A procurement risk management method and system based on AI technology

Abstract

The present invention discloses a procurement risk management method and system based on AI technology, which relates to the field of bidding technology. The method includes: obtaining enterprise procurement-related information collected by a bidding smart supervision system; analyzing the enterprise procurement-related information to obtain key information related to procurement risks, and determining the corresponding risk name and risk level based on the key information and the risk information set in the preset risk type; when the risk level of one target risk is higher than the preset level threshold, enabling supervision authority and sending a supervision pop-up window after receiving the supervision instruction. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit. The present invention solves the problem of poor accuracy in procurement risk management in the existing technology.

Description

Technical Field

[0001] The present invention relates to the field of bidding technology, and in particular to a procurement risk management method and system based on AI technology. Background Art

[0002] With the rapid development of information technology, especially the widespread adoption of electronic methods, traditional procurement and bidding processes are gradually shifting towards digitalization and automation. Electronic bidding systems have become a crucial tool for many companies' public procurement. Through electronic methods, purchasing units can more efficiently publish bidding information, receive bid documents, and monitor the procurement process in real time.

[0003] Currently, when overseeing procurement risks, the same response strategy is adopted regardless of the level of risk, resulting in poor accuracy in risk procurement governance. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a procurement risk management method and system based on AI technology, aiming to solve the problem of poor accuracy in procurement risk management in the existing technology.

[0005] On one hand, the present invention proposes a procurement risk management method based on AI technology, which is used to manage enterprise procurement risks collected by a bidding and tendering intelligent supervision system. The method includes:

[0006] Obtaining enterprise procurement-related information collected by the bidding and tendering intelligent supervision system, including procurement documents, bidding documents, tender documents, supplier registration-related behavior records and basic supplier information, basic information of bid evaluation experts, and bid evaluation reports;

[0007] Analyze the enterprise procurement-related information to obtain key information related to procurement risks, and determine the corresponding risk name and risk level based on the key information and the risk information set in the preset risk type;

[0008] When the risk level of one of the target risks is higher than the preset level threshold, the supervision authority is enabled and a supervision pop-up window is sent after receiving the supervision instruction. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit.

[0009] Furthermore, in the above-mentioned AI-based procurement risk management method, the steps of analyzing enterprise procurement-related information to obtain key information related to procurement risks, and comparing the key information with risk information set in a preset risk type to determine the corresponding risk name and risk level include:

[0010] Obtain the risk types and corresponding procurement links of different risk names, and determine the target enterprise procurement-related information required based on the risk type and corresponding procurement link;

[0011] Obtain the key elements described in the risk name, analyze the target company's procurement-related information, collect key information related to the key elements, and determine the risk name based on the comparison of the key information with the key elements.

[0012] Furthermore, in the above-mentioned procurement risk governance method based on AI technology, the risk types include process risk, bidding risk, quotation risk, bid evaluation risk and associated risk;

[0013] The procurement process includes registration, quotation, transaction and bid evaluation.

[0014] Furthermore, the above-mentioned procurement risk governance method based on AI technology, wherein, when the risk level of one of the target risks is higher than the preset level threshold, the supervision authority is enabled and a supervision pop-up window is sent after receiving the supervision instruction, and the supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit, further includes the following steps:

[0015] Obtain target enterprises with risks and use the target enterprises as entity nodes;

[0016] Determine the attributes of the entity node according to the preset rules based on the number of risks of the target enterprise, and establish an enterprise risk relationship map based on the risk relationship between the entity node and the target enterprise;

[0017] After receiving the supervision suggestions for the target risk, the enterprise risk relationship map is used to determine other target enterprises that are associated with the target unit in terms of the target risk, and the supervision suggestions are forwarded to the other target enterprises.

