Recognition method and device of bidding behavior, electronic equipment and storage medium

Abstract

The invention belongs to the field of bidding identification, and particularly relates to a bidding behavior identification method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining historical bidding data, training a preset natural language model based on the historical bidding data, and obtaining a preprocessing model; acquiring to-be-identified bidder data, preprocessing the to-be-identified bidder data based on the preprocessing model, and determining pre-query data; and based on the pre-query data and a preset data warehouse, determining a comparison result through comparative analysis. According to the method and the device, traditional manual bidding data auditing can be replaced by an informatization means, bidding risk early warning is provided in a front-end registration link of a bidding activity, the accuracy is improved, the efficiency is improved, and the error-tolerant rate of a later project is effectively increased.

Description

Technical Field

[0001] The present application belongs to the field of bid identification, and in particular, relates to a method, device, electronic device and storage medium for identifying bid rigging. Background Art

[0002] During the project bidding process, examining whether there is any collusion in bidding among the bidders is one of the key points of the bidding. Traditional bidding review methods mainly inquire whether there is a controlling or management relationship between the bidders, or whether there are directors, supervisors, or personnel overlap, etc. However, they often overlook the situations in which the handling personnel or reserved contact information are similar or overlapped during the bidding process. Such situations require manual review and comparison to see whether the authorized representatives or handling personnel of different bidders in each link of the bidding are similar, and whether the telephone numbers and email addresses are the same.

[0003] Manual review of relevant bid rigging and collusion requires a lot of manpower and material resources. At the same time, there is a certain probability that the situation cannot be identified, and the accuracy is difficult to guarantee, which greatly increases the risk of bid rigging and collusion in projects.

[0004] Therefore, finding an automated and intelligent method to analyze the potential risks of bid rigging and collusion in the bidding process has become an urgent problem that needs to be solved. Summary of the invention

[0005] The present application provides a method, device, electronic device and storage medium for identifying bid rigging and collusion, which can quickly analyze whether there is a risk of bid rigging and collusion among existing suppliers after the suppliers submit their bidding materials.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying and determining bid-rigging behavior, the method comprising: obtaining bidder data to be identified, the bidder data comprising: supplier name, contact person, contact number, and email address; performing preprocessing based on the bidder data to determine pre-query data, the preprocessing comprising source processing and commonality processing; determining a comparison result through comparative analysis based on the pre-query data and a preset data warehouse, the comparative analysis comprising: comparison of the same bidding project, comparison of different bidding projects of the same bidding unit, and comparison of different bidding projects of different bidding units, the comparison result is used to identify the bid-rigging behavior of the bidder; based on the comparison result, determining the bid-rigging risk level of the bidder data, the bid-rigging risk level is divided into high risk warning, medium risk warning, low risk warning, and no risk warning.

[0007] In a possible implementation, the source-posting processing of the bidder data includes: extracting key information of the bidder data through a preset natural language processing model based on the bidder data; identifying erroneous information and repeated information in the key information through a BERT model based on the key information, and determining correction data; and determining rule data based on the correction data and preset rules.

[0008] In a possible implementation, the method before extracting key information of the bidder data through a natural language processing model also includes: obtaining bidder sample data, wherein the bidder sample data is historical bidder sample data; performing a first training on the original natural language processing based on the bidder sample data to determine a preliminary training model; labeling the bidder sample data to determine the labeled data; and performing a second training based on the labeled data and the preliminary training model to determine the preset natural language processing model.

[0009] In one possible implementation, common processing of rule data includes: based on the rule data, removing noise, duplicate values ​​and abnormal values ​​in the rule data to determine the cleaned data; based on the cleaned data, converting the data format to determine the formatted data; based on the formatted data, standardizing the numerical data, removing stop words and performing word segmentation operations on the text data to obtain the pre-query data.

[0010] In a possible implementation, based on the pre-query data and the preset data warehouse, through comparison with the same bidding project, the comparison results are determined to include: when any of the contact phone number or the email address is the same, it is judged as a high-risk warning; when the contact person is the same but the contact phone number and the email address are different, it is judged as a low-risk warning.

