A Bidding Risk Early Warning System and Method Based on a Large Model

Abstract

This invention discloses a bidding risk early warning system and method based on a large model, relating to the field of bidding technology. The key technical points include the following steps: acquiring basic information data and historical bidding data of bidding projects; generating a project feature map of the bidding projects based on the basic information data, and obtaining a project risk feature library based on the project feature map; collecting the risk identification range of the early warning large model, and performing feature matching based on the risk identification range and the project risk feature library to obtain the corresponding risk points to be warned for the bidding projects; obtaining the risk correlation trajectory between the risk points to be warned and the bidding projects based on the historical bidding data of the bidding projects, and obtaining the risk correlation coefficient corresponding to the risk points to be warned based on the risk correlation trajectory; setting risk early warning parameters for the bidding projects based on the basic information data; the effect is to build a solid risk prevention and control barrier for the smooth conduct of bidding activities.

Description

Technical Field

[0001] This invention relates to the field of bidding and tendering technology, and more specifically, to a bidding and tendering risk early warning system and method based on a large model. Background Technology

[0002] In bidding activities, due to the involvement of multiple parties and the complexity of the process, traditional risk management models are gradually becoming inadequate for the needs of refined management. Traditional methods have a low degree of risk quantification, often using vague classifications such as "high, medium, and low," which cannot accurately distinguish the threat level of different risk points, leading to resource misallocation. This can easily result in too much effort being invested in risks with low actual threat, while critical high-impact risks are neglected, leading to problems such as non-compliance of bid documents and contract performance disputes.

[0003] Meanwhile, risk identification relies on human experience to judge isolated risk points, lacking in-depth exploration of risk correlations. For example, focusing only on the compliance of the current project bidder's qualification documents without linking it to their past bidding behavior, such as records of bid rigging or collusion, or unusual cooperation with agencies, makes it difficult to detect hidden risks. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of this invention is to provide a bidding risk early warning system and method based on a large model.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A bidding risk early warning method based on a large model, comprising the following steps:

[0007] Obtain basic information data and historical bidding data for bidding projects; generate project feature maps for bidding projects based on the basic information data; and obtain a project risk feature database based on the project feature maps.

[0008] The risk identification range of the large-scale early warning model is collected, and feature matching is performed based on the risk identification range and the project risk feature library to obtain the risk points to be warned for the bidding project.

[0009] Based on historical bidding data of bidding projects, the risk correlation trajectory between the risk points to be warned and the bidding projects is obtained, and the risk correlation coefficient corresponding to the risk points to be warned is obtained based on the risk correlation trajectory.

[0010] Set risk warning parameters for bidding projects based on basic information data; obtain historical risk parameters for risk points to be warned; and analyze the risk warning parameters and historical risk parameters of risk points to be warned to obtain the risk warning coefficients corresponding to the risk points to be warned.

[0011] The comprehensive risk coefficient corresponding to the risk point to be warned is obtained based on the risk correlation coefficient and the risk impact coefficient;

[0012] Based on the comprehensive risk coefficient, the target early warning risk points corresponding to the bidding project are obtained, and risk early warning information for the bidding project is generated based on the target early warning risk points.

[0013] Preferably, a project feature map of the bidding project is generated based on basic information data, and a project risk feature database is obtained based on the project feature map. This specifically includes the following steps:

[0014] Collect the first time point when the bidding process begins and the second time point when the bid evaluation process ends for the bidding project.

[0015] The project cycle of the bidding project is obtained based on the first and second time nodes, and a project feature map of the bidding project is generated based on the basic information within the project cycle.

[0016] Obtain the attribute information of each feature point in the project feature map. The attribute information includes key feature attributes and secondary feature attributes. Set feature classification criteria based on key feature attributes and secondary feature attributes. Construct a project risk feature library based on feature classification criteria.

[0017] Preferably, feature matching is performed based on the risk identification scope and the project risk feature database to obtain the risk points to be warned for the bidding project, specifically as follows:

[0018] If the risk identification scope of the early warning model includes risk features in the project risk feature library, then the risk points corresponding to the risk features will be marked as the risk points to be warned for the bidding project.

[0019] Preferably, the risk correlation trajectory between the risk points to be warned and the bidding projects is obtained based on historical bidding data of the bidding projects, specifically including the following steps:

[0020] Obtain the historical risk location of the risk points to be warned; obtain the event location of historical risk events based on the historical bidding data of bidding projects;

[0021] Based on the historical risk location and event location, the risk correlation between historical risk events and risk points to be warned is obtained;

[0022] Based on the risk correlation between historical risk events and risk points to be warned, a risk correlation trajectory between risk points to be warned and bidding projects is generated.

