Intelligent bid evaluation data processing method and system

Abstract

The invention discloses a bid evaluation data intelligent processing method and system, and relates to the technical field of electronic bid invitation and bidding, and the method comprises the steps: obtaining multi-source heterogeneous data, and carrying out the structural conversion processing of the multi-source heterogeneous data; based on the model construction data, bidding subject features, bidding content features and bidding behavior features are extracted, a multi-layer association relationship among the features is analyzed, and an association analysis model is constructed; inputting the current to-be-evaluated bid data into the correlation analysis model, executing abnormal bid identification and outputting abnormal behavior early warning information; performing intelligent analysis processing on the current to-be-evaluated bid data, and extracting bid evaluation auxiliary information; based on the abnormal behavior early warning information and the bid evaluation auxiliary information, bid evaluation decision suggestions are generated, and a visual interface is constructed; and encrypting and storing bid evaluation process data through a distributed storage technology. According to the method, through structured processing and feature extraction of the multi-source heterogeneous data, comprehensive association analysis of the bidding data is realized, and scientificity and accuracy of bid evaluation decisions are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic bidding and tendering, and in particular to a method and system for intelligently processing bid evaluation data. Background Art

[0002] With the widespread adoption of electronic bidding, the amount of data generated during the bid evaluation process is becoming increasingly large and complex, yet existing bid evaluation systems still have significant shortcomings. Current bid evaluation systems primarily rely on manual review or single technical methods (such as electronic signatures), lacking the ability to integrate and process multi-source, heterogeneous data. In practice, historical bidder data, market trends, corporate credit reports, and other information are often dispersed across disparate systems, making multi-dimensional correlation analysis difficult and hindering comprehensive decision-making support for bid evaluation experts.

[0003] Furthermore, the traditional bid evaluation process lacks transparency, evaluation records can be tampered with, and expert bias is difficult to effectively circumvent, making bid rigging and collusion highly concealed. Bid evaluation experts are required to manually review numerous bid documents during the review process, which is labor-intensive and inefficient. This is especially true in remote bid evaluation scenarios, which lack effective expert collaboration mechanisms and real-world interaction capabilities. Furthermore, existing systems often isolate emerging technologies like blockchain, artificial intelligence, and virtual reality, preventing them from forming an effective technological integration system. Summary of the Invention

[0004] The present invention provides a method and system for intelligent processing of bid evaluation data, which are used to solve the technical problems of insufficient data integration, opaque process and low evaluation efficiency in existing bid evaluation systems.

[0005] In view of this, the first aspect of the present invention provides a method for intelligently processing bid evaluation data, comprising: Acquire multi-source heterogeneous data related to bid evaluation and perform structured conversion on the multi-source heterogeneous data; the multi-source heterogeneous data includes model construction data and current bid evaluation data; Based on the model-based data construction, the bidding subject characteristics, bidding content characteristics and bidding behavior characteristics are extracted, and the multi-layer correlation relationship between the characteristics is analyzed to build a correlation analysis model; Input the current bid data to be evaluated into the association analysis model, perform abnormal bidding identification and output abnormal behavior warning information; Intelligently analyze and process the current bid evaluation data to extract auxiliary information for bid evaluation; Generate bid evaluation decision suggestions and build a visual interface based on abnormal behavior warning information and bid evaluation auxiliary information; The bidding process data is encrypted and stored through distributed storage technology.

[0006] Optionally, the model building data includes historical bidding data, extended verification data and process evidence data; the current data to be evaluated includes bidder qualification documents, structured technical bid documents and standardized business quotation documents.

[0007] Optionally, analyzing the multi-layer association relationships between features and building an association analysis model includes: Calculate the correlation index between the bidding subject characteristics, bidding content characteristics and bidding behavior characteristics, and determine the connection relationship between the characteristics based on the preset correlation threshold to generate a feature correlation network; The nodes in the feature correlation network are classified according to the bidding subject characteristics, bidding content characteristics and bidding behavior characteristics, and a multi-layer feature network structure is constructed; Perform topological analysis on multi-layer characteristic network structures to determine key nodes and connection paths in the network; Using graph embedding technology, the nodes and their topological relationships in the multi-layer feature network structure are converted into low-dimensional vector representations, and high-order correlation patterns between features are extracted; An association analysis model is established based on low-dimensional vector representation and high-order association patterns.

[0008] Optionally, performing abnormal bidding identification and outputting abnormal behavior warning information includes: Build a feature library of abnormal bidding behavior; Based on the association analysis model, the current bid evaluation data is converted into association feature vectors, and high-order association patterns are extracted; Calculate the similarity between the associated feature vector and the feature vectors of each abnormal type in the abnormal bidding behavior feature library, and filter abnormal bidding candidates based on the preset similarity threshold; Cluster analysis of abnormal bidding candidates is performed using high-order association patterns to generate multiple abnormal bidding clusters; Extract abnormal correlation patterns from abnormal bidding clusters and evaluate the abnormal risk level based on the abnormal correlation patterns; Generate abnormal behavior warning information based on the degree of abnormal risk.

[0009] Optionally, intelligent analysis and processing of the current bid evaluation data includes: Analyze bidder qualification documents, verify compliance and validity, and generate qualification assessment results; Analyze structured technical bids, evaluate the feasibility, innovation and responsiveness of technical content, and form a basis for technical scoring; Analyze standardized commercial quotation documents, determine the rationality and completeness of quotations, and generate quotation evaluation conclusions; Compare and analyze the differences, strengths and weaknesses of the technical contents of different bidders to form horizontal comparison data; Integrate qualification assessment results, technical scoring basis, quotation evaluation conclusions and horizontal comparison data to generate structured bid evaluation auxiliary information.