[0011] In a possible implementation, based on the pre-query data and the preset data warehouse, by comparing different bidding projects of the same bidding unit, the comparison results are determined to include: when the supplier name and the contact person are different, but the email address and the contact number are the same, a risk warning is issued; when the supplier name is different, but the contact person, the email address and the contact number are the same, a risk warning is issued; when the supplier name is the same, but the contact person, the email address and the contact number are different, it is judged to be risk-free; when the supplier name, the email address and the contact number are different, but the contact person is the same, it is judged to be a low-risk warning.

[0012] In a possible implementation, based on the pre-query data and the preset data warehouse, through comparison of different bidding projects of different bidding units, the comparison results are determined to include: the supplier name and the contact person are different, the contact number and the email address are the same, and it is judged as a low risk warning; the supplier name is different, the contact person, the contact number and the email address are the same, and it is judged as a low risk warning; the supplier name is the same, the contact person, the email address and the contact number are different, and it is judged as no risk; the supplier name, the email address and the contact number are different, and the contact person is the same, and it is judged as a low risk warning.

[0013] In the second aspect, an embodiment of the present application provides a device for identifying bid-rigging and collusion, the device comprising: an acquisition module, used to acquire bidder data to be identified, the bidder data comprising: supplier name, contact person, contact number, and email address; a conversion module, used to perform pre-processing based on the bidder data to determine pre-query data, the pre-processing comprising source processing and common processing; a processing module, used to determine a comparison result through comparative analysis based on the pre-query data and a preset data warehouse, the comparative analysis comprising: comparison of the same bidding project, comparison of different bidding projects of the same bidding unit, and comparison of different bidding projects of different bidding units, the comparison result is used to identify the bid-rigging and collusion behavior of the bidder; an early warning module, used to determine the bid-rigging and collusion risk level of the bidder data based on the comparison result, the bid-rigging and collusion risk level is divided into high-risk warning, medium-risk warning, low-risk warning, and no-risk warning.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in the first aspect or any one of the implementation methods thereof is implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect or any one of the implementation methods thereof is implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, the electronic device executes the method described in the first aspect or any one of the implementation methods thereof.

[0017] The solution provided by this application obtains the supplier name, contact person, contact number, email address and other data to be processed, and determines the pre-query data through pre-processing, wherein the pre-processing includes source processing and common processing; based on the pre-query data, the comparison result is determined by comparing and analyzing with the existing data in the data warehouse; based on the comparison result, it is determined whether the supplier is suspected of bid rigging or collusion. This application can intuitively display whether there is any similar key information of personnel in the current registered supplier, and provides a risk warning of bid rigging or collusion in the front-end registration link of the bidding activity, which effectively increases the fault tolerance rate of the later projects, and at the same time efficiently and high-quality solves the disadvantages of low efficiency and omissions in manual review. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 any creative work.

[0019] Figure 1 A flowchart of a method for identifying bid-rigging behavior provided in one embodiment of the present application;

[0020] Figure 2 A structural block diagram of a device for identifying bid-rigging behavior provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0024] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0026] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0028] Figure 1 A flowchart of a method for identifying bid-rigging behavior provided in an embodiment of the present application is provided, and the method includes:

[0029] S110, obtaining the bidder data to be identified, the bidder data including: supplier name, contact person, contact number, and email address.

[0030] Furthermore, the bidder data also includes qualification certificates, supplier office addresses, and other data that can describe the supplier as detailed as possible at the data level.

[0031] S120, pre-processing is performed based on the bidder data to determine pre-query data, and the pre-processing includes source processing and common processing.

[0032] In one possible implementation, the source processing of the bidder data includes: based on the bidder data, extracting key information of the bidder data through a natural language processing model; based on the key information, identifying erroneous information and duplicate information in the key information through a BERT model, and determining correction data; based on the correction data and preset rules, determining rule data.

[0033] Exemplarily, a generative pre-trained language model (Generative Pre-trained Transformer, GPT) is used to perform semantic recognition on the bidder's data; then a pre-trained deep learning model (Bidirectional Encoder Representations from Transformers, BERT) is used to identify erroneous and repeated information in the key information of the bidder's data, and the semantic recognition results of GPT can be verified twice; finally, data that conforms to the original intention and is standardized is obtained.

[0034] As another example, use Python to write code to extract data, use libraries such as pandas and sqlalchemy to read data, and combine regular expressions to obtain original and standardized data.