[0023] Preferably, the risk correlation coefficient corresponding to the risk point to be warned is obtained based on the risk correlation trajectory, specifically including the following steps:

[0024] Set risk association intervals, each of which corresponds to a risk weight;

[0025] Based on the inclusion relationship between the risk correlation degree and the risk correlation interval in the risk correlation trajectory, the risk correlation trajectory is divided to obtain at least one segmented risk correlation trajectory;

[0026] Extract the target risk weights from the segmented risk correlation trajectories;

[0027] Based on the segmented risk correlation trajectory and the target risk weight corresponding to the segmented risk correlation trajectory, the risk correlation coefficient corresponding to the risk point to be warned is obtained.

[0028] Preferably, risk warning parameters for bidding projects are set based on basic information data, specifically including the following steps:

[0029] Based on basic information data, the project type and project size of the bidding project are obtained;

[0030] Risk warning parameters for bidding projects are set according to the project type and project size;

[0031] The risk warning parameters include the risk occurrence probability threshold, risk impact threshold, risk response difficulty threshold, and risk monitoring frequency for bidding projects.

[0032] Preferably, the historical risk parameters of the risk points to be warned are obtained, and the risk warning coefficient corresponding to the risk points to be warned is obtained by analyzing the risk warning parameters and the historical risk parameters of the risk points to be warned. This specifically includes the following steps:

[0033] The historical risk parameters include the historical occurrence probability, historical impact, historical response difficulty, and historical monitoring records of the risk points to be warned.

[0034] Set risk parameter weights; wherein, the risk parameter weights include probability weights, impact weights, difficulty weights, and monitoring weights;

[0035] By comparing the risk warning parameters of the bidding project with the historical risk parameters of the risk points to be warned, the parameter-matched risk points of the risk points to be warned are obtained.

[0036] The probability coefficients of parameter-fitted risk points are obtained based on probability weights, risk occurrence probability thresholds, and the historical occurrence probabilities of parameter-fitted risk points.

[0037] The influence coefficient of the parameter-adapted risk point is obtained based on the influence weight, the risk influence threshold, and the historical influence of the parameter-adapted risk point.

[0038] The difficulty coefficient of the parameter-adapted risk point is obtained based on the difficulty weight, the risk response difficulty threshold, and the historical response difficulty of the parameter-adapted risk point.

[0039] The monitoring coefficient of the parameter-adapted risk point is obtained based on the monitoring weight, risk monitoring frequency, and historical monitoring records of the parameter-adapted risk point.

[0040] The risk warning coefficient corresponding to the risk point to be warned is obtained based on the probability coefficient, impact coefficient, difficulty coefficient and monitoring coefficient.

[0041] Preferably, the target early warning risk points corresponding to the bidding project are obtained based on the comprehensive risk coefficient, specifically as follows:

[0042] The risk point with the highest comprehensive risk coefficient is marked as the target risk point for the bidding project.

[0043] A bidding risk early warning system based on a large model includes:

[0044] Acquisition Module: Acquires basic information data and historical bidding data of bidding projects; generates project feature maps of bidding projects based on basic information data; and obtains project risk feature database based on project feature maps.

[0045] Data Acquisition and Matching Module: Collects the risk identification range of the early warning model, and performs feature matching based on the risk identification range and the project risk feature library to obtain the risk points to be warned for the bidding project;

[0046] The first processing module obtains the risk correlation trajectory between the risk points to be warned and the bidding projects based on the historical bidding data of the bidding projects, and obtains the risk correlation coefficient corresponding to the risk points to be warned based on the risk correlation trajectory.

[0047] Analysis module: Sets risk warning parameters for bidding projects based on basic information data; obtains historical risk parameters of risk points to be warned; and analyzes the risk warning parameters and historical risk parameters of risk points to be warned to obtain the risk warning coefficient corresponding to the risk points to be warned.

[0048] The second processing module: Based on the risk correlation coefficient and the risk impact coefficient, the comprehensive risk coefficient corresponding to the risk point to be warned is obtained;

[0049] Risk warning module: Based on the comprehensive risk coefficient, the module obtains the target warning risk points corresponding to the bidding project, and generates risk warning information for the bidding project based on the target warning risk points.