[0018] Furthermore, in the aforementioned AI-based procurement risk governance method, the steps of determining the attributes of the entity nodes according to preset rules based on the number of risks of the target enterprise, and establishing an enterprise risk relationship map based on the risk relationship between the entity nodes and the target enterprise include:

[0019] Obtain the number of procurement links involved in the target enterprise, and plan a concentric circle area composed of preset circular areas in sequence according to the number of procurement links as the entity node of the target enterprise;

[0020] Obtain the number of risks faced by the target enterprise in different procurement links, and determine the size of each circular area based on the number of risks;

[0021] The concentric circle areas corresponding to the procurement links where risks occur for target enterprises with risk relationships are connected by line segments, and the corresponding risk descriptions are attached to obtain an enterprise risk relationship map.

[0022] Furthermore, the AI-based procurement risk management method further includes the following steps: connecting the concentric circle areas corresponding to the procurement links where the risks occur of the target enterprises with risk relationships with line segments and attaching corresponding risk descriptions to obtain an enterprise risk relationship map:

[0023] According to the enterprise risk relationship graph, multiple candidate entity nodes with risk quantities higher than a threshold are obtained respectively;

[0024] Calculating the betweenness centrality and degree centrality of each procurement link among the candidate entity nodes respectively, and determining the risk value of each procurement link according to the betweenness centrality and degree centrality;

[0025] Identify the target procurement links whose risk value is greater than the preset value, and increase the risk level within the target procurement links to the preset level to enable supervision authority.

[0026] Furthermore, the above-mentioned procurement risk management method based on AI technology includes:

[0027] The calculation formula of degree centrality is:

[0028] ;

[0029] The calculation formula for betweenness centrality is:

[0030] ;

[0031] The formula for calculating the risk value is:

[0032] ;

[0033] in, deg ( v ) represents the node of the procurement process v The degree indicates how many edges are directly connected to other procurement links. σ ( s,t ) represents the node of the procurement process s To the point of procurement t The number of shortest paths, σ ( s,t ∣ v ):Node in the procurement process v From the node s in the procurement process to the node in the procurement process t The number of occurrences in the shortest path between w 1 and w2 are the weight coefficients of degree centrality and betweenness centrality respectively.

[0034] Another object of the present invention is to provide a procurement risk management system based on AI technology, which is used to manage enterprise procurement risks collected by a bidding and tendering intelligent supervision system. The system includes:

[0035] An acquisition module is used to obtain enterprise procurement-related information collected by the bidding and tendering intelligent supervision system, including procurement documents, bidding documents, tender documents, supplier registration-related behavior records and supplier basic information, bid evaluation expert basic information and bid evaluation reports;

[0036] An analysis module is used to analyze enterprise procurement-related information to obtain key information related to procurement risks, and to determine the corresponding risk name and risk level based on the comparison of the key information with the risk information set in the preset risk type;

[0037] The supervision module is used to enable supervision authority and send a supervision pop-up window after receiving the supervision instruction when the risk level of one of the target risks is higher than the preset level threshold. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit.

[0038] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program implements the steps of the above method when executed by a processor.

[0039] Another object of the present invention is to provide an electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the steps of the above method are implemented when the processor executes the program.

[0040] The present invention obtains enterprise procurement related information collected by the bidding and tendering intelligent supervision system; analyzes enterprise procurement related information to obtain key information related to procurement risks, and determines the corresponding risk name and risk level by comparing the key information with the risk information set in the preset risk type; when the risk level of one of the target risks is higher than the preset level threshold, the supervision authority is enabled and a supervision pop-up window is sent after receiving the supervision instruction. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit. Different risk levels are set, and the supervision mechanism is used to supervise high-risk risks. Low-risk risks do not need supervision, so as to achieve accurate risk management and avoid the waste of resources caused by a unified supervision strategy. This solves the problem of poor accuracy in procurement risk management in the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1This is a flowchart of the procurement risk management method based on AI technology in the first embodiment of the present invention;

[0042] Figure 2 This is a structural block diagram of the procurement risk management system based on AI technology in the third embodiment of the present invention.

[0043] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0044] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0045] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0047] Example 1

[0048] See also Figure 1 , shown is a procurement risk management method based on AI technology in the first embodiment of the present invention, which is used to manage enterprise procurement risks collected by a bidding and tendering intelligent supervision system. The method includes steps S10 to S12.