[0035] In one possible implementation, common processing of rule data includes: based on the rule data, removing noise, duplicate values ​​and abnormal values ​​in the rule data to determine the cleaned data; based on the cleaned data, converting the data format to determine the formatted data; based on the formatted data, standardizing the numerical data, removing stop words and performing word segmentation operations on the text data to obtain pre-query data.

[0036] Exemplarily, a data extraction and transformation tool (Extract, Transform, Load, ETL) is used to process the rule data that has been processed at the source, including: removing duplicate data, processing missing values ​​(such as by filling the mean, median or inferring based on context, etc.), and identifying and correcting outliers; then the data is converted into a unified format, such as lowercase English letters after the "@" symbol in the email format, converting string type numbers to numeric types, etc.; further, the data is standardized using a standardization algorithm, such as: Z-Score standardization method, so that the data is analyzed on a unified scale, and finally the pre-query data is obtained.

[0037] S130, determining a comparison result through comparative analysis based on the pre-query data and the preset data warehouse.

[0038] Exemplarily, the preset data warehouse is used to store historical bidder data.

[0039] In a possible implementation, by comparing the same bidding project, the comparison results include: when any of the contact phone number or email address information is the same, it is judged as a high-risk warning; when the contact person is the same but the contact and email address are different, it is judged as a low-risk warning.

[0040] Exemplarily, there are four situations as follows:

[0041] 1. The supplier name cannot enter the same data on the front end, so there is no identical data source.

[0042] 2. If the contact person has the same name, email address or phone number, the system will automatically issue a high-risk warning and determine that there is bid rigging.

[0043] 3. If the contact names are different but the email addresses or phone numbers are the same, the system will automatically issue a high-risk warning and determine that there is collusion in bidding.

[0044] 4. If the contact name is the same but the email address and telephone number are different, the system will trigger a low-risk warning, indicating that there may be a risk of bid collusion. Further reviewers are required to compare the registration information to see if the name is the same to make a final judgment.

[0045] In a possible implementation, by comparing different bidding projects of the same bidding unit, based on pre-query data and a preset data warehouse, the comparison results are determined, including: when the supplier name and contact person are different but the email address and contact number are the same, a risk warning is issued; when the supplier name is different but the contact person, email address and contact number are the same, a risk warning is issued; when the supplier name is the same but the contact person, email address and contact number are different, it is judged as no risk; when the supplier name, email address and contact number are different but the contact person is the same, it is judged as a low risk warning.

[0046] Exemplarily, there are four situations as follows:

[0047] 1. If the supplier name and contact name are different, but the email or contact number is the same, and different supplier names represented by the same data have appeared in a historical project, the system will automatically issue a high-risk warning and determine that there is a risk of bid rigging and collusion. If different supplier names represented by the same data have not appeared in the same historical project, the system will automatically issue a medium-risk warning and indicate that there is a risk of bid rigging and collusion. Further verification is required to determine whether the registrant information has changed.

[0048] 2. If the supplier names are different, the contact names are the same, the email addresses or contact numbers are the same, and the different supplier names represented by the same data have appeared in a historical project, the system will automatically issue a high-risk warning and determine that there is a risk of bid rigging and collusion. If the different supplier names represented by the same data have not appeared in the same historical project, the system will automatically issue a medium-risk warning and indicate that there is a risk of bid rigging and collusion. Further verification is required to determine whether the registrant has changed the company he / she is currently working for.

[0049] 3. No risk warning for suppliers with the same name.

[0050] 4. If the supplier name, email address and contact number are different but the contact name is the same, the system will trigger a low-risk warning, indicating that there may be a risk of bid collusion. Further reviewers are required to compare the registration information to see if there is a same name to make a final judgment.

[0051] In one possible implementation, based on pre-query data and a preset data warehouse, through comparison of different bidding projects of different bidding units, the comparison results are determined to include: the supplier name and contact person are different, but the contact number and email address are the same, which is judged as a low-risk warning; the supplier name is different, but the contact person, contact number and email address are the same, which is judged as a low-risk warning; the supplier name is the same, but the contact person, email address and contact number are different, which is judged as no risk; the supplier name, email address and contact number are different, but the contact person is the same, which is judged as a low-risk warning.

[0052] Exemplarily, there are four situations as follows:

[0053] 1. If the supplier name and contact name are different but the email address or telephone number is the same, the system will automatically issue a low-risk warning and determine that there is a possible risk of bid collusion. The reviewer must remind the tenderer of the risk.

