Information management method and system based on electronic bidding transaction platform

Abstract

The invention discloses an information management method and system based on an electronic bidding transaction platform, and relates to the technical field of information management. By constructing a multi-dimensional and multi-level information management system, deep mining and intelligent identification of potential association relationships and behavior patterns among bidding units are realized, so that the capability of the electronic bidding platform in the aspects of risk prevention and control and abnormal behavior identification is effectively improved. By fusing multi-source heterogeneous data such as industry and commerce registration information, bidding history, project contracts and the like and introducing atlas modeling and semantic analysis technologies, key risk factors such as legal person penetration, historical cooperation, high bidding document similarity and the like can be accurately identified, then the risk association strength between bidding units is quantitatively evaluated, and the risk assessment efficiency is improved. And a visual map and an auxiliary auditing mechanism are formed, so that the judgment efficiency of supervisors is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to an information management method and system based on an electronic bidding transaction platform. Background Art

[0002] With the continuous advancement of "Internet Plus" and digital government, electronic bidding platforms, as key information-based tools for government procurement, engineering construction, and large-scale project management, have played a significant role in improving bidding efficiency, reducing transaction costs, and enhancing transparency. In particular, in areas such as construction engineering, infrastructure development, and government procurement, electronic bidding platforms have gradually replaced traditional offline operations, enabling online processing of the entire project process, including project announcements, qualification reviews, document uploads, bid opening and evaluation, and contract filing. Furthermore, with the continued development of new-generation information technologies such as blockchain, big data, and artificial intelligence, the ability to conduct in-depth information mining and risk management based on platform data has become a key area of ​​focus for the evolution and upgrade of electronic bidding platforms.

[0003] While existing electronic bidding platforms already possess the basic capabilities for data collection and online transactions, they still face significant deficiencies in compliance review and risk warning for bidding activities. For one thing, most systems currently only focus on static bidding information collection and basic comparison, lacking dynamic modeling and structured recognition of deeper information such as historical connections between bidders, equity relationships, and collaborative activities. This makes it difficult to promptly detect hidden risk behaviors such as undercover bidding and bid rigging.

[0004] On the other hand, existing technologies lack semantic analysis and behavioral pattern recognition of bid document content, making it impossible to accurately identify collaborative behavior between suspected bidders based on text similarity, term overlap, structural templates, etc. Furthermore, the lack of efficient visualization methods makes it difficult for regulators to quickly identify complex correlation paths and potential risks, increasing the difficulty and subjectivity of manual review. Summary of the Invention

[0005] In view of the common problems of weak identification of related information and difficulty in detecting risky behaviors in existing electronic bidding technologies, the present invention proposes an information management method and system based on an electronic bidding transaction platform.

[0006] Therefore, the problem to be solved by the present invention is the problem of deep relationship identification and intelligent early warning of behavioral risks among bidding units.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides an information management method based on an electronic bidding transaction platform, which includes: step S1: collecting bidding unit data information from the electronic bidding platform, and standardizing and structuring the data information to establish basic data information nodes; step S2: based on the structured data information, using rule reasoning and entity matching technology to construct a graph structure between bidding units, including explicit or implicit association relationships; step S3: using natural language processing technology to extract semantic features and perform similarity comparison on the bidding documents of the current project, and identify suspicious behavior patterns of multiple units; step S4: fusing structural association information with semantic behavior analysis results to model the integration, calculate the risk association strength between bidding units, and generate risk level labels; step S5: presenting the risk association strength and risk level labels in a graph visualization manner, supporting supervisors to view the association paths and behavior trajectories of bidding units, and providing a manual review interface to assist in judgment, forming a closed-loop processing mechanism.