[0049] Step S10, obtaining enterprise procurement related information collected by the bidding and tendering intelligent supervision system, the enterprise procurement related information including procurement documents, bidding documents, tender documents, supplier registration related behavior records and supplier basic information, evaluation expert basic information and evaluation report.

[0050] Among them, the bidding and tendering intelligent supervision system is a platform for supervising behaviors, data and other information in the enterprise procurement process. It is a management system based on modern information technology, especially big data, cloud computing, artificial intelligence and other technologies. It can collect relevant information about enterprise procurement from all aspects of enterprise procurement. Based on these data, the enterprise's procurement process can be supervised and risks can be discovered in a timely manner. Specifically, enterprise procurement-related information includes procurement documents, bidding documents, tender documents, supplier registration-related behavior records and supplier basic information, evaluation expert basic information and evaluation reports, etc.

[0051] Step S11 , analyzing the enterprise procurement related information to obtain key information related to procurement risks, and comparing the key information with the risk information set in the preset risk type to determine the corresponding risk name and risk level.

[0052] Among them, these data can be analyzed and mined to obtain key information related to risks. Relevant risk types are pre-established within the system, including procedural risks, bidding risks, quotation risks, evaluation risks and associated risks. Each risk type has different risk names, which represent different risks, such as "the bidding announcement period is too short" and "too many project failures". Each different risk name has corresponding judgment rules and detailed risk information, that is, when what conditions are met, there is a corresponding risk. The collected key information can be compared with the risk information set in the risk type to determine whether there is a risk at present. Specifically, NLP technology can be used to automatically parse text content, such as bidding announcements, bids, etc., to extract key information. Structured data can also be actively entered according to the established risks, that is, what data is needed for risk judgment, and the corresponding data is actively entered and input into the system for management and control.

[0053] In addition, in some optional embodiments of the present invention, the step of analyzing enterprise procurement-related information to obtain key information related to procurement risks, and comparing the key information with risk information set in a preset risk type to determine the corresponding risk name and risk level includes:

[0054] Obtain the risk types and corresponding procurement links of different risk names, and determine the target enterprise procurement-related information required based on the risk type and corresponding procurement link;

[0055] Obtain the key elements described in the risk name, analyze the target company's procurement-related information, collect key information related to the key elements, and determine the risk name based on the comparison of the key information with the key elements.

[0056] Among them, in order to obtain key information on risk governance that may be involved in the enterprise procurement process in a targeted and efficient manner, different risk types are divided according to different risks. Different procurement stages are divided under each risk type according to the stages where risks occur, such as the registration stage, the quotation stage, the transaction stage, and the bid evaluation stage. Specific risk names are divided under the procurement stages. Therefore, based on the procurement stage and risk type in which the risk name is located, it is possible to quickly locate and determine which enterprise procurement data this key information can be obtained from. For example, when one of the risks is named "large difference in expert scores", it is an evaluation risk in the bid evaluation stage. Therefore, it can be determined that the key information used to judge whether the difference in expert scores is large comes from the "bid evaluation report" file. The bid evaluation report can be accurately analyzed to obtain the key information required for risk name determination, and finally a determination is made to obtain the final risk result, specifically including the specific name of the risk and the risk level. The risk level is pre-determined by the system based on experience and actual conditions. That is, each risk name is assigned a different risk level, which can include low risk, medium risk, and high risk.

[0057] Step S12: When the risk level of one of the target risks is higher than the preset level threshold, the supervision authority is enabled and a supervision pop-up window is sent after receiving the supervision instruction. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit.

[0058] Among them, the preset level threshold is set to high risk. When there is a high risk, the supervision authority can be enabled in the display interface within the system. After enabling the supervision authority, the corresponding supervision pop-up window can be sent by clicking on the supervision instruction. Through the supervision pop-up window, relevant personnel can supervise the risk, that is, send the supervision suggestions to the relevant responsible units.