[0050] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a bidding risk warning method based on a large model.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] This invention comprehensively measures the threat level of potential risk points by calculating a comprehensive risk coefficient based on a combination of risk correlation trajectories and historical parameters. In terms of resource allocation optimization, once the target risk point is clearly identified, project participants can concentrate manpower and resources to prioritize the prevention and control of that risk, avoiding the dispersion of resources on secondary risks. For example, specific contingency plans can be developed in advance for high-risk points, monitoring frequency can be increased, resource utilization efficiency can be improved, and prevention and control costs can be reduced. From the perspective of project progress assurance, focusing on the risk point with the highest comprehensive risk coefficient can prevent the escalation of major risks in advance, reducing their impact on the bidding process (such as bid opening and evaluation) and subsequent project implementation (such as contract performance and costs), ensuring that the project proceeds as planned, maintaining the fairness and standardization of bidding activities, building a solid risk prevention and control barrier for the smooth conduct of bidding activities, and improving the overall risk response level of the industry. Attached Figure Description

[0053] Figure 1 This is a schematic diagram illustrating the steps of a bidding risk early warning method based on a large model proposed in this invention.

[0054] Figure 2 This invention presents a schematic diagram of a bidding risk early warning system based on a large model.

[0055] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0056] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. Detailed Implementation

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0060] Reference Figures 1-3 .

[0061] Example 1 further illustrates the bidding risk early warning system and method based on a large model proposed in this invention.

[0062] A bidding risk early warning method based on a large model, comprising the following steps:

[0063] Obtain basic information data and historical bidding data for bidding projects; generate project feature maps for bidding projects based on the basic information data; and obtain a project risk feature database based on the project feature maps.

[0064] The risk identification range of the large-scale early warning model is collected, and feature matching is performed based on the risk identification range and the project risk feature library to obtain the risk points to be warned for the bidding project.

[0065] Based on historical bidding data of bidding projects, the risk correlation trajectory between the risk points to be warned and the bidding projects is obtained, and the risk correlation coefficient corresponding to the risk points to be warned is obtained based on the risk correlation trajectory.

[0066] Set risk warning parameters for bidding projects based on basic information data; obtain historical risk parameters for risk points to be warned; and analyze the risk warning parameters and historical risk parameters of risk points to be warned to obtain the risk warning coefficients corresponding to the risk points to be warned.

[0067] The comprehensive risk coefficient corresponding to the risk point to be warned is obtained based on the risk correlation coefficient and the risk impact coefficient;

[0068] Based on the comprehensive risk coefficient, the target early warning risk points corresponding to the bidding project are obtained, and risk early warning information for the bidding project is generated based on the target early warning risk points.

[0069] This application constructs a complete risk warning process based on data and large-scale models. First, by acquiring basic information data of bidding projects (covering basic project information, participant information, etc.) and historical bidding data (various records of past projects), the basic information data is used to generate a project feature map, sort out the key features of the project, and then extract a project risk feature library from it, classifying and storing the potential risks of the project in the form of features.

[0070] This application comprehensively captures data details across the entire bidding and tendering process. For basic information data, it focuses on the bidding and tendering project to be analyzed, collecting fundamental attributes such as project name, industry (construction, goods procurement, or services), budget amount, scope of tender (equipment list, service content boundaries), and tendering method (open tendering or invited tendering). Simultaneously, it collects information on participating entities, such as the tenderer's corporate qualifications and credit rating, the business scope of potential bidders, their past participation in similar projects, and dynamic information such as key nodes in the tendering process (registration deadline, bid opening location, composition of evaluation experts). Historical bidding and tendering data is retrieved from the company's or industry's project database, including data on similar or related past projects. This includes risk events that occurred in historical projects (such as bid rigging, performance disputes), the historical behavior of participating parties (a bidder's past pricing strategies, number of defaults after winning the bid), historical project results (whether delivery was successful, issues during acceptance), and industry cyclical data (price fluctuations of similar projects in different years, high-risk periods). This data is obtained through automatic capture from public resource trading platforms, export from the company's internal project management system, and manual verification of historical archives.

[0071] First, core characteristic entities are extracted from the basic data, such as the project entity (including attributes like project budget and bidding type), participating entities (bidders, bidders, and agencies, each with its own qualifications, credit ratings, etc.), and process nodes (registration, bid opening, bid evaluation, and other stages and time attributes). Then, the relationships between these entities are analyzed, such as the agency relationship of "bidder—agency—agency," the participation relationship of "bidder—participant—project segment," and the potential risk association of "process node—association—risk history." Next, knowledge graph technology (such as graph database tools) is used to construct a visualized project characteristic graph, using these entities as "nodes" and relationships as "edges." For example, in the graph, the "Project A" node can be clearly seen connecting "bidder A" and "bidder B," and "bidder B" is also associated with the "Class B qualification" label through the "qualification" relationship. The "bid opening stage" node is associated with the risk warning of "anomalies in historical project bid openings."