[0008] As a preferred solution of the information management method based on the electronic bidding and tendering transaction platform of the present invention, the specific implementation process of step S1 includes: Collecting original information data sets from bidding units on the electronic bidding platform, including business registration information, historical bidding records, project winning information, and contract terms, and setting identification fields for the original information data sets according to data source, data timestamp, and data type; Preset field templates, and reorganize and regularize the unstructured fields in the original information dataset, reconstructing legal person information, shareholder structure, historical project keywords, and contract clause summaries into a structured field set, and annotating field confidence parameters; Performing a semantic unification operation on the natural language content in the structured field set, standardizing the contract clause text, project winning bid information, and service terms in the contract clause text based on semantic normalization rules to obtain a unified semantic expression field set; Based on the structured field set and the unified semantic expression field set, a bidding unit basic node is established. The bidding unit basic node includes an identification field, a field confidence parameter and a semantic expression field, and serves as the basic metadata of the unit node in the knowledge graph.

[0009] As a preferred solution of the information management method based on the electronic bidding transaction platform of the present invention, the specific implementation process of step S2 includes: Extract the legal person name field, contact information field, and registered address field from the basic information node to form a candidate entity set, and use entities whose field confidence is greater than the preset entity confidence threshold as the high-confidence entity set; Based on the legal person name field and registered capital field in the highly trusted entity set, under the preset equity inference rule conditions, the control path relationship strength between the two bidding units is calculated; if the control path relationship strength between the two bidding units is greater than or equal to a preset control path relationship strength threshold, the two bidding unit base nodes are connected as an equity control relationship edge; Perform a joint comparison between the keyword fields of historical bidding projects and the time fields of winning projects in the high-confidence entity set, determine whether there is a historical joint bidding behavior between the two bidding units based on the overlap rate of project participation time and the semantic similarity of keywords, and construct a joint behavior relationship edge; A graph structure consisting of unit nodes, equity control relationship edges, and joint behavior relationship edges is used as the initial knowledge graph between bidding units, and the nodes in the graph structure inherit identification fields and semantic expression fields.

[0010] As a preferred solution of the information management method based on the electronic bidding transaction platform of the present invention, the specific implementation process of step S3 also includes: Perform text segmentation processing on each document in the current project bidding document set, extract the semantic substructure set consisting of the bidding terms response segment, technical parameter segment and company profile segment, and annotate each semantic segment with the paragraph position number and original unit; Based on the semantic substructure set, a contextual embedding model is used to generate a vector representation for each semantic segment. The semantic segment vectors submitted by different bidding units are then compared pairwise based on a set window length to construct a semantic comparison matrix. Evaluate all elements in the semantic comparison matrix. If there are more than three semantic segments between any pair of units with similarity higher than the preset semantic consistency threshold, mark the pair of units as a highly semantically consistent set. For the semantic structure matching of all unit pairs in the highly consistent semantic set, a semantic repetition index is calculated based on the distribution density of similar paragraphs and the template structure ratio.

[0011] As a preferred solution of the information management method based on the electronic bidding transaction platform of the present invention, the specific implementation process of step S4 includes: Based on the path set between any two basic nodes of the bidding units in the initial knowledge graph between the bidding units, the path length, path type distribution and associated node density are extracted to form a structural association vector; Retrieve the semantic repetition index of the corresponding units of any two bidding unit basic nodes and construct a semantic behavior vector, including semantic repetition density and template structure ratio; Construct a fusion model to calculate the risk association strength value of the corresponding units of any two bidding unit basic nodes. The input of the fusion model is the structural association vector and the semantic behavior vector, and the output is a risk strength score between 0 and 1. A risk strength threshold is set and a risk level label is generated based on the score. All risk intensity scores are aggregated to form an inter-unit risk matrix.

[0012] As a preferred solution of the information management method based on the electronic bidding transaction platform of the present invention, the specific implementation process of step S5 includes: Based on the graph structure and risk matrix, the risk intensity score is mapped to the corresponding graph edge weight to generate a weighted risk graph, where the color and thickness of the edge reflect the risk level; The node clustering algorithm is applied to the weighted graph to aggregate and display the bidding units in the area where the risk edge weights are concentrated, generate risk cluster areas, and output the central unit and average risk value for each subgraph.