[0059] In summary, the procurement risk management method based on AI technology in the above embodiment of the present invention obtains enterprise procurement related information collected by the bidding and tendering intelligent supervision system; analyzes enterprise procurement related information to obtain key information related to procurement risks, and determines the corresponding risk name and risk level based on the key information and the risk information set in the preset risk type; when the risk level of one of the target risks is higher than the preset level threshold, the supervision authority is enabled and a supervision pop-up window is sent after receiving the supervision instruction. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit. Different risk levels are set, and the supervision mechanism is used to supervise high-risk risks. Low-risk risks do not need to be supervised, so as to achieve accurate risk management and avoid the waste of resources caused by a unified supervision strategy. It solves the problem of poor accuracy in procurement risk management in the existing technology.

[0060] Example 2

[0061] This embodiment also proposes a procurement risk management method based on AI technology. The difference between the procurement risk management method based on AI technology in this embodiment and the procurement risk management method based on AI technology in Example 1 is that:

[0062] When the risk level of one of the target risks is higher than the preset level threshold, the step of enabling supervision authority and sending a supervision pop-up window after receiving the supervision instruction, wherein the supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit, further includes:

[0063] Obtain target enterprises with risks and use the target enterprises as entity nodes;

[0064] Determine the attributes of the entity node according to the preset rules based on the number of risks of the target enterprise, and establish an enterprise risk relationship map based on the risk relationship between the entity node and the target enterprise;

[0065] After receiving the supervision suggestions for the target risk, the enterprise risk relationship map is used to determine other target enterprises that are associated with the target unit in terms of the target risk, and the supervision suggestions are forwarded to the other target enterprises.

[0066] Among them, in order to more intuitively display the risks faced by enterprises during procurement and analyze the potential risk relationships between enterprises, an enterprise risk relationship map is constructed. Specifically, after the target enterprises with risks have been monitored in advance, these enterprises are obtained and used as entity nodes. Based on the risk relationships between enterprises, an enterprise risk relationship map is established. It should be noted that some of the risks of enterprise procurement are related to other enterprises. For example, "enterprises use the same equipment to bid" and "use the same IP to register" require at least two enterprises to form risks, which can be considered as risk relationships between enterprises. Therefore, an enterprise risk relationship map is established based on this risk relationship and enterprise entity nodes.

[0067] In addition, since risks are displayed in the form of a list, after establishing the enterprise risk relationship map, in order to efficiently execute supervision, after receiving supervision suggestions for high-risk target risks, the enterprise risk relationship map is used to determine other target enterprises that are associated with the target unit in terms of target risks. That is, when the target risk involves multiple enterprises, when one of the enterprises is found to send supervision suggestions, it will automatically be linked to other target enterprises and forwarded.

[0068] In addition, in some optional embodiments of the present invention, the step of determining the attributes of the entity node according to a preset rule based on the number of risks of the target enterprise, and establishing an enterprise risk relationship map based on the risk relationship between the entity node and the target enterprise includes:

[0069] Obtain the number of procurement links involved in the target enterprise, and plan a concentric circle area composed of preset circular areas in sequence according to the number of procurement links as the entity node of the target enterprise;

[0070] Obtain the number of risks faced by the target enterprise in different procurement links, and determine the size of each circular area based on the number of risks;

[0071] The concentric circle areas corresponding to the procurement links where risks occur for target enterprises with risk relationships are connected by line segments, and the corresponding risk descriptions are attached to obtain an enterprise risk relationship map.

[0072] Among them, the enterprise risk relationship map is further improved. Specifically, the number of risks currently faced by enterprises in different procurement stages is taken into account. In specific implementation, the same number of circular areas is determined based on the number of procurement stages, that is, the types of procurement stages. For example, if an enterprise faces risks in the "registration stage, quotation stage, and transaction stage," three circular areas are set. The three circular areas form a concentric circle area of different sizes based on the order of the bidding process. The inner and outer circles can be determined based on the chronological order of the bidding process. The size of each circular area is determined by the number of risks in the procurement stage. The radius of the circle corresponding to the number can be found in a preset mapping table based on experience or big data analysis, and the radius of the circle is determined based on the number. First, a circular area near the center of the circle is determined, and then a second circular area is determined. To make each circular area distinguishable, the radius of the second circular area is determined. After the radius is mapped, the radius of the previous circle center is added to the final radius. The circular area of each procurement stage in the entity node can be used as a procurement stage child node under the entity node. Finally, the target enterprises with risk relationships are connected to obtain the enterprise risk relationship map.