[0010] Optionally, generating a bid evaluation decision suggestion and building a visual interface includes: Construct a decision matrix, cross-analyze abnormal behavior warning information and bid evaluation auxiliary information, and form a decision support data structure; Generate bid evaluation decision suggestions including recommended scoring ranges, abnormal risk warning marks and evaluation key points based on the decision support data structure; Construct a multi-level visual interface for bid evaluation decision recommendations based on qualifications, technology, and business, and mark risk points and decision-making basis in the visual interface; Build an interactive rating input interface and generate real-time rationality prompt information based on the degree of deviation between the expert input rating and the system recommended rating range; The scoring data entered by the review experts through the interactive scoring input interface is recorded as the actual scoring data of the experts, and the scoring trajectory and modification history are recorded to form the review behavior data.

[0011] Optionally, encrypting and storing bid evaluation process data through distributed storage technology includes: Package the bid evaluation process data and generate a data integrity check value; the bid evaluation process data includes bid evaluation decision recommendations, actual expert scoring data, and review behavior data; Using a multi-node distributed storage architecture, the packaged bid evaluation process data is encrypted and stored in shards. Each node stores different data shards and saves the corresponding checksum values. A threshold signature mechanism is used to authorize and control storage nodes.

[0012] A second aspect of the present invention provides an intelligent processing system for bid evaluation data, comprising: The data preprocessing module is used to obtain multi-source heterogeneous data related to bid evaluation and perform structured conversion processing on the multi-source heterogeneous data; The association analysis module is used to construct data based on the model, extract the characteristics of the bidding subject, bidding content and bidding behavior, analyze the multi-layer association relationship between the characteristics, and build an association analysis model; The abnormal bidding identification module is used to input the current bid evaluation data into the correlation analysis model, perform abnormal bidding identification and output abnormal behavior warning information; The bid evaluation auxiliary analysis module is used to perform intelligent analysis and processing on the current bid evaluation data and extract auxiliary information for bid evaluation; The bid evaluation decision support module is used to generate bid evaluation decision suggestions based on abnormal behavior warning information and bid evaluation auxiliary information, and build a visual interface to support expert review decisions; The data encryption and evidence storage module is used to encrypt and store the bid evaluation process data through distributed storage technology.

[0013] According to a third aspect of an embodiment of the present invention, a computer device is provided, comprising: a memory, a processor, and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the first aspect of the present invention and various methods that may be involved in the first aspect.

[0014] According to a fourth aspect of an embodiment of the present invention, a readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the first aspect of the present invention and various methods that may be involved in the first aspect.

[0015] The beneficial effects of the present invention are as follows: the present invention realizes all-round correlation analysis of bidding data through structured processing and feature extraction of multi-source heterogeneous data, effectively improving the scientificity and accuracy of bid evaluation decisions; by calculating the similarity of correlation feature vectors and high-order correlation pattern cluster analysis, it realizes intelligent identification and risk warning of abnormal bidding behaviors such as bid rigging and collusion; a bid evaluation decision support system based on a decision matrix is ​​designed, abnormal behavior warning information and bid evaluation auxiliary information are cross-analyzed, and a multi-level visual interface is constructed, which significantly improves the transparency and review efficiency of the bid evaluation process; a distributed storage architecture and a threshold signature mechanism are used to perform sharded encrypted storage of bid evaluation process data, combined with data integrity verification, to ensure the security and non-tamperability of bid evaluation data, and fundamentally solve the problem of insufficient data credibility in traditional bid evaluation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative work.

[0017] Figure 1 This is a flow chart of the intelligent processing method for bid evaluation data.

[0018] Figure 2 Construct a flow chart for the association analysis model of the intelligent processing method of bid evaluation data.

[0019] Figure 3 This is a flowchart of bid evaluation decision support and visual interaction for the intelligent processing method of bid evaluation data. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0021] The terms "first," "second," "third," "fourth," and so forth (if any) in the description and claims of the present invention and in the accompanying drawings are used to distinguish similar items and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present invention described herein can be practiced in sequences other than those illustrated or described herein.

[0022] It should be understood that in various embodiments of the present invention, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0023] It should be understood that in the present invention, "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0024] It should be understood that in the present invention, "multiple" refers to two or more. "And / or" is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "Contains A, B and C", "Contains A, B, C" means that A, B, and C are all included, "Contains A, B or C" means that one of A, B, and C is included, and "Contains A, B and / or C" means that any one, any two, or any three of A, B, and C are included.

[0025] It should be understood that, in the present invention, "B corresponding to A," "B corresponding to A," "A corresponds to B," or "B corresponds to A" means that B is associated with A and B can be determined based on A. Determining B based on A does not mean determining B based solely on A; B can also be determined based on A and / or other information. A and B match when the similarity between A and B is greater than or equal to a preset threshold.

[0026] Depending on the context, "if" as used herein may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting."

[0027] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0028] Example 1, with reference to Figures 1 to 3 , which is the first embodiment of the present invention, provides an intelligent processing method for bid evaluation data. The flow chart of the method is as follows Figure 1 As shown, the method includes, S1: Obtain multi-source heterogeneous data related to bid evaluation and perform structured conversion processing on the multi-source heterogeneous data.

[0029] Multi-source heterogeneous data includes model construction data and current bid data awaiting evaluation; model construction data includes historical bid data, extended verification data, and process evidence data; current bid data awaiting evaluation includes bidder qualification documents, structured technical bid documents, and standardized commercial quotation documents. Furthermore, historical bid data includes authorized historical bid records and their anomaly markers (such as bid collusion, abnormal bids, and non-qualification). Historical bid records include historical qualification documents, historical technical bid documents, and historical commercial quotation documents; extended verification data includes enterprise credit information and analysis data of related enterprises; and process evidence data includes bid document submission logs, electronic signature records of review experts, and blockchain evidence hash values.

