Government purchase project risk level identification system and method based on big data

Abstract

The invention provides a government purchase project risk level identification system and method based on big data. The system comprises a risk data acquisition module, a purchase project creation module, a risk determination module and a risk prompt module. The risk data acquisition module is used for acquiring punishment and complaint information of historical government purchase projects and storing the information to the database; the purchase project creation module is used for creating a new purchase project and obtaining keyword information of the new purchase project; the risk judgment module is used for comparing the keyword information of the new purchase project with punishment and complaint information of historical government purchase projects in the database, and outputting a risk level according to a comparison result; the risk prompt module is used for receiving the risk level determined by the risk judgment module and displaying the project risk level and risk case information to a user; therefore, project risks are automatically identified and graded in a data-driven mode, related personnel are helped to pre-judge the risks in advance, and the fairness and efficiency of government purchase work are improved.

Description

Technical Field

[0001] The present application relates to the technical field of project risk assessment, and in particular to a government procurement project risk level identification system and method based on big data. Background Art

[0002] As an important part of public fiscal expenditure, the fairness, transparency and effectiveness of government procurement projects are directly related to the credibility of government departments and the rational allocation of fiscal resources. In actual operation, government procurement projects often encounter problems such as irregular procurement processes, supplier violations, frequent complaints and disputes, which may increase the risk of project implementation and affect procurement efficiency and effectiveness. Therefore, how to identify and evaluate the risk level of government procurement projects in advance so as to take corresponding risk control measures is an urgent problem to be solved in the current government procurement field.

[0003] In the existing technology, some risk assessment methods rely on manual experience and judgment, and lack systematic data analysis methods, which limits the accuracy and efficiency of risk identification. In addition, these methods usually require procurement personnel to manually screen and analyze a large amount of historical data, which is time-consuming and labor-intensive, and is prone to judgment errors due to the interference of subjective factors. With the development of big data technology, more and more government procurement data are digitized and stored, which makes it possible to realize risk identification of government procurement projects based on data analysis. However, how to effectively use these historical data to automatically identify the risk level of procurement projects and use them to provide support for procurement decisions is still a technical problem. Summary of the invention

[0004] The present application provides a government procurement project risk level identification system and method based on big data, which can automatically identify and grade project risks in a data-driven manner, help relevant personnel predict risks in advance, and improve the fairness and efficiency of government procurement work.

[0005] In the first aspect, the present application provides a government procurement project risk level identification system based on big data, including: a risk data collection module, a procurement project creation module, a risk determination module and a risk warning module;

[0006] The risk data collection module is used to obtain the penalty and complaint information of historical government procurement projects and store it in the database;

[0007] The procurement project creation module is used to create a new procurement project and obtain keyword information of the new procurement project;

[0008] The risk assessment module is used to compare the keyword information of the newly created procurement project with the penalty and complaint information of the historical government procurement projects in the database, and output the risk level according to the comparison results;

[0009] The risk warning module is used to receive the risk level determined by the risk determination module and display the project risk level and risk case information to the user.

[0010] Optionally, the risk assessment module is used to compare the keyword information of the newly created procurement project with the penalty and complaint information of the historical government procurement projects in the database, and output the risk level based on the comparison result, including: if no penalty or complaint case is matched, it is judged as low risk; if a penalty or complaint case is matched and the number of matches is less than N, it is judged as medium risk; if the number of matches is greater than N, it is judged as high risk.

[0011] The risk assessment module is used to compare the keyword information of the newly-built procurement project with the penalty and complaint information of the historical government procurement projects in the database, and output the risk level according to the comparison result, including: using the KMP algorithm to compare the keyword information of the newly-built procurement project with the project name and / or keywords in the database.