[0073] Specifically, when making a connection, the location of the connection is determined based on the procurement link where the risk occurs. For example, if a certain risk relationship is generated in the "registration link" of two companies, the circular areas corresponding to the "registration link" of the two companies are connected by line segments.

[0074] In addition, in some optional embodiments of the present invention, to further enhance risk management security, an in-depth analysis of enterprise risks is conducted. Risk levels are adjusted by analyzing the nature of the enterprise's risk relationship map. Specifically, multiple candidate entity nodes with risk counts exceeding a threshold are identified. The betweenness centrality and degree centrality of the procurement link nodes within these entity nodes are then determined. The risk value of each procurement link is then determined based on the betweenness centrality and degree centrality. A high degree centrality for a procurement link indicates that it has a direct risk relationship with multiple other links. This suggests that the link may be a core risk transmission point or may be inherently subject to greater risk. In this case, the risk level of that link should be increased. A high betweenness centrality for a procurement link indicates that it plays a key role in the shortest path between multiple procurement links. If a risk occurs in that link, it could quickly spread to multiple other links, leading to systemic risk. Therefore, it is necessary to focus on these nodes and combine degree centrality and betweenness centrality to more comprehensively assess the risk factor. For example, a weight can be assigned to the degree centrality and betweenness centrality of each link to calculate a comprehensive risk index.

[0075] Specifically, the calculation formula of degree centrality is:

[0076] ;

[0077] The calculation formula for betweenness centrality is:

[0078] ;

[0079] The formula for calculating the risk value is:

[0080] ;

[0081] in, deg ( v ) represents the node of the procurement process v The degree indicates how many edges are directly connected to other procurement links. σ ( s,t ) represents the node of the procurement process s To the point of procurement t The number of shortest paths, σ ( s,t ∣ v ) represents the node of the procurement process v From the node s in the procurement process to the node in the procurement process t The number of occurrences in the shortest path between w 1 and w 2 are the weight coefficients of degree centrality and betweenness centrality respectively.

[0082] In summary, the procurement risk management method based on AI technology in the above embodiment of the present invention obtains enterprise procurement related information collected by the bidding and tendering intelligent supervision system; analyzes enterprise procurement related information to obtain key information related to procurement risks, and determines the corresponding risk name and risk level based on the key information and the risk information set in the preset risk type; when the risk level of one of the target risks is higher than the preset level threshold, the supervision authority is enabled and a supervision pop-up window is sent after receiving the supervision instruction. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit. Different risk levels are set, and the supervision mechanism is used to supervise high-risk risks. Low-risk risks do not need to be supervised, so as to achieve accurate risk management and avoid the waste of resources caused by a unified supervision strategy. It solves the problem of poor accuracy in procurement risk management in the existing technology.

[0083] Example 3

[0084] See also Figure 2 , shown is a procurement risk management system based on AI technology proposed in the third embodiment of the present invention, which is used to manage enterprise procurement risks collected by a bidding and tendering intelligent supervision system. The system includes:

[0085] The acquisition module 100 is used to obtain enterprise procurement-related information collected by the bidding and tendering intelligent supervision system, wherein the enterprise procurement-related information includes procurement documents, bidding documents, tender documents, supplier registration-related behavior records and supplier basic information, bid evaluation expert basic information and bid evaluation reports;

[0086] Analysis module 200, for analyzing enterprise procurement-related information to obtain key information related to procurement risks, and determining corresponding risk names and risk levels based on the key information compared with risk information set in preset risk types;

[0087] The supervision module 300 is used to enable supervision authority and send a supervision pop-up window after receiving the supervision instruction when the risk level of one of the target risks is higher than the preset level threshold. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit.

[0088] Furthermore, in the above-mentioned procurement risk governance system based on AI technology, the steps of analyzing enterprise procurement-related information to obtain key information related to procurement risks, and comparing the key information with risk information set in a preset risk type to determine the corresponding risk name and risk level include:

[0089] Obtain the risk types and corresponding procurement links of different risk names, and determine the target enterprise procurement-related information required based on the risk type and corresponding procurement link;

[0090] Obtain the key elements described in the risk name, analyze the target company's procurement-related information, collect key information related to the key elements, and determine the risk name based on the comparison of the key information with the key elements.