[0030] It should be noted that the process of acquiring multi-source heterogeneous data includes: obtaining historical bidding data from the historical bidding database through a secure data interface (two-way authentication), and regular incremental synchronization; receiving the original files uploaded by the bidder through the electronic bidding system, and generating the current bid evaluation data through pre-defined template parsing; obtaining enterprise credit information through the National Enterprise Credit Information Publicity System API, including enterprise registration information and administrative penalty records; obtaining the equity information of related enterprises through a legally authorized data interface, including equity structure and actual controller information; the bid document submission log contains de-identified IP addresses and timestamps; the electronic signature records of the review experts are generated using compliant CA digital certificates; the blockchain evidence hash value is generated by cryptographic hash calculation of the core terms of the bid document through the blockchain node.

[0031] Furthermore, the following structured transformations are performed on multi-source heterogeneous data, including: for unstructured data (such as PDF qualification documents), key fields are extracted through OCR technology and converted into JSON format; for semi-structured data (such as XML technical bids), they are verified according to predefined XSD templates and converted into relational tables; for standardized data (such as CSV business quotations), the currency unit is forced to be unified and the logical consistency is verified (such as the error between the total of sub-item quotations and the total price is ≤0.01%).

[0032] S2: Build data based on the model, extract bidding subject characteristics, bidding content characteristics and bidding behavior characteristics, analyze the multi-layer correlation relationship between the characteristics, and build a correlation analysis model.

[0033] In a specific embodiment of the present invention, the association analysis model construction flow chart is as follows: Figure 2 Shown, including: S2.1: Build data based on the model to extract bidding entity characteristics, bidding content characteristics, and bidding behavior characteristics.

[0034] Specifically, the bidding entity characteristics are extracted, including: extracting the bidding company's registered capital, qualification level, historical winning rate and qualification non-compliance mark in the abnormal mark from the historical bidding data; extracting the equity structure, actual controller information, related company list, and administrative penalty record from the extended verification data; standardizing the extracted bidding entity characteristics and encoding the category-type features.

[0035] Furthermore, the bidding content features are extracted, including: extracting technical solution keywords and key technical parameters (such as construction period and equipment specifications) from historical technical bid documents; extracting the total price to budget ratio and the dispersion of sub-item quotations from historical business quotation files; extracting quotation anomaly marks and technical solution similarity marks from abnormal mark information; vectorizing the extracted bidding content features and calculating the feature importance weights.

[0036] Furthermore, bidding behavior features are extracted, including: extracting IP address geographical distribution, file upload timestamp sequence, and modification frequency from the bidding document submission log; extracting review time nodes and key review opinion change records from the review expert electronic signature records; extracting file hash values ​​from blockchain evidence hash values; extracting bid rigging marks from abnormal mark information; numerically representing the extracted bidding behavior features, and extracting time series patterns from time series features.

[0037] Finally, the dimensions of various features are reduced and outliers are processed to ensure feature quality.

[0038] S2.2: Calculate the correlation index between the bidding entity characteristics, bidding content characteristics and bidding behavior characteristics, and determine the connection relationship between the characteristics based on the preset correlation threshold to generate a feature correlation network.

[0039] Specifically, a feature pair set is constructed, and specific features in the bidding subject features, bidding content features and bidding behavior features are paired with each other; according to the feature type, the correlation index of the feature pair is calculated, the Pearson correlation coefficient is calculated for the numerical feature pair, the mutual information value is calculated for the categorical feature pair, and the point-two column correlation value is calculated for the mixed type feature pair; based on the historical abnormal bidding case data, the optimal correlation threshold is determined as the preset correlation threshold through cross-validation; the correlation index of the feature pair is compared with the preset correlation threshold, and when the correlation index is greater than or equal to the preset threshold, a connection relationship is established between the corresponding features; a feature correlation network is constructed, in which the features serve as network nodes, the connection relationship as the network edge, and the correlation index value as the edge weight.

[0040] S2.3: Classify the nodes in the feature correlation network according to the bidding entity characteristics, bidding content characteristics and bidding behavior characteristics, and construct a multi-layer feature network structure.

[0041] Furthermore, a category identifier is added to each node in the feature correlation network, and marked as a bidding subject feature node, a bidding content feature node or a bidding behavior feature node; three independent feature layers are created, corresponding to the bidding subject feature layer, the bidding content feature layer and the bidding behavior feature layer respectively; the nodes are mapped to the corresponding feature layers according to the category identifier, while retaining the connection relationship between the nodes; the intra-layer connection and the inter-layer connection are distinguished, forming a multi-layer feature network structure containing three feature layers and their connection relationships.

[0042] Among them, the connection relationship between nodes in the same feature layer in the feature correlation network is retained as intra-layer connection, and the connection relationship between nodes in different feature layers in the feature correlation network is extracted as inter-layer connection; a multi-layer feature network structure including three feature layers and their intra-layer connections and inter-layer connections is constructed.

[0043] S2.4: Perform topological analysis on multi-layer feature network structures to determine key nodes and connection paths in the network.

[0044] Furthermore, the degree centrality of each node in the multi-layer feature network structure is calculated, and nodes that establish connection relationships with multiple other nodes are identified as potential key nodes; the betweenness centrality of each node is calculated, and nodes located on multiple shortest paths are identified as bridging nodes; the eigenvector centrality of each node is calculated, and nodes with greater influence in the overall network structure are identified as core nodes; based on the comprehensive score of the three centralities, the set of key nodes in the network is determined; the shortest connection path between key nodes is determined, and the path weight is calculated, which is equal to the product of all edge weights on the path; the connection paths are sorted based on the path weight, and the top N paths with the highest weights are selected as key connection paths; inter-layer propagation analysis is performed on the key connection paths to identify abnormal feature propagation chains from the bidding subject feature layer through the bidding content feature layer to the bidding behavior feature layer.

[0045] S2.5: Use graph embedding technology to convert the nodes and their topological relationships in the multi-layer feature network structure into low-dimensional vector representations, and extract high-order correlation patterns between features.