[0013] As a preferred solution of the information management method based on the electronic bidding transaction platform of the present invention, the specific implementation process of step S5 further includes: Mark the behavioral trajectory path in each risk cluster area, including the shortest risk path from the unit node to other nodes, and mark the semantic behavior indicators in the path to form a graph trajectory view; A manual review interface is introduced in the graph view interface, where supervisors label risk clusters and their paths. The labels are written back to the structure graph and the risk matrix is ​​updated. The graph trajectory view also includes a risk progression model driven by a causal rule chain. The risk progression model constructs a number of causal rule chains based on behavior and semantic signals based on the explicit or implicit relationships between bidders. Each causal rule chain consists of a set of behavioral events with temporal and deductive relationships. Based on the risk progression model, the risk evolution path is quantitatively modeled and a causal rule chain score is calculated; based on the causal rule chain score, the cumulative increase in risk level between the bidding units is calculated, and a risk label cumulative increase threshold is preset. If the cumulative increase in risk labels between any two bidding units is greater than or equal to the risk label cumulative increase threshold, the two bidding units are marked as having an escalated risk state, and the cumulative increase in risk level is jointly calculated with the risk association strength score to generate an updated risk level label between the bidding units; Based on the updated risk level label, the edge weights between the bidding units in the atlas trajectory view are updated to the risk intensity corresponding to the updated risk level label.

[0014] In the second aspect, an embodiment of the present invention provides an information management system based on an electronic bidding and tendering transaction platform, which includes an information collection module for collecting the business registration information, historical bidding records, project participation information and related contract information of the bidding units from the electronic bidding and tendering platform, and standardizing and structuring the data to establish basic information nodes; a graph construction module for constructing a graph structure between bidding units based on structured data using rule reasoning and entity matching technology, including explicit or implicit association relationships, the explicit or implicit association relationships including legal person association, equity penetration, historical consortium and project cooperation; a semantic analysis module for analyzing the current project's The bidding documents use natural language processing technology to extract semantic features and perform similarity comparison to identify whether there are suspicious behavior patterns among multiple units, including highly similar file content, repeated terms, and templated structures; the risk modeling module is used to integrate structural association information with semantic behavior analysis results to calculate the risk association strength between bidding units and generate risk level labels or early warning prompts; the visual decision module is used to present the risk association strength and risk level labels in a graphical visualization manner, support supervisors to view the association paths and behavior trajectories of bidding units, and provide a manual review interface to assist in judgment, forming a closed-loop processing mechanism.

[0015] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of an information management method based on an electronic bidding and tendering transaction platform as described in the first aspect of the present invention are implemented.

[0016] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program instructions are executed by a processor, the steps of an information management method based on an electronic bidding and tendering transaction platform as described in the first aspect of the present invention are implemented.

[0017] The beneficial effects of the present invention are as follows: by constructing a multi-dimensional, multi-level information management system, the present invention achieves in-depth exploration and intelligent identification of potential correlations and behavioral patterns between bidding units, thereby effectively improving the electronic bidding platform's capabilities in risk prevention and control and abnormal behavior identification. By integrating multi-source heterogeneous data such as industrial and commercial registration information, bidding history, and project contracts, and introducing graph modeling and semantic analysis technology, the present invention can accurately identify key risk factors such as legal person penetration, historical cooperation, and high similarity in bidding documents, and then quantitatively assess the intensity of risk correlations between bidding units, and form a visual graph and auxiliary review mechanism, thereby improving the judgment efficiency of supervisors.

[0018] The present invention has good scalability and operability in practical applications. Through standardized and structured data processing processes, it reduces the risk of information inconsistency interfering with analysis results. At the same time, the fusion model realizes early identification of potential collusion and bid rigging behaviors through cross-comparison of structural paths and semantic features, effectively preventing illegal bidding from damaging market fairness.

[0019] In summary, the present invention not only improves the electronic bidding platform's ability to automatically identify risky behaviors, but also provides important support for building a transparent, trustworthy, and controllable digital trading environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 The figure is a schematic diagram of the steps of an information management method based on an electronic bidding and tendering transaction platform.

[0022] Figure 2 This is a structural diagram of an information management system based on an electronic bidding and tendering transaction platform. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0025] Secondly, the term "one embodiment" or "embodiment" 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 various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0026] Reference Figure 1~Figure 2 , is an embodiment of the present invention, which provides an information management method based on an electronic bidding transaction platform, including: Step S1: Collect bidding unit data information from the electronic bidding platform, standardize and structure the data information, and establish basic data information nodes.