[0012] Optionally, the using of the KMP algorithm to compare the keyword information of the newly created procurement item with the item name and / or keyword in the database includes:

[0013] Step S1: construct a partial match table, wherein the partial match table, also called a prefix table or a longest common prefix and suffix table, is used to store the longest common prefix and suffix lengths of the substrings before each position in the keyword string, represented by an array next[j], each position is represented by a pointer j, and the pointer j is initialized to 0, pointing to the first character of the keyword string;

[0014] Step S2: Perform string matching on the keyword string and the text string, and initialize two pointers, i, j = 0, i points to the beginning of the text string in the database, and j points to the beginning of the keyword string;

[0015] Step S3: compare the keyword string and the text string character by character. If the current character matches, move the two pointers i and j at the same time. If the match reaches the end of the keyword string, that is, j==m, where m is the length of the keyword string, it means the match is successful. Record the starting position of the current successful match, and move i to the position i-m+1, that is, move to the next character position of the current successful match in the text string, and reset j to 0, and repeat this step.

[0016] Step S4: If the characters do not match, but j is not 0, update j to next[j] according to the partial match table, and i remains unchanged; if the characters do not match, and j is 0, move i one position to the right, reset j to 0, and return to step S3;

[0017] Step S5: When i exceeds the length of the text string, the starting position of the successful match is output. If no matching keyword string is found after the text string traversal is completed, a special value is returned to indicate that the match failed.

[0018] Optionally, the risk data collection module visits the national government procurement website according to a predetermined period, uses the API interface or web crawling technology provided by the website to obtain penalty and complaint information of historical government procurement projects, and stores it in the database.

[0019] The risk warning module can provide users with project risk levels by popping up a window or marking the project information page. The risk case information includes penalty and complaint cases that match the keywords of the newly created procurement project.

[0020] In the second aspect, the present application provides a method for identifying the risk level of government procurement projects based on big data, characterized in that the method comprises:

[0021] Step S100: Obtain the penalty and complaint information of historical government procurement projects and store them in the database;

[0022] Step S200: Create a new procurement project and obtain keyword information of the new procurement project;

[0023] Step S300, comparing the keyword information of the newly created procurement project with the penalty and complaint information of the historical government procurement projects in the database, and outputting the risk level according to the comparison result;

[0024] Step S400: Receive and prompt the user with the project risk level.

[0025] Compared with the prior art, this application has the following advantages:

[0026] The present invention provides a government procurement project risk level identification system and method based on big data, which realizes automatic identification of the risk level of new procurement projects by performing data analysis on the punishment and complaint information of historical government procurement projects. Compared with the traditional method that relies on manual experience, the system can automatically receive and prompt the risk level of the project, provide decision support for procurement bidding agents, and effectively reduce the subjective error of human judgment. By prompting the risk level and possible risk points, the bidding agent can study relevant government procurement cases before the bidding of the procurement project begins, improve their understanding and response capabilities of project risks, and thus lay the foundation for the smooth implementation of the project. Therefore, the present invention can automatically identify and classify project risks in a data-driven manner before the implementation of the government procurement project, help relevant personnel to predict risks in advance, and improve the fairness and efficiency of government procurement work. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0028] Figure 1 A schematic diagram of the architecture of a government procurement project risk level identification system based on big data provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of the steps of a method for identifying the risk level of a government procurement project based on big data provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of a user page of a procurement project creation module 200 provided in an embodiment of the present application;

[0031] Figure 4 A schematic diagram showing risk case information provided in an embodiment of the present application.

[0032] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0034] Figure 1 A schematic diagram of the architecture of a government procurement project risk level identification system based on big data provided in an embodiment of the present application.

[0035] First, refer to Figure 1 The embodiment of the present invention discloses a government procurement project risk level identification system based on big data, including: a risk data collection module 100, a procurement project creation module 200, a risk determination module 300 and a risk warning module 400.

[0036] The risk data collection module 100 is used to obtain the penalty and complaint information of historical government procurement projects and store it in the database.

[0037] For example, the risk data collection module 100 will visit the national government procurement website according to a predetermined period (such as daily, weekly or monthly), and use the API interface or web crawling technology provided by the website to extract the latest announcement information. After obtaining the data, the risk data collection module 100 will filter out items related to "administrative penalty decisions" and "complaint handling information announcements" based on a preset keyword list. Subsequently, the module 100 will conduct a detailed analysis of these items, extract information such as project names, keywords, complainants, penalty items, and complaint items, and store this information in the database for further risk analysis and evaluation.

[0038] The procurement project creation module 200 is used to create a new procurement project and obtain keyword information of the new procurement project.