[0091] Furthermore, in the above-mentioned procurement risk governance system based on AI technology, the risk types include process risk, bidding risk, quotation risk, bid evaluation risk and associated risk;

[0092] The procurement process includes registration, quotation, transaction and bid evaluation.

[0093] Furthermore, the procurement risk governance system based on AI technology, wherein, when the risk level of one of the target risks is higher than a preset level threshold, the supervision authority is enabled and a supervision pop-up window is sent after receiving the supervision instruction, wherein the supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit, further includes:

[0094] Obtain target enterprises with risks and use the target enterprises as entity nodes;

[0095] Determine the attributes of the entity node according to the preset rules based on the number of risks of the target enterprise, and establish an enterprise risk relationship map based on the risk relationship between the entity node and the target enterprise;

[0096] After receiving the supervision suggestions for the target risk, the enterprise risk relationship map is used to determine other target enterprises that are associated with the target unit in terms of the target risk, and the supervision suggestions are forwarded to the other target enterprises.

[0097] Furthermore, in the aforementioned AI-based procurement risk governance system, the steps of determining the attributes of the entity nodes according to preset rules based on the number of risks of the target enterprise, and establishing an enterprise risk relationship map based on the risk relationship between the entity nodes and the target enterprise include:

[0098] Obtain the number of procurement links involved in the target enterprise, and plan a concentric circle area composed of preset circular areas in sequence according to the number of procurement links as the entity node of the target enterprise;

[0099] Obtain the number of risks faced by the target enterprise in different procurement links, and determine the size of each circular area based on the number of risks;

[0100] The concentric circle areas corresponding to the procurement links where risks occur for target enterprises with risk relationships are connected by line segments, and the corresponding risk descriptions are attached to obtain an enterprise risk relationship map.

[0101] Furthermore, the procurement risk governance system based on AI technology may further include the following steps after the step of connecting the concentric circle areas corresponding to the procurement links where the risks occur of the target enterprises with risk relationships by line segments and attaching corresponding risk descriptions to obtain an enterprise risk relationship map:

[0102] According to the enterprise risk relationship graph, multiple candidate entity nodes with risk quantities higher than a threshold are obtained respectively;

[0103] Calculating the betweenness centrality and degree centrality of each procurement link among the candidate entity nodes respectively, and determining the risk value of each procurement link according to the betweenness centrality and degree centrality;

[0104] Identify the target procurement links whose risk value is greater than the preset value, and increase the risk level within the target procurement links to the preset level to enable supervision authority.

[0105] Furthermore, the above-mentioned procurement risk management system based on AI technology,

[0106] The calculation formula of degree centrality is:

[0107] ;

[0108] The calculation formula for betweenness centrality is:

[0109] ;

[0110] The formula for calculating the risk value is:

[0111] ;

[0112] in, deg ( v ) represents the node of the procurement process v The degree indicates how many edges are directly connected to other procurement links. σ ( s,t ) represents the node of the procurement process s To the point of procurement t The number of shortest paths, σ ( s,t ∣ v ) represents the node of the procurement process v From the node s in the procurement process to the node in the procurement process t The number of occurrences in the shortest path between w 1 and w2 are the weight coefficients of degree centrality and betweenness centrality respectively.

[0113] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments and will not be repeated here.

[0114] Example 4

[0115] Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the above-mentioned embodiments 1 to 2.

[0116] Example 5

[0117] On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, the steps of the method described in any one of the above-mentioned embodiments 1 to 2 are implemented.

[0118] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are 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.