[0027] Specifically, the original information data set of the bidding units on the electronic bidding platform is collected, the original information data set including business registration information, historical bidding records, project winning information and contract terms text, and identification fields are set for the original information data set according to data source, data timestamp and data type; Preset field templates are used to reorganize and regularize the unstructured fields in the original information dataset, reconstructing legal entity information, shareholder structure, historical project keywords, and contract clause summaries into a structured field set and annotating field confidence parameters. These preset field templates are based on the frequency statistics of structured fields in the platform's historical bidding information, combined with standard data items from different industries (such as bidding documents and contract document structures) to form a field template set. Template content includes but is not limited to legal entity name, unified social credit code, bidding response segment fields, and contract clause fields. Historical project keywords are words or phrases that represent the core characteristics of past bidding projects. Keywords are typically extracted from project names, project descriptions, and bidding scopes using the TF-IDF algorithm.

[0028] Furthermore, a semantic unification operation is performed on the natural language content in the structured field set, and the contract clause text, project winning bid information, and service terms in the contract clause text are standardized based on semantic normalization rules to obtain a unified semantic expression field set; Based on the structured field set and the unified semantic expression field set, a bidding unit basic node is established. The bidding unit basic node includes an identification field, a field confidence parameter and a semantic expression field, and serves as the basic metadata of the unit node in the knowledge graph.

[0029] Step S2: Based on the structured data information, rule reasoning and entity matching technology are used to construct a graph structure between bidding units, covering explicit or implicit association relationships.

[0030] Specifically, the legal person name field, contact information field and registered address field in the basic information node are extracted to form a candidate entity set, and the entities whose field confidence is greater than the preset entity confidence threshold are used as the high-confidence entity set; the entity confidence threshold is set based on the confidence distribution of "real matching entities" manually verified in historical annotation data, and the confidence statistical mean plus one standard deviation is used as the initial setting value of the empirical threshold. The optimal threshold can also be automatically adjusted through cross-validation.

[0031] Furthermore, based on the legal person name field and registered capital field in the high-confidence entity set, under the preset equity inference rule conditions, the control path relationship strength between the two bidding units is calculated, referring to the following formula: ; in, represents the control path relationship strength between the i-th bidding unit and the j-th bidding unit, Indicates the influence of the intermediate node in the kth segment path in the equity or position relationship, which is set according to the equity ratio or position level (for example, when the controlling stake is ≥ 50%, 1; when the controlling stake is between 20% and 50%, is 0.5), The contribution value of equity / employment and other control types in the kth segment of the path between the i-th bidder and the j-th bidder (based on the experience of industry experts, scoring based on type, strength, and degree of legal binding), represents the shortest path length between the i-th bidding unit and the j-th bidding unit, and K represents the total number of paths.

[0032] If the control path relationship strength between the two bidding units is greater than or equal to the preset control path relationship strength threshold, the two bidding unit base nodes are connected as an equity control relationship edge; The historical bidding project keyword fields and the winning project time fields in the high-confidence entity set are jointly compared. Based on the project participation time overlap rate and keyword semantic similarity, it is determined whether the two bidding units have historical joint bidding behavior, and a joint behavior relationship edge is constructed. Refer to the following formula: ; represents the historical joint bidding behavior score between the i-th bidding unit and the j-th bidding unit, represents the historical bidding project time set of the i-th bidding unit, represents the historical bidding project time set of the j-th bidding unit, represents the keyword set of historical bidding items of the i-th bidding unit, Represents the keyword set of past bidding projects of the j-th bidding unit. The keyword set refers to a set of high-frequency industry terms extracted from historical bidding projects, such as "municipal infrastructure", "survey and design", "informatization operation and maintenance", "underground pipeline corridor", "new energy photovoltaic construction", etc., which are automatically obtained using keyword extraction algorithms (such as TextRank and TF-IDF) in combination with the tender announcement text.