[0039] Specifically, the user creates a new procurement project through the procurement project creation module 200 and inputs relevant information of the procurement project, wherein the relevant information of the procurement project includes the project name, keywords, project applicants, etc. For example, for a comfort supplies procurement project, the keyword information includes "comfort supplies".

[0040] The risk determination module 300 is used to compare the keyword information of the newly-built procurement project with the penalty and complaint information of the historical government procurement projects in the database, and output the risk level according to the comparison result.

[0041] The risk determination module 300 obtains the keyword information of the newly created procurement project through the procurement project creation module 200, compares the keyword information of the newly created procurement project with the project name and / or keyword in the database, and determines the comparison result, wherein the keyword matching algorithm may adopt, for example, the KMP algorithm, the Boyer-Moore algorithm, the Rabin-Karp algorithm, etc. If no penalty or complaint case is matched, it is determined to be low risk; if a penalty or complaint case is matched, and the number of matches is less than N, it is determined to be medium risk; if the number of matches is greater than N, it is determined to be high risk, wherein N can be determined based on experience, for example, N=3.

[0042] In some embodiments, the KMP algorithm is used to perform keyword matching, including:

[0043] Step S1: construct a partial match table, wherein the partial match table, also called a prefix table or a longest common prefix and suffix table, is used to store the longest common prefix and suffix lengths of the substrings before each position in the keyword string, represented by an array next[j], each position is represented by a pointer j, and the pointer j is initialized to 0, pointing to the first character of the keyword string;

[0044] Step S2: Perform string matching on the keyword string and the text string, and initialize two pointers, i, j = 0, i points to the beginning of the text string in the database, and j points to the beginning of the keyword string;

[0045] Step S3: compare the keyword string and the text string character by character. If the current character matches, move the two pointers i and j at the same time. If the match reaches the end of the keyword string, that is, j==m, where m is the length of the keyword string, it means the match is successful. Record the starting position of the current successful match, and move i to the position i-m+1, that is, move to the next character position of the current successful match in the text string, and reset j to 0, and repeat this step.

[0046] Step S4: If the characters do not match, but j is not 0, update j to next[j] according to the partial match table, and i remains unchanged; if the characters do not match, and j is 0, move i one position to the right, reset j to 0, and return to step S3;

[0047] Step S5: When i exceeds the length of the text string, the result of successful matching is output. If no matching keyword string is found after the text string traversal is completed, a special value is returned to indicate that the matching failed.

[0048] It can be understood that the text string is the project name and / or keyword data stored in the database.

[0049] The risk prompt module 400 is used to receive the risk level determined by the risk determination module 300 and display the project risk level and risk case information to the user.

[0050] For example, the risk warning module 400 can remind the user of the project risk level through a page pop-up window or by marking it on the project information page. The risk case information includes penalty and complaint cases that match the keywords of the newly created procurement project.

[0051] See also Figure 3 As shown, the newly created procurement project is a condolence procurement project. The procurement project creation module 200 obtains project related information according to user input. For example, the project keyword is "consolation gifts". At this time, the risk determination module 300 obtains the newly created procurement project keyword information through the procurement project creation module 200, compares the newly created procurement project keyword information with the project name and / or keyword in the database, and determines the comparison result. For example, this project is determined to be "medium risk", and "medium risk" is marked in the risk level column of the project information page, so as to remind the procurement bidding agent that they can study related cases through the risk case information displayed by the risk warning module 400, such as Figure 4 shown.

[0052] Second, refer to Figure 2 The embodiment of the present invention also discloses a method for identifying the risk level of government procurement projects based on big data, including:

[0053] S100, obtain the penalty and complaint information of historical government procurement projects and store it in the database;

[0054] S200, creating a new procurement project and obtaining keyword information of the new procurement project;

[0055] S300, compare the keyword information of the newly created procurement project with the penalty and complaint information of the historical government procurement projects in the database, and output the risk level according to the comparison results;

[0056] Specifically, the keyword information of the newly created procurement project is compared with the project name and / or keywords in the database to determine the comparison result. If no penalty or complaint case is matched, it is judged as low risk. If a penalty or complaint case is matched and the number of matches is less than N, it is judged as medium risk. If the number of matches is greater than N, it is judged as high risk, where N can be determined based on experience, for example, N=3.