[0054] 2. If the supplier names are different but the contact names, email addresses or phone numbers are the same, the system will automatically issue a low-risk warning and determine that there is a risk of bid collusion. The reviewer must remind the tenderer of the risk.

[0055] 3. No risk warning for suppliers with the same name.

[0056] 4. If the supplier name, email address and contact number are different but the contact name is the same, the system will trigger a low-risk warning, indicating that there may be a risk of bid collusion. Further reviewers are required to compare the registration information to see if there is a same name to make a final judgment.

[0057] For example, when a person (including natural persons and legal persons) holds a large proportion of shares in two or more subsidiaries and bids for different bidding projects of the same bidding unit through these subsidiaries, the bidders may have different supplier names and names, but the same contact information and email address. If different units represented by the same data do not appear in the same historical project, a risk reminder will be issued and it will be checked whether the registrant information has changed.

[0058] Furthermore, if different supplier names represented by the same data have appeared in the same historical project, the system will automatically issue a high-risk warning.

[0059] For example, if a contact person leaves one supplier and joins another supplier, and both suppliers happen to have participated in the same bidding project, it is possible that the supplier names of the suppliers are different, but the contact person's phone and email address are the same.

[0060] For example, if the contact person is the same but the supplier name, contact number and email address are different, there may be a duplicate name.

[0061] S140, based on the comparison results, determining the risk level of bid rigging and collusion in the bidders' data.

[0062] In one possible implementation, the risk levels of bid rigging are divided into high-risk warning, medium-risk warning, low-risk warning and no-risk warning. The higher the risk level of bid rigging, the greater the probability that the supplier is suspected of bid rigging.

[0063] Exemplarily, after receiving the results of the comparison, the key identical data is extracted and displayed in the early warning module, with red highlighting for high-risk warnings, yellow highlighting for medium-risk warnings, blue highlighting for low-risk warnings and no color highlighting for no risk to distinguish the suspected bid rigging in the early warnings.

[0064] Figure 2 This is a structural block diagram of a device for identifying bid-rigging behavior provided by an embodiment of the present application. For the sake of convenience, only the parts related to the embodiment of the present application are shown. Figure 2 The device 200 for identifying bid-rigging behavior includes an acquisition module 201 , a conversion module 202 , a processing module 203 , and an early warning module 204 .

[0065] The acquisition module 201 is used to acquire the bidder data to be identified, and the bidder data includes: supplier name, contact person, contact number, and email address.

[0066] The conversion module 202 is used to perform pre-processing based on the bidder data to determine pre-query data, wherein the pre-processing includes source processing and common processing.

[0067] Processing module 203 is used to determine the comparison result through comparative analysis based on the pre-query data and the preset data warehouse. The comparative analysis includes: comparison of the same bidding project, comparison of different bidding projects of the same bidding unit, and comparison of different bidding projects of different bidding units. The comparison result is used to identify the bid-rigging behavior of the bidder.

[0068] The early warning module 204 determines the risk level of bid rigging and collusion of the bidder data based on the comparison result, and the risk level of bid rigging and collusion is divided into high risk warning, medium risk warning, low risk warning and no risk warning.

[0069] The solution provided by this application obtains the supplier name, contact person, contact number, email address and other data to be processed, and determines the pre-query data through pre-processing, wherein the pre-processing includes source processing and common processing; based on the pre-query data, the comparison result is determined by comparing and analyzing with the existing data in the data warehouse; based on the comparison result, it is determined whether the supplier is suspected of bid rigging or collusion. This application can intuitively display whether there is any similar key information of personnel in the current registered supplier, and provides a risk warning of bid rigging or collusion in the front-end registration link of the bidding activity, which effectively increases the fault tolerance rate of the later projects, and at the same time efficiently and high-quality solves the disadvantages of low efficiency and omissions in manual review.

[0070] Figure 3 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, the electronic device 3 of this embodiment includes: at least one processor 30 ( Figure 3 Only one is shown in the figure) a processor, a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, and when the processor 30 executes the computer program 32, the steps in any of the above method embodiments are implemented.

[0071] The electronic device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of the electronic device 3 and does not constitute a limitation on the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0072] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0073] In some embodiments, the memory 31 may be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. In other embodiments, the memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 3. Further, the memory 31 may also include both an internal storage unit of the electronic device 3 and an external storage device. The memory 31 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0074] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0075] An embodiment of the present application also provides an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the computer program.