[0033] Furthermore, a graph structure consisting of unit nodes, equity control relationship edges, and joint behavior relationship edges is used as the initial knowledge graph between bidding units, and the nodes in the graph structure inherit identification fields and semantic expression fields.

[0034] Step S3: Use natural language processing technology to extract semantic features and perform similarity comparison on the bidding documents of the current project to identify suspicious behavior patterns of multiple units.

[0035] Specifically, the text segmentation process is performed on each document in the current project bidding document set, and a semantic substructure set consisting of the bidding terms response segment, the technical parameter segment, and the company profile segment is extracted. Each semantic segment is annotated with a paragraph position number and original unit. Based on the set of semantic substructures, a pre-trained language model (such as BERT or RoBERTa) is used to segment each semantic segment and remove stop words. The sentence vectors are then input into the pre-trained language model to obtain the sentence vector (e.g., the vector corresponding to the [CLS] label). These sentence vectors are then L2-normalized. Semantic segment vectors submitted by different bidders are then compared pairwise based on a set window length to construct a semantic comparison matrix. Furthermore, all elements in the semantic comparison matrix are evaluated. If there are more than three semantic segments with similarity higher than the preset semantic consistency threshold between any pair of bidding unit basic nodes, they are marked as a highly semantically consistent set. For the semantic structure matching of all unit pairs in the highly consistent semantic set, the semantic repetition index is calculated based on the distribution density of similar paragraphs and the template structure ratio, referring to the following formula: ; in, represents the semantic duplication between the bidding documents of the i-th bidding unit and the j-th bidding unit, Indicates the total number of terms in the document, represents the word vector of the mth term in the bidding document of the i-th bidding unit, Represents the word vector of the mth term in the bid document of the jth bidder.

[0036] Step S4: Fusion modeling is performed on the structural association information and the semantic behavior analysis results to calculate the risk association strength between bidding units and generate risk level labels or warning prompts.

[0037] Specifically, based on the path set between any two bidding unit basic nodes corresponding to the units in the initial knowledge graph between the bidding units, the path length, path type distribution and associated node density are extracted to form a structural association vector; Retrieve the semantic repetition index of the corresponding units of any two bidding unit basic nodes and construct a semantic behavior vector, including semantic repetition density and template structure ratio; Furthermore, a fusion model is constructed to calculate the risk association strength value of the corresponding units of any two bidding unit basic nodes. The input of the fusion model is the structural association vector and the semantic behavior vector, and the output is a risk strength score between 0 and 1. A risk strength threshold is set and a risk level label is generated based on the score. Refer to the following formula: ; in, represents the risk association strength score between the i-th bidding unit and the j-th bidding unit, The sigmoid function is used to map the score to the range of 0~1. and are the weight coefficients of the structure and behavior vectors, is a structural vector, representing the characteristic combination of the graph path and historical behavior relationship, is a behavior vector, which represents suspicious behavior features such as semantic repetition.

[0038] The risk level classification rules are as follows: ; in, Indicates the risk level label between the i-th bidding unit and the j-th bidding unit, Indicates the preset high risk threshold, Indicates the preset medium risk threshold.

[0039] All risk intensity scores are aggregated to form an inter-unit risk matrix.

[0040] Step S5: The risk association strength and risk level labels are presented in a visual graph to support supervisors in viewing the association paths and behavior trajectories of the bidding units, and provide a manual review interface to assist in judgment, thus forming a closed-loop processing mechanism.

[0041] Specifically, based on the graph structure and risk matrix, the risk intensity score is mapped to the corresponding graph edge weight to generate a weighted risk graph, where the color and thickness of the edge reflect the risk level; The node clustering algorithm is applied to the weighted graph to aggregate and display the bidding units in the area where the risk edge weights are concentrated, generate risk cluster areas, and output the central unit and average risk value for each subgraph.

[0042] Furthermore, the behavioral trajectory path is marked in each risk cluster area, including the shortest risk path from the unit node to other nodes, and the semantic behavioral indicators are marked in the path to form a graph trajectory view; A manual review interface is introduced in the graph view interface, and supervisors will label risk clusters and their paths, including label status such as "association confirmation", "non-association", and "pending review". The labels will be written back to the structural graph and the risk matrix will be updated.