[0072] Building a project risk feature database based on project feature maps is the process of uncovering risk patterns. Analyzing abnormal signals in node attributes—for example, if "Bidder B's qualification is Class B" but the project requires "Class A," the "qualification non-compliance risk feature" is extracted; if "the project budget is 30% lower than similar projects," it corresponds to "cost insufficiency leading to quality risk feature." Risks are also uncovered from relationship networks, identifying potential risks through entity associations. For instance, if "Agency C and Bidder B have three joint bidding records," combined with industry bid-rigging cases, the "related party bid-rigging risk feature" is extracted; if "the bid opening time is set outside working hours," it is associated with "process non-compliance risk" in historical projects, identifying the "time compliance risk feature." These risk features are then standardized, categorized, and stored according to risk types such as compliance, economy, and performance. Each feature is defined with a "name, triggering condition, and associated entity" (e.g., for the "bid-rigging risk" feature, the triggering condition is "the agency and the bidder have cooperated ≥2 times and the price difference ≤5%," associated with the entities "agent and bidder"), forming the project risk feature database.

[0073] The risk identification range of the large-scale early warning model is collected, and features in the project risk feature library are matched with this identification range. If a risk feature that the model can identify has a corresponding risk point in the library, it is marked as a risk point to be warned. The identification capability of the large-scale model is used to initially screen out risks that need attention. Based on historical bidding data, the correlation between the risk points to be warned and the project is mined, the historical risk location of the risk points to be warned is obtained, and the risk correlation degree is calculated by combining the event location of historical risk events to generate a risk correlation trajectory. Then, by dividing the correlation trajectory interval and extracting the corresponding risk weight, the risk correlation coefficient of the risk points to be warned is obtained, thus quantifying the degree of correlation between the risk points and the project.

[0074] Based on the project type and scale in the basic information data, risk warning parameters (including risk occurrence probability thresholds, impact severity thresholds, etc.) are set, and historical risk parameters (such as historical occurrence probability and impact severity) of the risk points to be warned are obtained. The corresponding parameters of the two are compared, and combined with the pre-set probability weights, impact weights, and other risk parameter weights, the probability coefficient, impact coefficient, and other sub-coefficients are calculated respectively. Finally, the risk warning coefficient is obtained by summing them up, measuring the risk from the perspective of the project's own requirements and the historical performance of the risk. Combining the risk correlation coefficient and the risk impact coefficient, the comprehensive risk coefficient of the risk points to be warned is obtained, and the magnitude of the risk is assessed by comprehensively considering the correlation and the degree of impact.

[0075] From all potential risk points, the one with the highest overall risk coefficient is marked as the target risk point. Specific risk warning information is generated for this risk point to inform the bidding participants of the risks that they need to pay close attention to and prevent, helping them to take measures in advance to avoid or reduce risks and ensure the smooth progress of the bidding project.

[0076] Based on basic information data, a project feature map of the bidding project is generated, and based on the project feature map, a project risk feature database is obtained. The specific steps include:

[0077] Collect the first time point when the bidding process begins and the second time point when the bid evaluation process ends for the bidding project.

[0078] The project cycle of the bidding project is obtained based on the first and second time nodes, and a project feature map of the bidding project is generated based on the basic information within the project cycle.

[0079] Obtain the attribute information of each feature point in the project feature map. The attribute information includes key feature attributes and secondary feature attributes. Set feature classification criteria based on key feature attributes and secondary feature attributes, and construct a project risk feature library based on feature classification criteria.

[0080] After calculating the project cycle of the bidding project based on the first and second time nodes, a feature map is generated. Based on the two determined time nodes, the duration and stage distribution of the project from the start of bidding to the end of bid evaluation are calculated. All basic information within the cycle (project budget, participant information, process requirements for each stage, etc.) is transformed into feature points and relationships in the map according to the time axis and business node dimensions. For example, in the map, the registration stage node is associated with attributes such as the registration deadline and the number of potential bidders, while the Bidder A node is associated with features such as qualification level and past bidding records.

[0081] From the feature points of the graph, key feature attributes (core elements that directly affect project risk, such as whether the bidder's qualifications meet the standards, and the deviation rate between the project budget and market price) and secondary feature attributes (information that has a weaker impact on risk or serves as supplementary explanation, such as the bidder's office address and project promotional slogans) are distinguished. The information in the secondary feature attributes serves as supplementary explanations or related clues for risk features. According to this standard, the various risk-related features mined from the graph (such as "delay at a certain stage time node" corresponding to "process risk feature") are standardized, organized, and stored to form a project risk feature library.

[0082] Based on the risk identification scope and the project risk feature database, feature matching is performed to obtain the risk points to be warned for the bidding project, specifically:

[0083] If the risk identification scope of the early warning model includes risk features in the project risk feature library, then the risk points corresponding to the risk features will be marked as the risk points to be warned for the bidding project.