[0046] Furthermore, an adjacency matrix of a multi-layer feature network structure is constructed to record the connection relationship and weight information between nodes; a random walk strategy is applied to the adjacency matrix to generate a node co-occurrence sequence; based on the generated node co-occurrence sequence, a distributed representation learning method is used to train the node vector representation, and each feature node is mapped to a vector space of a preset dimension; a hierarchical information weight factor is introduced to perform weighted adjustment on the node vectors between different feature layers to enhance the expressive power of the inter-layer association; the similarity between nodes is calculated in the vector space to construct a node vector similarity matrix; based on the similarity matrix, a clustering algorithm is used to group similar nodes and identify feature combinations of cross-layer connections; a subgraph pattern mining method is used to extract recurring connection patterns from the multi-layer feature network structure; the extracted high-order association patterns are correlated with historical abnormal bidding mark data for correlation analysis to screen out association patterns that are highly correlated with abnormal bidding behavior and establish an association pattern library.

[0047] S2.6: Build an association analysis model based on low-dimensional vector representations and high-order association patterns.

[0048] Optimally, by organizing bidders, content, and behavioral characteristics into a multi-layered network structure, the association analysis model can capture cross-dimensional anomalous propagation paths that are difficult to detect with traditional methods. Multiple centrality metrics are used to identify key nodes and their propagation links, revealing potential collusion relationships. Graph embedding technology, which incorporates hierarchical information weighting factors, achieves efficient vectorized representation while preserving topological relationships, significantly improving the ability to identify high-order association patterns. These innovations enable the association analysis model to discover deep bidding anomalies from complex and heterogeneous data, significantly enhancing the accuracy of identifying hidden collusive bidding behaviors while reducing the rate of false positives, providing regulators with a more precise risk warning tool.

[0049] S3: Input the current bid evaluation data into the association analysis model, perform abnormal bidding identification and output abnormal behavior warning information.

[0050] In a specific embodiment of the present invention, step S3 includes: S3.1: Build a feature library of abnormal bidding behavior.

[0051] Specifically, marked abnormal bidding cases are extracted from the historical bidding data in the model construction data; a multi-layer feature network structure is applied to each abnormal case for feature extraction, and the features are converted into low-dimensional vector representations using graph embedding technology; the feature vectors are classified and stored according to the type of anomaly (such as collusion in bidding, bid rigging, qualification affiliation, etc.); the center point of the feature vector of each type of anomaly is calculated as the typical feature representation of that type of anomaly, forming a complete feature library of abnormal bidding behavior.

[0052] S3.2: Based on the association analysis model, the current bid evaluation data is converted into association feature vectors, and high-order association patterns are extracted.

[0053] Furthermore, the current data to be evaluated is received and preprocessed and standardized according to the input format requirements of the association analysis model; the preprocessed data to be evaluated is input into the association analysis model to obtain the association feature vector; the association feature vector is normalized to eliminate dimensional differences; the potential graph structure representing the relationship between features is extracted from the association feature vector through the forward propagation calculation of the association analysis model; the potential association structure is matched with the association pattern library stored in the model for similarity, and the structure with a matching similarity exceeding the pattern recognition threshold is used as a candidate association pattern; the candidate association patterns are scored for importance using the attention mechanism, and patterns with scores exceeding the importance screening threshold are screened out; multiple filtered association patterns are combined to form a complete high-order association pattern representation.

[0054] Preferably, through the innovative fusion of graph embedding technology and attention mechanism, the automatic recognition and importance quantification of complex correlation patterns between multi-dimensional features of bidding data are achieved, which effectively improves the detection accuracy of covert collusion in bidding behavior and reduces the system's dependence on expert experience.

[0055] S3.3: Calculate the similarity between the associated feature vector and the feature vectors of each abnormal type in the abnormal bidding behavior feature library, and filter abnormal bidding candidates based on the preset similarity threshold.

[0056] Specifically, a hierarchical screening strategy is adopted. First, the associated feature vectors of the current bid evaluation data and the feature vectors of each abnormal type in the abnormal bidding behavior feature library are normalized with L2 norm and converted into unit vector form; then, cosine similarity is used as the initial screening indicator to calculate the cosine similarity value between the associated feature vector and the feature vector of each abnormal type.

[0057] Furthermore, a preliminary screening threshold is set, and samples with cosine similarity values ​​lower than the preliminary screening threshold are directly judged as normal bidding behavior without further calculation; for candidates with cosine similarity values ​​higher than or equal to the preliminary screening threshold, fine screening is performed.

[0058] In the fine screening stage, Mahalanobis distance calculation is selectively applied according to the data distribution characteristics of the anomaly type, and the distance value is mapped to a similarity index in the interval [0,1] through exponential transformation; based on the historical recognition accuracy data of anomaly types pre-stored by the system, it is dynamically determined whether multiple similarity indicators need to be integrated: for anomaly types with high recognition accuracy, only a single optimal index can be used; for anomaly types that are difficult to identify, a weighted fusion strategy is adopted to calculate the comprehensive similarity.

[0059] For the bidding samples after the similarity is determined, differentiated similarity threshold sets are set for different anomaly types based on the severity and historical frequency of the anomaly types predefined by the system; the top k anomaly types with the highest similarity are determined for each candidate, where the k value is dynamically set based on the system resource capabilities and processing priority, and only these k types are subjected to threshold judgment. When the similarity is greater than or equal to the corresponding threshold, the bid is marked as a candidate for the corresponding anomaly type; only the candidates determined to be abnormal are sorted according to the similarity to form a priority-sorted set of abnormal bidding candidates.

[0060] Preferably, through the innovative combination of hierarchical screening and adaptive similarity fusion mechanism, accurate identification and risk grading of different types of abnormal bidding behaviors are achieved, which greatly improves the system processing efficiency and reduces the false alarm rate, showing significant advantages in processing complex bidding scenarios with uneven data distribution.

[0061] S3.4: Use high-order association patterns to perform cluster analysis on abnormal bidding candidates and generate multiple abnormal bidding clusters.