[0043] The graph trajectory view also includes a risk progression model driven by a causal rule chain. The risk progression model constructs a number of causal rule chains based on behavior and semantic signals based on the explicit or implicit relationships between bidders. Each causal rule chain consists of a set of behavioral events with temporal and deductive relationships. Based on the risk progression model, the risk evolution path is quantitatively modeled and the causal rule chain score is calculated. Refer to the following formula: ; in, represents the score of the causal rule chain between the i-th bidding unit and the j-th bidding unit when the q-th causal rule chain acts on the causal rule chain between the i-th bidding unit and the j-th bidding unit, represents the weight coefficient of the h-th causal event (obtained based on expert experience or data training), Represents the judgment function. If the i-th bidding unit and the j-th bidding unit trigger the h-th causal event, then The value is 1, otherwise it is 0. Represents the number of causal events in the qth causal rule chain.

[0044] Based on the causal rule chain score, the cumulative risk level increment between bidding units is calculated, referring to the following formula: ; in, It represents the cumulative increase in risk level between the i-th bidding unit and the j-th bidding unit, Represents the preset risk advancement step coefficient, represents the total number of causal rule chains, represents the trigger threshold value of the preset qth causal rule chain, represents the indicator function, if , then it is 1, otherwise it is 0.

[0045] A risk label cumulative increase threshold is preset. If the cumulative increase in the risk labels between any two bidding units is greater than or equal to the risk label cumulative increase threshold, the two bidding units will be marked as risk escalation status, and the cumulative increase in risk level and the risk association strength score will be jointly calculated to generate an updated risk level label between the bidding units. The calculation formula is as follows: ,in, Updated risk level label between the i-th bidding unit and the j-th bidding unit.

[0046] Based on the updated risk level label, the edge weights between the bidding units in the atlas trajectory view are updated to the risk intensity corresponding to the updated risk level label.

[0047] Furthermore, this embodiment also provides an information management system based on the electronic bidding and tendering transaction platform, including: an information collection module for collecting the business registration information, historical bidding records, project participation information and related contract information of the bidding units from the electronic bidding and tendering platform, and standardizing and structuring the data to establish basic information nodes; a graph construction module for constructing a graph structure between bidding units based on structured data using rule reasoning and entity matching technology, including explicit or implicit association relationships, the explicit or implicit association relationships including legal person association, equity penetration, historical consortium and project cooperation; a semantic analysis module for analyzing the investment in the current project The bidding documents use natural language processing technology to extract semantic features and perform similarity comparison to identify whether there are suspicious behavior patterns among multiple units, including highly similar file content, repeated terms, and templated structures; the risk modeling module is used to integrate structural association information with semantic behavior analysis results to model, calculate the risk association strength between bidding units, and generate risk level labels or early warning prompts; the visual decision module is used to present the risk association strength and risk level labels in a graphical visualization manner, support supervisors to view the association paths and behavior trajectories of bidding units, and provide a manual review interface to assist in judgment, forming a closed-loop processing mechanism.

[0048] This embodiment also provides a computer device, which is suitable for an information management method based on an electronic bidding and tendering transaction platform, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement an information management method based on an electronic bidding and tendering transaction platform as proposed in the above embodiment.

[0049] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0050] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, an information management method based on an electronic bidding and tendering transaction platform as proposed in the above embodiment is implemented.

[0051] In summary, the present invention, by constructing a multi-dimensional, multi-level information management system, achieves in-depth exploration and intelligent identification of potential correlations and behavioral patterns between bidding units, thereby effectively improving the electronic bidding platform's capabilities in risk prevention and control and abnormal behavior identification. By integrating multi-source heterogeneous data such as industrial and commercial registration information, bidding history, and project contracts, and introducing graph modeling and semantic analysis technology, the present invention can accurately identify key risk factors such as legal person penetration, historical cooperation, and high similarity of bidding documents, and then quantitatively assess the intensity of risk correlations between bidding units, and form a visual graph and auxiliary review mechanism, thereby improving the judgment efficiency of supervisors.