[0084] This application needs to clarify that the early warning model pre-sets the risk identification scope, which covers various risk characteristics that may appear in bidding projects. At the same time, a project risk feature library is constructed through the processing of basic information of bidding projects in the early stage. The project risk feature library stores feature content related to the potential risks of the project extracted from the project feature map.

[0085] When identifying potential risk points, the risk identification range of the early warning model is compared with the project risk feature database. If a risk feature identified by the early warning model has a corresponding entry in the project risk feature database, it means that the risk point indicated by that feature is related to the current bidding project. At this point, the risk points corresponding to these risk features are marked as key risk points requiring attention and awaiting early warning in the current bidding project.

[0086] Based on historical bidding data of bidding projects, the risk correlation trajectory between potential warning risk points and bidding projects is obtained, specifically including the following steps:

[0087] Obtain the historical risk location of the risk points to be warned; obtain the event location of historical risk events based on the historical bidding data of bidding projects;

[0088] Based on the historical risk location and event location, the risk correlation between historical risk events and risk points to be warned is obtained;

[0089] Based on the risk correlation between historical risk events and risk points to be warned, a risk correlation trajectory between risk points to be warned and bidding projects is generated.

[0090] This application aims to uncover the logical connections between potential risk points and bidding projects, conducting analysis based on historical data. It locates the historical risk positions of potential risk points within historical bidding data, which can be project process stages (such as bidding registration and evaluation), time points (such as a quarter or month), or scenarios involving participating parties (cooperation with specific bidders or agencies). Simultaneously, it identifies the locations of past actual risk events within historical data, also defined from the dimensions of process, time, and participating parties.

[0091] Based on these two types of location information, the "risk correlation" between historical risk events and risk points to be warned is obtained through spatial or logical connections. For example, if the historical risk location of a risk point to be warned frequently overlaps with the event location of a certain type of historical risk event, or is highly connected in terms of time and process, it indicates a high correlation, thereby quantifying the closeness of the connection between the two.

[0092] Based on this risk correlation data, the correlation patterns and propagation paths between the risk points to be warned and various historical risk events throughout the entire bidding process are analyzed to generate a risk correlation trajectory. This clearly presents the potential or associated risk events that the risk points to be warned may trigger at different stages of the project, providing an intuitive logical basis for subsequent risk impact assessment and the development of prevention and control strategies.

[0093] And based on the risk correlation trajectory, the risk correlation coefficient corresponding to the risk point to be warned is obtained, which specifically includes the following steps:

[0094] Set up risk-related intervals, each of which corresponds to a risk weight;

[0095] Based on the inclusion relationship between the risk correlation degree and the risk correlation interval in the risk correlation trajectory, the risk correlation trajectory is divided to obtain at least one segmented risk correlation trajectory;

[0096] Extract the target risk weights from the segmented risk correlation trajectories;

[0097] Based on the segmented risk correlation trajectory and the target risk weight corresponding to the segmented risk correlation trajectory, the risk correlation coefficient corresponding to the risk point to be warned is obtained.

[0098] This application quantifies risk correlation trajectories to obtain risk correlation coefficients for potential risk points, thus measuring the degree of risk correlation. First, risk correlation intervals are pre-defined, and each interval is assigned a corresponding risk weight. These intervals and weights are determined based on historical experience, industry standards, or data analysis, and are used for subsequent correlation classification and quantification. Next, the risk correlation degree within the risk correlation trajectory is determined, and it is identified which pre-defined interval it falls into. The complete risk correlation trajectory is then divided into multiple segmented trajectories according to inclusion relationships, with each segment corresponding to a specific interval. Next, the corresponding target risk weights are extracted from the segmented risk correlation trajectories to clarify the weight of each segment. Finally, combining the specific characteristics of the segmented risk correlation trajectories (such as length, coverage stage, etc.) and the corresponding target risk weights, the risk correlation coefficients for potential risk points are comprehensively derived through weighted calculations, transforming the complex trajectory of risk correlation into a quantitative indicator usable for risk assessment, providing data support for subsequent risk analysis and early warning.

[0099] And based on the basic information data, risk warning parameters for bidding projects are set, specifically including the following steps:

[0100] Based on basic information data, the project type and project size of the bidding project are obtained;

[0101] Set risk warning parameters for bidding projects based on project type and scale;

[0102] Among them, the risk warning parameters include the risk occurrence probability threshold, risk impact threshold, risk response difficulty threshold, and risk monitoring frequency for bidding projects.

[0103] This application configures risk warning parameters based on basic project information to lay a solid foundation for risk management in bidding and tendering. First, it mines basic information data about bidding and tendering projects to clearly define project types (such as engineering construction, goods procurement, and service outsourcing) and project scale (measured by indicators such as investment amount and the volume of business involved). This is the core basis for setting subsequent parameters, because different types and scales of projects have significant differences in risk performance and management needs.