[0062] Specifically, the extracted high-order correlation patterns are converted into structured feature vectors of abnormal bidding candidates. For standard features, their activation strength is directly quantified. For complex graph-structured correlation patterns, a graph kernel method is applied to map the topological relationships into a comparable feature space. Based on this feature representation, a similarity matrix is ​​calculated between abnormal bidding candidates. To address the multidimensional nonlinear nature of the correlation patterns, a cosine similarity metric based on the weighted importance of the correlation patterns is employed. Based on the feature dimensionality and data distribution characteristics, clustering algorithms suitable for high-dimensional data (such as K-means or hierarchical clustering) are selected to group abnormal bidding candidates. Clustering parameters are optimized to enhance sensitivity to key pattern differences. Using multiple evaluation metrics such as the silhouette coefficient and Davies-Bouldin index, combined with cross-validation, the optimal number of clusters is determined, ultimately generating multiple internally consistent abnormal bidding clusters.

[0063] S3.5: Extract abnormal correlation patterns from abnormal bidding clusters and evaluate the abnormal risk level based on the abnormal correlation patterns.

[0064] Furthermore, for each abnormal bidding cluster, the common behavioral characteristics among bidders, including price trends, document similarity, and temporal correlation, are analyzed to identify the interaction network structure among bidders within the cluster. Based on the extracted features and interaction structure, a feature representation of abnormal correlation is constructed, quantifying the distribution strength of features across each dimension to form an operationalized abnormal correlation pattern. By comparing the features with historical abnormal case studies, the specific abnormality type corresponding to each cluster (such as collusion, bid rigging, and qualification fraud) is determined, and all associated bidders within the cluster are identified. A comprehensive risk score is calculated based on the strength and complexity of the abnormal correlation pattern, cluster size, and historical risk distribution. This score is then used to classify abnormal bidding clusters and determine the risk level of each cluster.

[0065] S3.6: Generate abnormal behavior warning information based on the degree of abnormal risk.

[0066] Furthermore, based on the risk assessment results of abnormal bidding clusters, a multi-level anomaly warning knowledge base was constructed, mapping risk levels, anomaly types, and associated bidding entity information into structured warning templates. Warning information containing risk identification, anomaly type, and associated entities was generated for each abnormal bidding cluster. High-risk anomalies were automatically linked to relevant evidence chains and behavioral feature descriptions. By extracting multidimensional anomaly association patterns from abnormal bidding clusters and implementing risk quantification assessments, combined with an intelligent warning generation mechanism based on the warning knowledge base and structured templates, the accuracy of abnormal bidding behavior identification and the timeliness of warnings were significantly improved.

[0067] S4: Perform intelligent analysis and processing on the current bid evaluation data to extract auxiliary information for bid evaluation.

[0068] In a specific embodiment of the present invention, step S4 includes: S4.1: Analyze bidder qualification documents, verify compliance and validity, and generate qualification assessment results.

[0069] Specifically, a qualification assessment rule set is constructed based on project requirements to clarify necessary and priority conditions; information extraction technology is used to obtain key information in the qualification documents, including qualification certificate number, grade, validity period and registered personnel information; the extracted qualification information is compared and verified with the authoritative database to confirm the authenticity of the certificate; the bidder's historical qualification records in the authoritative database are retrieved, and the time series analysis method is used to evaluate its qualification stability and development trend; the qualifications are scored according to the assessment rule set to generate qualification compliance indicators; the verification results, stability analysis and compliance scores are integrated to form a complete qualification assessment result.

[0070] S4.2: Analyze the structured technical bid, evaluate the feasibility, innovation and responsiveness of the technical content, and form the basis for technical scoring.

[0071] Specifically, a technical evaluation framework and indicator system are constructed based on the bidding requirements; natural language processing and text mining technologies are used to automatically extract key technical elements from the technical bid documents, including technical routes, process flows, quality control measures and resource allocation plans; the feasibility of the technical solutions is evaluated, and the rationality of technical parameters and the completeness of implementation conditions are analyzed; innovative points and special contents in the technical solutions are identified, and their application value and technological advancement are evaluated; semantic matching analysis is performed between the content of the technical bid documents and the bidding requirements, and the technical responsiveness and coverage are quantitatively evaluated through keyword weights and topic relevance calculations; the advantages and risks of the technical solutions are evaluated, and combined with the scoring criteria, a systematic technical scoring basis is formed.

[0072] S4.3: Analyze standardized commercial quotation documents, determine the rationality and completeness of the quotation, and generate quotation evaluation conclusions.

[0073] Specifically, check the format standardization and content completeness of the quotation document to confirm that all items required by the tender are covered; extract unit price and total price information through optical character recognition and table parsing technology, and apply automated calculation verification tools to verify arithmetic accuracy and logical consistency; calculate the ratio of the bid price to the procurement budget to evaluate the overall quotation level; analyze the quotation structure, calculate the proportion of each sub-item and compare it with the industry standard; use box plots and Z-score statistical methods to analyze the price distribution of all bidders, and identify abnormally high or low-priced items that are beyond 3 times the standard deviation; conduct a rationality assessment of quotation items that deviate from the normal level; integrate the above analysis results to generate a quotation evaluation conclusion.

[0074] S4.4: Compare and analyze the differences, advantages and disadvantages of the technical contents of different bidders to form horizontal comparative data.

[0075] Specifically, keyword extraction algorithms and structured data extraction technologies are used to automatically identify and extract key indicator parameters from the technical proposals of each bidder, and a technical indicator comparison matrix with unified dimensions is constructed; text similarity calculation models and semantic clustering technologies are used to analyze the content similarity of the technical proposals of different bidders, and accurately distinguish between general content and differentiated personalized content; the differences in the routes of each bidder in key technical links are identified, and the advantages and disadvantages of different technical paths are evaluated; the technical innovations and special contents of each bidder are compared, and their application value in the project is evaluated; based on project requirements, the applicability and implementation effect of each technical proposal are evaluated; and the analysis results are integrated to generate structured horizontal comparison data.

[0076] S4.5: Integrate qualification assessment results, technical scoring basis, quotation evaluation conclusions and horizontal comparison data to generate structured bid evaluation auxiliary information.