[0052] The present invention has good scalability and operability in practical applications. Through standardized and structured data processing processes, it reduces the risk of information inconsistency interfering with analysis results. At the same time, the fusion model realizes early identification of potential collusion and bid rigging behaviors through cross-comparison of structural paths and semantic features, effectively preventing illegal bidding from damaging market fairness.

[0053] In summary, the present invention not only improves the electronic bidding platform's ability to automatically identify risky behaviors, but also provides important support for building a transparent, trustworthy, and controllable digital trading environment.

[0054] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An information management method based on an electronic bidding and tendering transaction platform, characterized by: include: Step S1: Collect bidding unit data information from the electronic bidding platform, standardize and structure the data information, and establish basic data information nodes; Step S2: Based on the structured data information, rule reasoning and entity matching technology are used to construct a graph structure between bidding units, including explicit or implicit association relationships; Step S3: Using natural language processing technology to extract semantic features and perform similarity comparison on the bidding documents of the current project to identify suspicious behavior patterns of multiple units; Step S4: Fusion modeling is performed on the structural association information and the semantic behavior analysis results to calculate the risk association strength between the bidding units and generate risk level labels; Step S5: The risk association strength and risk level labels are presented in a visual graph to support supervisors in viewing the association paths and behavior trajectories of the bidding units, and provide a manual review interface to assist in judgment, thus forming a closed-loop processing mechanism.

2. The information management method based on the electronic bidding and tendering transaction platform according to claim 1 is characterized in that: The step S1 comprises: Collecting original information data sets from bidding units on the electronic bidding platform, including business registration information, historical bidding records, project winning information, and contract terms, and setting identification fields for the original information data sets according to data source, data timestamp, and data type; Preset field templates, and reorganize and regularize the unstructured fields in the original information dataset, reconstructing legal person information, shareholder structure, historical project keywords, and contract clause summaries into a structured field set, and annotating field confidence parameters; Performing a semantic unification operation on the natural language content in the structured field set, standardizing the contract clause text, project winning bid information, and service terms in the contract clause text based on semantic normalization rules to obtain a unified semantic expression field set; Based on the structured field set and the unified semantic expression field set, a bidding unit basic node is established. The bidding unit basic node includes an identification field, a field confidence parameter and a semantic expression field, and serves as the basic metadata of the unit node in the knowledge graph.

3. The information management method based on the electronic bidding and tendering transaction platform according to claim 2 is characterized in that: The step S2 comprises: Extract the legal person name field, contact information field, and registered address field from the basic information node to form a candidate entity set, and use entities whose field confidence is greater than the preset entity confidence threshold as the high-confidence entity set; Based on the legal person name field and registered capital field in the highly trusted entity set, under the preset equity inference rule conditions, the control path relationship strength between the two bidding units is calculated; if the control path relationship strength between the two bidding units is greater than or equal to a preset control path relationship strength threshold, the two bidding unit base nodes are connected as an equity control relationship edge; Perform a joint comparison between the keyword fields of historical bidding projects and the time fields of winning projects in the high-confidence entity set, determine whether there is a historical joint bidding behavior between the two bidding units based on the overlap rate of project participation time and the semantic similarity of keywords, and construct a joint behavior relationship edge; A graph structure consisting of unit nodes, equity control relationship edges, and joint behavior relationship edges is used as the initial knowledge graph between bidding units, and the nodes in the graph structure inherit identification fields and semantic expression fields.

4. The information management method based on the electronic bidding and tendering transaction platform according to claim 3 is characterized in that: The step S3 comprises: Perform text segmentation processing on each document in the current project bidding document collection, extract the semantic substructure set consisting of the bidding terms response section, technical parameter section, and company profile section, and annotate each semantic section with the paragraph position number and original unit; Based on the semantic substructure set, a contextual embedding model is used to generate a vector representation for each semantic segment. The semantic segment vectors submitted by different bidding units are then compared pairwise based on a set window length to construct a semantic comparison matrix. All elements in the semantic comparison matrix are evaluated. If there are more than three semantic segments with similarity higher than the preset semantic consistency threshold between any unit pair, they are marked as a highly semantically consistent set. For the semantic structure matching of all unit pairs in the highly consistent semantic set, a semantic repetition index is calculated based on the distribution density of similar paragraphs and the template structure ratio.