[0076] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0077] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0078] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0079] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0080] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0081] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] The embodiments described above 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, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for identifying bid-rigging behavior, characterized in that: The method comprises: Obtain the bidder data to be identified, the bidder data including: supplier name, contact person, contact number, and email address; Based on the bidder data, pre-processing is performed to determine pre-query data, wherein the pre-processing includes source processing and common processing; Based on the pre-query data and the preset data warehouse, a comparison result is determined through comparative analysis, wherein the comparative analysis includes: comparison of the same bidding project, comparison of different bidding projects of the same bidding unit, and comparison of different bidding projects of different bidding units, and the comparison result is used to identify the bid-rigging behavior of the bidder; Based on the comparison results, the risk level of bid rigging and collusion of the bidder data is determined, and the risk level of bid rigging and collusion is divided into high risk warning, medium risk warning, low risk warning and no risk warning.

2. The method according to claim 1, characterized in that The source processing of the bidder data includes: Based on the bidder data, extract key information of the bidder data by using a preset natural language processing model; Based on the key information, identifying erroneous information and duplicate information in the key information through a BERT model, and determining correction data; Based on the correction data and the preset rules, rule data is determined.

3. The method according to claim 2, characterized in that The common processing of the rule data includes: Based on the rule data, remove noise, duplicate values ​​and abnormal values ​​in the rule data to determine cleaned data; Based on the cleaned data, convert the data into a format to determine formatted data; Based on the formatted data, the numerical data is standardized, and the text data is subjected to stop word removal and word segmentation operations to obtain the pre-query data.

4. The method according to claim 1, characterized in that: Based on the pre-query data and the preset data warehouse, by comparing the same bidding project, the comparison results include: When any of the contact phone number or email address is the same, it is judged as a high-risk warning; when the contact person is the same but the contact phone number and email address are different, it is judged as a low-risk warning.

5. The method according to claim 1, characterized in that Based on the pre-query data and the preset data warehouse, by comparing different bidding projects of the same bidding unit, the comparison results are determined to include: when the supplier name and the contact person are different, but the email address and the contact number are the same, a risk warning is issued; when the supplier name is different, but the contact person, the email address and the contact number are the same, a risk warning is issued; when the supplier name is the same, but the contact person, the email address and the contact number are different, it is judged to be risk-free; when the supplier name, the email address and the contact number are different, but the contact person is the same, it is judged to be a low-risk warning.

6. The method according to claim 1, characterized in that Based on the pre-query data and the preset data warehouse, by comparing different bidding projects of different bidding units, the comparison results are determined to include: the supplier name and the contact person are different, the contact number and the email address are the same, and it is judged as a low risk warning; the supplier name is different, the contact person, the contact number and the email address are the same, and it is judged as a low risk warning; the supplier name is the same, the contact person, the email address and the contact number are different, and it is judged as no risk; the supplier name, the email address and the contact number are different, and the contact person is the same, and it is judged as a low risk warning.

7. The method according to claim 2, characterized in that Before extracting the key information of the bidder data by using a preset natural language processing model, the method further includes: Obtaining bidder sample data, wherein the bidder sample data is historical bidder sample data; Performing a first training on the original natural language processing based on the sample data of the bidder to determine a preliminary training model; Marking the sample data of the bidder and determining the marked data; Based on the labeled data and the preliminary training model, a second training is performed to determine the preset natural language processing model.

8. A device for identifying bid-rigging behavior, characterized in that: The device comprises: An acquisition module is used to acquire the bidder data to be identified, wherein the bidder data includes: supplier name, contact person, contact number, and email address; A conversion module, used for performing pre-processing based on the bidder data to determine pre-query data, wherein the pre-processing includes source processing and common processing; A processing module, configured to determine a comparison result through comparative analysis based on the pre-query data and the preset data warehouse, wherein the comparative analysis includes: comparison of the same bidding project, comparison of different bidding projects of the same bidding unit, and comparison of different bidding projects of different bidding units, and the comparison result is used to identify the bid-rigging behavior of the bidder; An early warning module is used to determine the risk level of bid rigging and collusion of the bidder data based on the comparison result, and the risk level of bid rigging and collusion is divided into high risk warning, medium risk warning, low risk warning and no risk warning.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images