[0077] Specifically, the weight allocation of each evaluation dimension is determined based on the scoring criteria of the bidding documents; the evaluation results of different dimensions are standardized to establish a unified and comparable scoring system; the comprehensive score and sub-item score of the bidder are calculated to form a ranking result; anomalies and focus points found in the scoring process are marked to provide key basis and analysis explanations for each score; the scoring results, basis explanations and anomaly annotations are organized into a structured data format to form complete structured bid evaluation auxiliary information.

[0078] Preferably, through the multi-dimensional intelligent analysis framework and deep information extraction technology, key information can be automatically identified and extracted from unstructured and semi-structured documents, greatly improving the efficiency and accuracy of bid evaluation data processing; the introduction of a standardized evaluation method system solves the technical problem that evaluation results of different dimensions cannot be directly compared, making multi-dimensional evaluation results comparable; the innovative integration of abnormal situation identification and annotation functions provides technical support for risk warning in the bid evaluation process and reduces bid evaluation risks; a mechanism for recording key steps in the scoring process is established to ensure the traceability and fairness of bid evaluation decisions.

[0079] S5: Based on abnormal behavior warning information and bid evaluation auxiliary information, generate bid evaluation decision suggestions and build a visual interface to support expert review decisions.

[0080] In a specific embodiment of the present invention, the bid evaluation decision support and visualization interaction flow chart is as follows: Figure 3 Shown, including: S5.1: Construct a decision matrix, cross-analyze abnormal behavior warning information and bid evaluation auxiliary information, and form a decision support data structure.

[0081] Specifically, a two-dimensional decision matrix is ​​created for bidders and evaluation indicators. The qualification assessment results, technical scoring basis, and bid evaluation conclusions are mapped to the decision matrix according to the weight ratios specified in the bid evaluation rules. Based on abnormal behavior warning information, risk levels are annotated in the decision matrix and clustered by anomaly type to form areas of expert focus. Based on historical scoring data and current horizontal comparison results, the expected score ranges for evaluation indicators are calculated, and indicator points with significant differences are marked. The similarity of technical solutions between bidders is calculated and, if the similarity exceeds a preset threshold, a special mark is added to the decision matrix. The above analysis results are integrated to construct a three-dimensional decision support data structure consisting of bidder dimensions, evaluation indicator dimensions, and anomaly association dimensions. This data structure, through multi-dimensional anomaly feature fusion and intelligent visualization mapping, enables correlation analysis between abnormal behavior and bid evaluation elements, improving the scientific nature and explainability of bid evaluation decisions.

[0082] S5.2: Based on the decision support data structure, generate evaluation decision recommendations including recommended scoring ranges, abnormal risk warning marks and evaluation key prompts.

[0083] Furthermore, based on the expected score and fluctuation range in the decision support data structure, a recommended scoring range is generated for each evaluation indicator. For evaluation indicators marked with abnormal risks, a risk level marker is added next to the recommended scoring range, along with a risk type description. For bidders whose technical solution similarity exceeds a preset threshold, a review focus prompt is generated for technical solution similarity. For bidders with abnormal bids, a price rationality analysis prompt based on the market average price deviation rate is generated. Based on the difference significance analysis results of the evaluation indicators, scoring key prompts are generated to guide experts to focus on key differences. The above analysis results are integrated to conduct a comprehensive assessment of each bidder's strengths, weaknesses, and risks, forming a structured evaluation content. Based on the comprehensive evaluation of various dimensions, an overall recommendation is generated, including whether the recommendation is shortlisted, the recommended ranking range, and key points of attention. The generated recommendations are categorized and organized according to the three dimensions of qualifications, technology, and business, forming a structured bid evaluation decision recommendation document. Through the deep integration of multi-dimensional abnormal features and professional evaluation indicators, this bid evaluation decision recommendation system achieves intelligent assistance and risk prevention and control in the bid evaluation process, significantly improving the objectivity and professionalism of the evaluation decision.

[0084] S5.3: Construct a multi-level visual interface for the bid evaluation decision recommendations based on the three dimensions of qualifications, technology, and business, and mark the risk points and decision-making basis in the visual interface.

[0085] Furthermore, a hierarchical visual interface based on the three dimensions of qualifications, technology, and business is designed, and logical connections are established between each layer through related indicators and risk factors; in the qualification review layer, the qualification evaluation results of each bidder are displayed, and qualification anomalies are marked with different identifiers; in the technical review layer, a technical indicator radar chart is constructed to show the scores of each bidder on different technical indicators; in the business review layer, a price comparison chart and price analysis trend chart are constructed to highlight price anomalies and market reference prices.

[0086] S5.4: Construct an interactive scoring input interface for review experts to input scores, and generate rationality prompt information in real time based on the degree of deviation between the scores input by experts and the score range recommended by the system.

[0087] Furthermore, a scoring input matrix is ​​constructed, with each review expert corresponding to a row and each review indicator corresponding to a column; the scoring range recommended by the system is displayed in the scoring input interface and marked with a specific identifier; the scoring values ​​entered by the experts are monitored, and the deviation rate from the midpoint of the recommended scoring range is calculated; when the deviation rate exceeds the preset threshold, a high deviation warning is triggered, and a rationality prompt is generated that requires confirmation by the review expert.

[0088] In the rationality prompt, the analysis of key factors leading to high-deviation judgments is displayed, including historical score distribution, key technical point analysis and abnormal risk prompts; the expert confirmation operations and modification trajectories of high-deviation scores are recorded, including the initial score, number of modifications, final score and confirmation reasons; the score distribution of the review experts is analyzed, and when the scores are polarized, a disagreement reminder is sent to the review team leader; the score consistency index is calculated, and when the consistency index exceeds the preset threshold, the review team leader is advised to organize an expert discussion; an annotation function is provided, allowing review experts to add text descriptions and basis for scores that deviate from the recommended range; a score trace diagram is generated to show the score adjustment process and final results of each expert; in the rationality prompt, the analysis of key factors leading to high-deviation judgments is displayed, including historical score distribution, key technical point analysis and abnormal risk prompts.