[0104] Risk warning parameters are set based on clearly defined project types and scales. Threshold standards for the probability of risk occurrence, impact, and difficulty of response will differ depending on the characteristics of the project. For example, large-scale engineering construction projects, due to the numerous stages and complex participants, may have relatively low risk occurrence thresholds, and the risk impact threshold will be set according to the degree of impact on the overall project should the risk occur. Risk response difficulty thresholds are determined by combining the professional characteristics of the project type, clarifying the ease or difficulty standards for handling various risks. The frequency of risk monitoring is rationally planned based on the project scale and potential risk threats; larger, higher-risk projects naturally require more intensive monitoring. This comprehensive and adaptable approach establishes quantitative standards and monitoring rhythms for risk warnings in bidding projects, providing clear parameter guidance for subsequent risk identification, assessment, and response.

[0105] Obtain historical risk parameters for the risk points to be warned, and analyze the risk warning parameters and historical parameters of the risk points to be warned to obtain the risk warning coefficients corresponding to the risk points to be warned. This includes the following steps:

[0106] Historical risk parameters include the historical probability of occurrence, historical impact, historical difficulty of response, and historical monitoring records of the risk points to be warned.

[0107] Set risk parameter weights; these weights include probability weights, impact weights, difficulty weights, and monitoring weights.

[0108] By comparing the risk warning parameters of the bidding project with the historical risk parameters of the risk points to be warned, the parameter-matched risk points of the risk points to be warned are obtained.

[0109] The probability coefficients of parameter-fitted risk points are obtained based on probability weights, risk occurrence probability thresholds, and the historical occurrence probabilities of parameter-fitted risk points.

[0110] The influence coefficient of the parameter-adapted risk point is obtained based on the influence weight, the risk influence threshold, and the historical influence of the parameter-adapted risk point.

[0111] The difficulty coefficient of the parameter-adapted risk point is obtained based on the difficulty weight, the risk response difficulty threshold, and the historical response difficulty of the parameter-adapted risk point.

[0112] The monitoring coefficient of the parameter-adapted risk point is obtained based on the monitoring weight, risk monitoring frequency, and historical monitoring records of the parameter-adapted risk point.

[0113] The risk warning coefficient corresponding to the risk point to be warned is obtained based on the probability coefficient, impact coefficient, difficulty coefficient and monitoring coefficient.

[0114] This application extracts key historical occurrence probabilities, historical impact levels, historical response difficulties, and historical monitoring records from historical information on risk points to be warned. To reasonably measure the impact of different dimensions of historical data on the current risk warning, risk parameter weights need to be set, that is, weights are assigned to the dimensions of probability, impact, difficulty, and monitoring. The weighting will be based on factors such as the actual needs of the project and industry characteristics, highlighting the importance of different dimensions in risk assessment.

[0115] By comparing the pre-set risk warning parameters (such as risk occurrence probability threshold, risk impact degree threshold, etc.) of the current bidding project with the historical risk parameters of the risk points to be warned, we can find the risk points that match the parameters, clarify the matching of historical risk data under the current project risk control standards, and determine which historical risk characteristics are related to the current project warning requirements.

[0116] After obtaining the parameters that match the risk points, coefficients are calculated for each dimension. The probability coefficient is calculated by combining the probability weight, the project's risk occurrence probability threshold, and the historical occurrence probability of the matched risk points, thereby measuring the degree of early warning regarding the probability of the risk point occurring. Similarly, the impact coefficient is obtained by using the influence weight, the risk impact threshold, and the historical impact, reflecting the degree of impact of the risk on the project. The difficulty coefficient is calculated by using the difficulty weight, the risk response difficulty threshold, and the historical response difficulty, reflecting the difficulty of handling the risk. The monitoring coefficient is determined based on the monitoring weight, the risk monitoring frequency, and historical monitoring records, demonstrating the completeness of historical monitoring.

[0117] By comprehensively summing the coefficients of the four dimensions—probability coefficient, impact coefficient, difficulty coefficient, and monitoring coefficient—and performing weighted summation and other calculations, the risk warning coefficient of the risk point to be warned is obtained. This transforms the complex characteristics of the risk point into a quantitative value, intuitively presenting the warning level of the risk point in the current project.

[0118] Based on the comprehensive risk coefficient, the target early warning risk points corresponding to the bidding project are obtained as follows:

[0119] The risk point with the highest comprehensive risk coefficient is marked as the target risk point for the bidding project.