[0119] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or for use in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, a "computer-readable storage medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0120] More specific examples (a non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0121] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0122] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0123] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A procurement risk management method based on AI technology, characterized by: For managing enterprise procurement risks collected by a bidding and tendering intelligent supervision system, the method includes: Obtaining enterprise procurement-related information collected by the bidding and tendering intelligent supervision system, including procurement documents, bidding documents, tender documents, supplier registration-related behavior records and basic supplier information, basic information of bid evaluation experts, and bid evaluation reports; Analyze the enterprise procurement-related information to obtain key information related to procurement risks, and determine the corresponding risk name and risk level based on the key information and the risk information set in the preset risk type; The step of analyzing the enterprise procurement-related information to obtain key information related to procurement risks, and comparing the key information with risk information set in a preset risk type to determine the corresponding risk name and risk level includes: Obtain the risk types and corresponding procurement links of different risk names, and determine the target enterprise procurement-related information required based on the risk type and corresponding procurement link; Obtain the key elements described in the risk name, analyze the target company's procurement-related information to collect key information related to the key elements, and determine the risk name based on the comparison of the key information with the key elements; The risk types include procedural risk, bidding risk, quotation risk, bid evaluation risk and associated risk; The procurement process includes registration, quotation, transaction and bid evaluation; When the risk level of one of the target risks is higher than the preset level threshold, the supervision authority is enabled and a supervision pop-up window is sent after receiving the supervision instruction. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit; Obtain target enterprises with risks and use the target enterprises as entity nodes; Obtain the number of procurement links involved in the target enterprise, and plan a concentric circle area composed of preset circular areas in sequence according to the number of procurement links as the entity node of the target enterprise; Obtain the number of risks faced by the target enterprise in different procurement links, and determine the size of each circular area based on the number of risks; Connect the concentric circle areas of the target enterprises with risk relationships corresponding to the procurement links where risks occur with line segments, and attach the corresponding risk descriptions to obtain the enterprise risk relationship map; After receiving the supervision suggestions for the target risk, the enterprise risk relationship map is used to determine other target enterprises that are associated with the target unit in terms of the target risk, and the supervision suggestions are forwarded to the other target enterprises; After the step of connecting the concentric circle areas corresponding to the procurement links where the risks occur for the target enterprises with risk relationships with line segments and attaching corresponding risk descriptions to obtain an enterprise risk relationship map, the following step is further included: According to the enterprise risk relationship graph, multiple candidate entity nodes with risk quantities higher than a threshold are obtained respectively; Calculating the betweenness centrality and degree centrality of each procurement link among the candidate entity nodes respectively, and determining the risk value of each procurement link according to the betweenness centrality and degree centrality; Identify target procurement links with risk values greater than the preset value, and raise the risk level within the target procurement link to the preset level to enable supervision authority; The calculation formula of degree centrality is: ； The calculation formula for betweenness centrality is: ； The formula for calculating the risk value is: ； in, deg ( v ) represents the node of the procurement process v The degree indicates how many edges are directly connected to other procurement links. σ ( s,t ) represents the node of the procurement process s To the point of procurement t The number of shortest paths, σ ( s,t ∣ v ) represents the node of the procurement process v From the node s in the procurement process to the node in the procurement process t The number of occurrences in the shortest path between w 1 and w 2 are the weight coefficients of degree centrality and betweenness centrality respectively.

2. A procurement risk management system based on AI technology, characterized by: The method for implementing the AI-based procurement risk management method of claim 1 is used to manage enterprise procurement risks collected by a bidding and tendering intelligent supervision system, and the system includes: An acquisition module is used to obtain enterprise procurement-related information collected by the bidding and tendering intelligent supervision system, including procurement documents, bidding documents, tender documents, supplier registration-related behavior records and supplier basic information, bid evaluation expert basic information and bid evaluation reports; An analysis module is used to analyze enterprise procurement-related information to obtain key information related to procurement risks, and to determine the corresponding risk name and risk level based on the comparison of the key information with the risk information set in the preset risk type; The supervision module is used to enable supervision authority and send a supervision pop-up window after receiving the supervision instruction when the risk level of one of the target risks is higher than the preset level threshold. The supervision pop-up window is used to receive supervision suggestions for the risk and send the supervision suggestions to the corresponding target unit.

3. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to claim 1 are implemented.

4. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the steps of the method according to claim 1 are implemented when the processor executes the program.

Images