[0089] S5.5: Record the scoring data entered by the review experts through the interactive scoring input interface as the actual scoring data of the experts, and record the scoring trajectory and modification history to form the review behavior data.

[0090] Specifically, it records and visualizes the expert scoring trajectory, including the initial score, revision process, and final score, while also providing annotations to allow for the addition of scoring rationale. It also analyzes the consistency of the expert review panel's scores. When significant disagreements arise or the consistency index exceeds a preset threshold, an analysis report is sent to the review team leader with coordination recommendations. Through intelligent scoring monitoring and real-time feedback mechanisms, this interactive scoring system ensures the independent judgment of review experts while providing data support. This ensures standardized guidance and anomaly prevention during the bid evaluation process, effectively improving the fairness and scientific nature of the review results.

[0091] S6: Encrypt and store the bidding process data through distributed storage technology.

[0092] In a specific embodiment of the present invention, step S6 includes: S6.1: Package the bid evaluation process data and generate a data integrity check value.

[0093] The bid evaluation process data includes evaluation decision recommendations, actual expert scoring data, and review behavior data. Furthermore, a data integrity check value is generated using the SHA-256 hash algorithm combined with digital signature technology. This involves calculating a SHA-256 hash value on the packaged data; digitally signing the hash value using the bid evaluation system's private key; and combining the original hash value with the digital signature to form a complete data check value, ensuring data integrity and immutability.

[0094] S6.2: Utilize a multi-node distributed storage architecture to encrypt and store the packaged bid evaluation process data in shards. Each node stores different data shards and saves the corresponding checksum values.

[0095] Specifically, a key sharing algorithm is used to split the data encryption key into multiple parts, of which any preset number of key shards can reconstruct the complete key; the packaged data is divided into four logical shards: qualification review data, technical review data, business review data, and comprehensive review data; each logical shard is encrypted to generate an encrypted data shard; the check value of each encrypted data shard is calculated to generate a data integrity check code; a chain storage structure is constructed, with each data shard as a block, containing its own data, timestamp, previous block check value, and current block check value; the encrypted data shards and corresponding check values ​​are deployed to different storage nodes respectively; role-based permission management and operation log recording are implemented on each storage node; data access timeliness control is set to allow authorized personnel to review the complete data within a preset time period after the bid evaluation is completed; a data recovery mechanism is constructed, and when historical bid evaluation data needs to be reviewed, the key is reconstructed and the data is decrypted after multi-node authorization verification; an audit tracking mechanism is implemented to record all data access and operation behaviors, and store them through independent nodes.

[0096] S6.3: A threshold signature mechanism is used to control the authorization of storage nodes. When the node signature authorization exceeds the minimum authorized node number threshold, access to the packaged evaluation process data is allowed.

[0097] The minimum authorized node count threshold is determined by two-thirds of the total number of nodes and is dynamically adjusted based on the confidentiality level of the bid evaluation project. For bid evaluation projects with a normal confidentiality level, it is set to N / 2+1 (N is the total number of nodes); for bid evaluation projects with a high confidentiality level, it is set to 2N / 3+1; and for bid evaluation projects with a special confidentiality level, it is set to 3N / 4+1, thus achieving differentiated authorization control at different security levels.

[0098] Furthermore, it should be noted that the distributed storage technology implemented in this invention utilizes a combination of asymmetric and homomorphic encryption to support statistical analysis and audit queries on encrypted bid evaluation data, enabling specific data analysis tasks to be performed without requiring full decryption. Furthermore, the system implements a blockchain-based data traceability mechanism that can trace every data change throughout the bid evaluation process, ensuring the security, integrity, and traceability of bid evaluation data during storage, effectively preventing the risk of data leakage and tampering caused by internal and external threats.

[0099] Furthermore, this embodiment also provides an intelligent processing system for bid evaluation data, including: a data preprocessing module, which is used to obtain multi-source heterogeneous data related to bid evaluation and perform structured conversion processing on the multi-source heterogeneous data; an association analysis module, which is used to construct data based on a model, extract bidding subject characteristics, bidding content characteristics and bidding behavior characteristics, and analyze the multi-layer association relationship between the characteristics to construct an association analysis model; an abnormal bid identification module, which is used to input the current data to be evaluated into the association analysis model, perform abnormal bid identification and output abnormal behavior warning information; an evaluation auxiliary analysis module, which is used to perform intelligent analysis and processing on the current data to be evaluated and extract evaluation auxiliary information; a bid evaluation decision support module, which is used to generate bid evaluation decision suggestions and build a visual interface to support expert review decisions based on abnormal behavior warning information and evaluation auxiliary information; a data encryption and evidence storage module, which is used to encrypt and store the bid evaluation process data through distributed storage technology.

[0100] In summary, the present invention realizes a comprehensive correlation analysis of bidding data through structured processing and feature extraction of multi-source heterogeneous data, effectively improving the scientificity and accuracy of bid evaluation decisions; by calculating the similarity of correlation feature vectors and clustering analysis of high-order correlation patterns, it realizes intelligent identification and risk warning of abnormal bidding behaviors such as bid rigging and collusion; a bid evaluation decision support system based on a decision matrix is ​​designed, which cross-analyzes abnormal behavior warning information and bid evaluation auxiliary information, and constructs a multi-level visual interface, which significantly improves the transparency and review efficiency of the bid evaluation process; a distributed storage architecture and a threshold signature mechanism are used to perform sharded encrypted storage of bid evaluation process data, combined with data integrity verification, to ensure the security and non-tamperability of bid evaluation data, and fundamentally solve the problem of insufficient data credibility in traditional bid evaluation systems.

[0101] Example 2 is the second embodiment of the present invention, which is different from the previous embodiment in that: If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0102] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0103] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting, or processing in another suitable manner as necessary, and then storing it in a computer memory.