5. The information management method based on the electronic bidding and tendering transaction platform according to claim 4 is characterized in that: The step S4 comprises: Based on the path set between any two basic nodes of the bidding units in the initial knowledge graph between the bidding units, the path length, path type distribution and associated node density are extracted to form a structural association vector; Retrieve the semantic repetition index of the corresponding units of any two bidding unit basic nodes and construct a semantic behavior vector, including semantic repetition density and template structure ratio; Construct a fusion model to calculate the risk association strength value of the corresponding units of any two bidding unit basic nodes. The input of the fusion model is the structural association vector and the semantic behavior vector, and the output is the normalized risk strength score. The risk strength threshold is set and the risk level label is generated according to the score. All risk intensity scores are aggregated to form an inter-unit risk matrix.

6. The information management method based on the electronic bidding and tendering transaction platform according to claim 5 is characterized in that: The step S5 comprises: Based on the graph structure and risk matrix, the risk intensity score is mapped to the corresponding graph edge weight to generate a weighted risk graph, where the color and thickness of the edge reflect the risk level; The node clustering algorithm is applied to the weighted graph to aggregate and display the bidding units in the area where the risk edge weights are concentrated, generate risk cluster areas, and output the central unit and average risk value for each subgraph.

7. The information management method based on the electronic bidding and tendering transaction platform according to claim 6 is characterized in that: The step S5 further includes: Mark the behavioral trajectory path in each risk cluster area, including the shortest risk path from the unit node to other nodes, and mark the semantic behavior indicators in the path to form a graph trajectory view; A manual review interface is introduced in the graph view interface, allowing supervisors to label risk clusters and their paths, including association confirmation, non-association, and pending review. The labels will be written back to the structure graph and the risk matrix will be updated; The graph trajectory view also includes a risk progression model driven by a causal rule chain. The risk progression model constructs a number of causal rule chains based on behavior and semantic signals based on the explicit or implicit relationships between bidders. Each causal rule chain consists of a set of behavioral events with temporal and deductive relationships. Based on the risk progression model, the risk evolution path is quantitatively modeled and a causal rule chain score is calculated; based on the causal rule chain score, the cumulative increase in risk level between the bidding units is calculated, and a risk label cumulative increase threshold is preset. If the cumulative increase in risk label between any two bidding units is greater than or equal to the risk label cumulative increase threshold, the two bidding units are marked as having an escalated risk state, and the cumulative increase in risk level is jointly calculated with the risk association strength score to generate an updated risk level label between the bidding units; Based on the updated risk level label, the edge weights between the bidding units in the atlas trajectory view are updated to the risk intensity corresponding to the updated risk level label.

8. An information management system based on an electronic bidding and tendering transaction platform, based on the information management method based on an electronic bidding and tendering transaction platform according to any one of claims 1 to 7, characterized in that: Also includes: The information collection module is used to collect the bidding units' business registration information, historical bidding records, project participation information and related contract information from the electronic bidding platform, standardize and structure the data, and establish basic information nodes; A graph construction module is used to construct a graph structure between bidding units based on structured data using rule reasoning and entity matching technology, including explicit or implicit relationships, such as legal person relationships, equity penetration, historical consortiums, and project collaborations; A semantic analysis module, which uses natural language processing technology to extract semantic features and perform similarity comparisons on the current project's bidding documents to identify suspicious behavior patterns across multiple entities, including highly similar document content, repeated terminology, and templated structures. The risk modeling module is used to integrate structural association information with semantic behavior analysis results to calculate the risk association strength between bidding units and generate risk level labels or early warning prompts; The visual decision-making module is used to present the risk association intensity and risk level labels in a graphically visualized manner, supporting supervisors to view the association paths and behavioral trajectories of bidding units, and providing a manual review interface to assist in judgment, thus forming a closed-loop processing mechanism.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the information management method based on the electronic bidding and tendering transaction platform described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of an information management method based on an electronic bidding and tendering transaction platform as described in any one of claims 1 to 7 are implemented.

Images