the contents shown in the above method embodiment.

[0165] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0166] Based on the same inventive concept, an embodiment of the present application further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the method for identifying collusive bidding behavior of any of the above embodiments when running.

[0167] Based on the same inventive concept, an embodiment of the present application further provides a computer program product, including a computer program, characterized in that the computer program is configured to execute the method for identifying collusive bidding behavior of any of the above embodiments when running.

[0168] Those skilled in the art can clearly understand that the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the aforementioned method embodiments, and for the sake of brevity, they are not further described here.

[0169] Those skilled in the art can understand that the technical solution of the present application can be essentially or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, which includes a number of program instructions, so that an electronic device (such as a personal computer, a server, or a network device, etc.) executes all or part of the steps of the method described in each embodiment of the present application when running the program instructions. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0170] Alternatively, all or part of the steps of implementing the aforementioned method embodiments may be accomplished by hardware associated with program instructions (such as electronic devices such as personal computers, servers, or network devices), and the program instructions may be stored in a computer-readable storage medium. When the program instructions are executed by a processor of an electronic device, the electronic device executes all or part of the steps of the methods described in the embodiments of the present application.

[0171] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that within the spirit and principles of the present application, they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate from the protection scope of the present application.

Claims

1. A method for identifying bidding rigging, It is characterized in that The method comprises: Extract unstructured data from multiple bidding documents in batches, obtain bidding document information and personnel information, and store them in the database; Mining the abnormal correlation between bidding document information and personnel information in the database to identify bidders’ collusion in bidding; The results of identifying the bidders' collusion in bidding are sent to the display unit for centralized display.

2. The method according to claim 1, It is characterized in that Multiple bidding documents are scanned copies in PDF format; The batch extraction of unstructured data of multiple bidding documents, obtaining bidding document information and personnel information, and storing them in a database includes: Calling the unstructured data extraction program of PDF bidding documents to realize large-scale data extraction; wherein, the unstructured data extraction program of PDF bidding documents parses the bidding document structure through a python program, extracts the tables and pictures in the PDF file, and then performs OCR recognition to obtain text data; Execute the unstructured data extraction program of the PDF bidding documents, extract the unstructured data of multiple bidding documents in batches, and obtain the bidding document information and personnel information; The bidding document information and personnel information are stored in the database as structured data, which serves as the basis for further data analysis.

3. The method according to claim 1 or 2, It is characterized in that The bidding document information includes the bidding batch, bid package name, bid package number, and bidder name; the personnel information includes the name and ID number of the personnel, including the legal representative, authorized agent, contact person, project leader, and project members; The mining of abnormal correlations between bidding document information and personnel information in the database to identify bidders' bidding collusion behavior includes: Using the structured analysis capabilities of the SQL language, we built a bidder collusion behavior identification model, and deeply analyzed the relationship between the bidding batch, bid package name, bid package number, bidder name, legal representative, entrusted agent, contact person, project leader, and project members; Among them, the bidders' collusion bidding behavior identification model is: For different bidding documents of the same bid package, at least one of the names and ID numbers of the legal representative, authorized agent, contact person, project leader, and project member stated in each bidding document has a non-empty intersection. The formula is as follows: In formula (1), F A 、F B , F are bidder A, bidder B and the collection of all bidders, and all have the attributes of the name and ID number of the legal representative, the authorized agent, the contact person, the project leader and the project members; F AB is the intersection of the attributes of bidder A and bidder B; Φ is an empty set; When formula (1) is satisfied, it is identified that bidders A and B have engaged in bidding collusion, which constitutes a bidding collusion situation.

4. The method according to claim 3, It is characterized in that Execute the unstructured data extraction program of the PDF bidding documents to batch extract the unstructured data of multiple bidding documents and obtain the bidding document information and personnel information, including: Store the image bytes stream data in the form of memory variables; Get multiple bidding documents and build a bidding document list; file_list=[file_1,file_2,...,file_n] (2) In formula (2), file_list is the bidding document list; file_1, file_2, ..., file_n are bidding documents; Input PDF file, output image bytes stream, get the image bytes stream of PDF file; In formula (3), pdffile is the bidding file variable, i.e., PDF file; file_list is the pdffile collection; function_pdftobytes is the function that converts pdffile into a picture bytes stream; Obtain the OCR recognition results of the image bytes stream and extract the bidding document information and personnel information data; pdf_json{pdffile}=[data_a,data_b] (4) In formula (4), pdf_json{pdffile} is the OCR recognition result of the image bytes stream; data_a is the bidding batch, bid package name, bid package number, and bidder name; data_b is the name and ID number of the legal representative, authorized agent, contact person, project leader, and project member; By using the multi-core concurrent mechanism and giving full play to the computing power of multi-core CPUs, equations (3) and (4) are calculated in multi-core concurrent manner to improve the efficiency of data extraction from bidding documents. The bidding document information and personnel information are stored in the database as structured data, including: Connect to the database and write the data of pdf_json{pdffile} into the database.

5. The method according to claim 4, It is characterized in that Mining the abnormal correlation between bidding document information and personnel information in the database to identify bidders’ collusion in bidding, including: Based on the bidding batch, bid package name, bid package number, and bidder name, the names and ID numbers of the legal representative, entrusted agent, contact person, project leader, and project members are aggregated and calculated. The SQL model formula is as follows: In formula (5), name is the name of the legal representative, authorized agent, contact person, project leader, and project member recorded in data_b; id_card is the ID number of the legal representative, authorized agent, contact person, project leader, and project member recorded in data_b; f count (data_a) is an aggregation function that counts personnel information; Formula (5) means that for the same bid package, if the number of bid documents that have been deduplicated and are associated with a certain name or ID number exceeds 1, then the name or ID number appears in different bid documents, indicating that the legal representative, or the authorized agent, or the contact person, or the project leader, or the project member stated in the bid documents of different bidders is the same person; When formula (5) is satisfied, the bidders’ collusion in bidding is identified, which constitutes a situation of bidders’ collusion in bidding; The SQL model described in formula (5) is a data analysis method for presenting the bidder collusion behavior identification model described in formula (1).

6. A device for identifying bidding rigging, It is characterized in that The device comprises: The acquisition module is used to batch extract the unstructured data of multiple bidding documents, obtain the bidding document information and personnel information, and store them in the database; Identification module, used to mine the abnormal correlation between bidding document information and personnel information in the database, and identify the bidding collusion behavior of bidders; The display module is used to send the results of identifying the bidders' collusion in bidding to the display unit for centralized display.

7. A system for identifying bidding rigging, It is characterized in that The system comprises: A network connection unit, used for establishing a network connection with a database server; Storage unit, used to store data and programs; The execution unit is used to read and execute the program of the storage unit, batch extract the unstructured data of multiple bidding documents, obtain the bidding document information and personnel information, and store them in the database; mine the abnormal correlation between the bidding document information and personnel information in the database, and identify the bidding collusion behavior of bidders; The display unit is used to display the results of identifying the bidders' collusion in bidding.

8. An electronic device, It is characterized in that The method comprises a memory, a processor and a display, wherein the memory stores a computer program, the processor executes the computer program, and the display displays the results of identifying the collusive bidding behavior of bidders; when the computer program is executed by the processor, the steps of the method described in any one of claims 1 to 5 are implemented.

9. A storage medium, It is characterized in that The storage medium stores a computer program, wherein the computer program is configured to execute the steps of any one of the methods of claims 1 to 5 when executed.

10. A computer program product comprising a computer program, It is characterized in that The computer program is configured to execute the steps of the method according to any one of claims 1 to 5 when executed.