[0104] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. The intelligent processing method for bid evaluation data is characterized by: include: Acquiring multi-source heterogeneous data related to bid evaluation and performing structured conversion processing on the multi-source heterogeneous data; the multi-source heterogeneous data includes model building data and current bid evaluation data; Building data based on the model, extracting bidding subject characteristics, bidding content characteristics, and bidding behavior characteristics, and analyzing the multi-layer correlation relationships between the characteristics to build a correlation analysis model; Inputting the current bid evaluation data into the association analysis model, performing abnormal bid identification and outputting abnormal behavior warning information; Performing intelligent analysis and processing on the current bid evaluation data to extract auxiliary bid evaluation information; Based on the abnormal behavior warning information and the bid evaluation auxiliary information, generate bid evaluation decision suggestions and build a visual interface; The bidding process data is encrypted and stored through distributed storage technology.

2. The method for intelligent processing of bid evaluation data according to claim 1, characterized in that: include: The model building data includes historical bidding data, extended verification data and process evidence data; the current data to be evaluated includes bidder qualification documents, structured technical bid documents and standardized business quotation documents.

3. The method for intelligent processing of bid evaluation data according to claim 1, characterized in that: The multi-layer association relationship between the analysis features and the construction of the association analysis model include: Calculating correlation indices among the bidding subject characteristics, bidding content characteristics, and bidding behavior characteristics, and determining connection relationships among the characteristics based on a preset correlation threshold to generate a feature correlation network; Classifying the nodes in the feature correlation network according to bidding subject characteristics, bidding content characteristics and bidding behavior characteristics to construct a multi-layer feature network structure; Performing topological analysis on the multi-layer characteristic network structure to determine key nodes and connection paths in the network; Using graph embedding technology, the nodes and their topological relationships in the multi-layer feature network structure are converted into low-dimensional vector representations, and high-order correlation patterns between features are extracted; An association analysis model is established based on the low-dimensional vector representation and the high-order association pattern.

4. The method for intelligent processing of bid evaluation data according to claim 1, characterized in that: The performing of abnormal bidding identification and outputting abnormal behavior warning information includes: Build a feature library of abnormal bidding behavior; Based on the association analysis model, the current bid evaluation data is converted into an association feature vector, and a high-order association pattern is extracted; Calculating the similarity between the associated feature vector and each abnormal type feature vector in the abnormal bidding behavior feature library, and screening abnormal bidding candidates according to a preset similarity threshold; performing cluster analysis on the abnormal bidding candidates using the high-order association pattern to generate a plurality of abnormal bidding clusters; extracting abnormal correlation patterns from the abnormal bidding clusters, and evaluating the abnormal risk level based on the abnormal correlation patterns; Generate abnormal behavior warning information based on the abnormal risk level.

5. The method for intelligent processing of bid evaluation data according to claim 1, characterized in that: The intelligent analysis and processing of the current bid evaluation data includes: Analyze bidder qualification documents, verify compliance and validity, and generate qualification assessment results; Analyze structured technical bids, evaluate the feasibility, innovation and responsiveness of technical content, and form a basis for technical scoring; Analyze standardized commercial quotation documents, determine the rationality and completeness of quotations, and generate quotation evaluation conclusions; Compare and analyze the differences, strengths and weaknesses of the technical contents of different bidders to form horizontal comparison data; Integrate the qualification assessment results, technical scoring basis, quotation evaluation conclusions and horizontal comparison data to generate structured bid evaluation auxiliary information.

6. The method for intelligent processing of bid evaluation data according to claim 1, characterized in that: Generating the bid evaluation decision suggestion and building the visual interface includes: Constructing a decision matrix, cross-analyzing the abnormal behavior warning information and the bid evaluation auxiliary information to form a decision support data structure; Generate a bid evaluation decision suggestion including a recommended scoring range, abnormal risk warning mark and evaluation key prompts based on the decision support data structure; Construct a multi-level visual interface for the bid evaluation decision suggestions according to the three dimensions of qualifications, technology, and business, and mark the risk points and decision basis in the visual interface; Build an interactive rating input interface and generate real-time rationality prompt information based on the degree of deviation between the expert input rating and the system recommended rating range; The scoring data input by the review experts through the interactive scoring input interface is recorded as the actual scoring data of the experts, and the scoring trajectory and modification history are recorded to form review behavior data.

7. The method for intelligent processing of bid evaluation data according to claim 1, characterized in that: The encrypted storage of bid evaluation process data by distributed storage technology includes: Packaging the bid evaluation process data and generating a data integrity check value; the bid evaluation process data includes bid evaluation decision recommendations, actual expert scoring data, and review behavior data; Using a multi-node distributed storage architecture, the packaged bid evaluation process data is encrypted and stored in shards. Each node stores different data shards and saves the corresponding checksum values. A threshold signature mechanism is used to authorize and control storage nodes.

8. The bid evaluation data intelligent processing system is characterized by: include: A data preprocessing module is used to obtain multi-source heterogeneous data related to bid evaluation and perform structured conversion processing on the multi-source heterogeneous data; The association analysis module is used to construct data based on the model, extract the characteristics of the bidding subject, bidding content and bidding behavior, analyze the multi-layer association relationship between the characteristics, and build an association analysis model; An abnormal bid identification module is used to input the current bid evaluation data into the association analysis model, perform abnormal bid identification and output abnormal behavior warning information; A bid evaluation auxiliary analysis module is used to perform intelligent analysis and processing on the current bid evaluation data and extract bid evaluation auxiliary information; A bid evaluation decision support module is used to generate bid evaluation decision suggestions and build a visual interface to support expert review decisions based on the abnormal behavior warning information and the bid evaluation auxiliary information; The data encryption and evidence storage module is used to encrypt and store the bid evaluation process data through distributed storage technology.

9. A computer device, characterized in that: include: A memory, a processor, and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the method according to any one of claims 1 to 7.

Images