[0120] This application uses data processing and calculation in the bidding risk warning process to obtain a comprehensive risk coefficient for each potential risk point. This coefficient integrates multiple dimensions such as risk correlation and impact, reflecting the degree of threat posed by the risk point to the project. When determining the target risk point for warning, the comprehensive risk coefficient of all potential risk points is compared, and the risk point with the highest coefficient is selected. This is because a higher comprehensive risk coefficient means that the potential threat posed by the risk point to the bidding project is more prominent in terms of probability of occurrence, degree of impact, and closeness of correlation. Marking this as the target risk point allows project participants to focus on the most critical and priority risks, accurately allocate resources for prevention and control, improve the pertinence and efficiency of risk warning and management, and ensure a smoother progress of the bidding project.

[0121] Example 2 further illustrates the bidding risk early warning system based on a large model proposed in this invention.

[0122] A bidding risk early warning system based on a large model includes:

[0123] Acquisition Module: Acquires basic information data and historical bidding data of bidding projects; generates project feature maps of bidding projects based on basic information data; and obtains project risk feature database based on project feature maps.

[0124] Data Acquisition and Matching Module: Collects the risk identification range of the early warning model, and performs feature matching based on the risk identification range and the project risk feature library to obtain the risk points to be warned for the bidding project;

[0125] The first processing module obtains the risk correlation trajectory between the risk points to be warned and the bidding projects based on the historical bidding data of the bidding projects, and obtains the risk correlation coefficient corresponding to the risk points to be warned based on the risk correlation trajectory.

[0126] Analysis module: Sets risk warning parameters for bidding projects based on basic information data; obtains historical risk parameters of risk points to be warned; and analyzes the risk warning parameters and historical risk parameters of risk points to be warned to obtain the risk warning coefficient corresponding to the risk points to be warned.

[0127] The second processing module: Based on the risk correlation coefficient and the risk impact coefficient, the comprehensive risk coefficient corresponding to the risk point to be warned is obtained;

[0128] Risk warning module: Based on the comprehensive risk coefficient, the module obtains the target warning risk points corresponding to the bidding project, and generates risk warning information for the bidding project based on the target warning risk points.

[0129] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a bidding risk warning method based on a large model.

[0130] like Figure 3 As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions from the memory 630 to execute a bidding risk warning method based on a large model.

[0131] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0132] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A bidding risk early warning method based on a large model, characterized in that, The method includes the following steps: Obtain basic information data and historical bidding data for bidding projects; generate project feature maps for bidding projects based on the basic information data; and obtain a project risk feature database based on the project feature maps. The risk identification range of the large-scale early warning model is collected, and feature matching is performed based on the risk identification range and the project risk feature library to obtain the risk points to be warned for the bidding project. Based on historical bidding data of bidding projects, the risk correlation trajectory between potential warning risk points and bidding projects is obtained, specifically including the following steps: Obtain the historical risk location of the risk points to be warned; obtain the event location of historical risk events based on the historical bidding data of bidding projects; Based on the historical risk location and event location, the risk correlation between historical risk events and risk points to be warned is obtained; Based on the risk correlation between historical risk events and risk points to be warned, a risk correlation trajectory between risk points to be warned and bidding projects is generated. And based on the risk correlation trajectory, the risk correlation coefficients corresponding to the risk points to be warned are obtained; Set risk warning parameters for bidding projects based on basic information data; obtain historical risk parameters for risk points to be warned; and analyze the risk warning parameters and historical risk parameters of risk points to be warned to obtain the risk warning coefficients corresponding to the risk points to be warned. The comprehensive risk coefficient corresponding to the risk point to be warned is obtained based on the risk correlation coefficient and the risk impact coefficient; Based on the comprehensive risk coefficient, the target early warning risk points corresponding to the bidding project are obtained, and risk early warning information for the bidding project is generated based on the target early warning risk points.

2. The bidding risk early warning method based on a large model according to claim 1, characterized in that, Based on basic information data, a project feature map of the bidding project is generated, and based on the project feature map, a project risk feature database is obtained. The specific steps include: Collect the first time point when the bidding process begins and the second time point when the bid evaluation process ends for the bidding project. The project cycle of the bidding project is obtained based on the first and second time nodes, and a project feature map of the bidding project is generated based on the basic information within the project cycle. Obtain the attribute information of each feature point in the project feature map. The attribute information includes key feature attributes and secondary feature attributes. Set feature classification criteria based on key feature attributes and secondary feature attributes. Construct a project risk feature library based on feature classification criteria.

3. The bidding risk early warning method based on a large model according to claim 2, characterized in that, Based on the risk identification scope and the project risk feature database, feature matching is performed to obtain the risk points to be warned for the bidding project, specifically: If the risk identification scope of the early warning model includes risk features in the project risk feature library, then the risk points corresponding to the risk features will be marked as the risk points to be warned for the bidding project.