[0057] S400: Receive and prompt the user with the project risk level.

[0058] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0059] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0060] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A government procurement project risk level identification system based on big data, characterized in that: include: A risk data collection module (100), a procurement project creation module (200), a risk determination module (300) and a risk warning module (400); A risk data collection module (100) is used to obtain penalty and complaint information of historical government procurement projects and store it in a database; The procurement project creation module (200) is used to create a new procurement project and obtain keyword information of the new procurement project; The risk determination module (300) is used to compare the keyword information of the newly-built procurement project with the penalty and complaint information of the historical government procurement projects in the database, and output the risk level according to the comparison result; The risk prompt module (400) is used to receive the risk level determined by the risk determination module (300) and display the project risk level and risk case information to the user.

2. According to the government procurement project risk level identification system based on big data according to claim 1, it is characterized in that: The risk determination module (300) is used to compare the keyword information of the newly-built procurement project with the penalty and complaint information of the historical government procurement projects in the database, and output the risk level according to the comparison result, including: if no penalty or complaint case is matched, it is judged as low risk; if a penalty or complaint case is matched and the number of matches is less than N, it is judged as medium risk; if the number of matches is greater than N, it is judged as high risk.

3. According to the government procurement project risk level identification system based on big data according to claim 1, it is characterized in that: The risk determination module (300) is used to compare the keyword information of the newly-built procurement project with the penalty and complaint information of the historical government procurement projects in the database, and output the risk level according to the comparison result, including: using the KMP algorithm to compare the keyword information of the newly-built procurement project with the project name and / or keywords in the database.

4. According to the government procurement project risk level identification system based on big data according to claim 3, it is characterized in that: The use of the KMP algorithm to compare the keyword information of the newly created procurement project with the project name and / or keyword in the database includes: Step S1: construct a partial match table, wherein the partial match table, also called a prefix table or a longest common prefix and suffix table, is used to store the longest common prefix and suffix lengths of the substrings before each position in the keyword string, represented by an array next[j], each position is represented by a pointer j, and the pointer j is initialized to 0, pointing to the first character of the keyword string; Step S2: Perform string matching on the keyword string and the text string, and initialize two pointers, i, j = 0, i points to the beginning of the text string in the database, and j points to the beginning of the keyword string; Step S3: compare the keyword string and the text string character by character. If the current character matches, move the two pointers i and j at the same time. If the match reaches the end of the keyword string, that is, j==m, where m is the length of the keyword string, it means the match is successful. Record the starting position of the current successful match, and move i to the position i-m+1, that is, move to the next character position of the current successful match in the text string, and reset j to 0, and repeat this step. Step S4: If the characters do not match, but j is not 0, update j to next[j] according to the partial match table, and i remains unchanged; if the characters do not match, and j is 0, move i one position to the right, reset j to 0, and return to step S3; Step S5: When i exceeds the length of the text string, the starting position of the successful match is output. If no matching keyword string is found after the text string traversal is completed, a special value is returned to indicate that the match failed.

5. The government procurement project risk level identification system based on big data according to claim 1 is characterized in that: The risk data collection module (100) visits the national government procurement website according to a preset period, uses the API interface or web page crawling technology provided by the website to obtain the penalty and complaint information of historical government procurement projects, and stores it in the database.

6. The government procurement project risk level identification system based on big data according to claim 1 is characterized in that: The risk warning module (400) prompts the user of the project risk level by means of a page pop-up window or by marking on the project information page.

7. The government procurement project risk level identification system based on big data according to claim 1 is characterized in that: The risk case information includes penalty and complaint cases that match the keywords of the new procurement project.

8. A method for identifying risk levels of government procurement projects based on big data, characterized in that: The method comprises: Step S100: Obtain the penalty and complaint information of historical government procurement projects and store them in the database; Step S200: Create a new procurement project and obtain keyword information of the new procurement project; Step S300, comparing the keyword information of the newly created procurement project with the penalty and complaint information of the historical government procurement projects in the database, and outputting the risk level according to the comparison result; Step S400: Receive and prompt the user with the project risk level.

Images