4. The bidding risk early warning method based on a large model according to claim 3, characterized in that, And based on the risk correlation trajectory, the risk correlation coefficient corresponding to the risk point to be warned is obtained, which specifically includes the following steps: Set risk association intervals, each of which corresponds to a risk weight; Based on the inclusion relationship between the risk correlation degree and the risk correlation interval in the risk correlation trajectory, the risk correlation trajectory is divided to obtain at least one segmented risk correlation trajectory; Extract the target risk weights from the segmented risk correlation trajectories; Based on the segmented risk correlation trajectory and the target risk weight corresponding to the segmented risk correlation trajectory, the risk correlation coefficient corresponding to the risk point to be warned is obtained.

5. The bidding risk early warning method based on a large model according to claim 4, characterized in that, And based on the basic information data, risk warning parameters for bidding projects are set, specifically including the following steps: Based on basic information data, the project type and project size of the bidding project are obtained; Risk warning parameters for bidding projects are set according to the project type and project size; The risk warning parameters include the risk occurrence probability threshold, risk impact threshold, risk response difficulty threshold, and risk monitoring frequency for bidding projects.

6. The bidding risk early warning method based on a large model according to claim 5, characterized in that, Obtain historical risk parameters for the risk points to be warned, and analyze the risk warning parameters and historical parameters of the risk points to be warned to obtain the risk warning coefficients corresponding to the risk points to be warned. This includes the following steps: The historical risk parameters include the historical occurrence probability, historical impact, historical response difficulty, and historical monitoring records of the risk points to be warned. Set risk parameter weights; wherein, the risk parameter weights include probability weights, impact weights, difficulty weights, and monitoring weights; By comparing the risk warning parameters of the bidding project with the historical risk parameters of the risk points to be warned, the parameter-matched risk points of the risk points to be warned are obtained. The probability coefficients of parameter-fitted risk points are obtained based on probability weights, risk occurrence probability thresholds, and the historical occurrence probabilities of parameter-fitted risk points. The influence coefficient of the parameter-adapted risk point is obtained based on the influence weight, the risk influence threshold, and the historical influence of the parameter-adapted risk point. The difficulty coefficient of the parameter-adapted risk point is obtained based on the difficulty weight, the risk response difficulty threshold, and the historical response difficulty of the parameter-adapted risk point. The monitoring coefficient of the parameter-adapted risk point is obtained based on the monitoring weight, risk monitoring frequency, and historical monitoring records of the parameter-adapted risk point. The risk warning coefficient corresponding to the risk point to be warned is obtained based on the probability coefficient, impact coefficient, difficulty coefficient and monitoring coefficient.

7. The bidding risk early warning method based on a large model according to claim 6, characterized in that, Based on the comprehensive risk coefficient, the target early warning risk points corresponding to the bidding project are obtained as follows: The risk point with the highest comprehensive risk coefficient is marked as the target risk point for the bidding project.

8. A bidding risk early warning system based on a large model, applied to the bidding risk early warning method based on a large model according to any one of claims 1-7, characterized in that, include: Acquisition module: Acquires basic information data and historical bidding data for bidding projects; Based on basic information data, a project feature map of the bidding project is generated, and a project risk feature database is obtained based on the project feature map; Data Acquisition and Matching Module: Collects the risk identification range of the early warning model, and performs feature matching based on the risk identification range and the project risk feature library to obtain the risk points to be warned for the bidding project; The first processing module: Based on historical bidding data of bidding projects, it obtains the risk correlation trajectory between the risk points to be warned and the bidding projects, specifically including the following steps: Obtain the historical risk location of the risk points to be warned; obtain the event location of historical risk events based on the historical bidding data of bidding projects; Based on the historical risk location and event location, the risk correlation between historical risk events and risk points to be warned is obtained; Based on the risk correlation between historical risk events and risk points to be warned, a risk correlation trajectory between risk points to be warned and bidding projects is generated. And based on the risk correlation trajectory, the risk correlation coefficients corresponding to the risk points to be warned are obtained; Analysis module: Sets risk warning parameters for bidding projects based on basic information data; obtains historical risk parameters of risk points to be warned; and analyzes the risk warning parameters and historical risk parameters of risk points to be warned to obtain the risk warning coefficient corresponding to the risk points to be warned. The second processing module: Based on the risk correlation coefficient and the risk impact coefficient, the comprehensive risk coefficient corresponding to the risk point to be warned is obtained; Risk warning module: Based on the comprehensive risk coefficient, the module obtains the target warning risk points corresponding to the bidding project, and generates risk warning information for the bidding project based on the target warning risk points.

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 program, it implements a bidding risk warning method based on a large model as described in any one of claims 1 to 7.

Images