Government affair data processing method, system and equipment and storage medium

Abstract

The invention discloses a government affair data processing method, system and device and a storage medium, and relates to the field of intelligent government affair decision, and the method comprises the steps: generating a tamper-proof block chain evidence storage triple through a multi-chain collaborative evidence storage mechanism based on a structured policy vector and government affair data; performing real-time decision matching by adopting a cosine similarity algorithm according to the block chain evidence storage triad, calculating a similarity value of the government affair item state vector and the structured policy vector, and generating a decision execution record when the similarity value reaches a policy compliance reference requirement; based on the decision execution record, starting a multi-chain collaborative auditing mechanism, identifying and positioning illegal operation nodes and generating an auditing report; according to the audit report, the audit data and the policy efficacy weight are optimized through a policy analysis engine, and a government affair data optimization proposal is generated; the policy knowledge graph is constructed by fusing the aging characteristics and the regional parameters through a dynamic quantization algorithm, and the structured policy vector is generated, so that the efficacy evaluation deviation of a static model is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent government decision-making, and particularly to a government data processing method, system, device, and storage medium. Background Art

[0002] In recent years, the field of government data processing has gradually integrated knowledge graphs and blockchain technologies to improve decision-making accuracy. At the policy quantification level, traditional methods mainly rely on static rule engines and natural language processing technologies to extract keywords from policy texts. At the same time, the application of blockchain technology in government systems focuses on data storage and evidence in a single-chain architecture. Typically, an administrative approval storage and evidence system implemented by Ethereum smart contracts ensures the traceability of processes through hash chain-up. In addition, vectorized decision-making models have been initially implemented in government scenarios, using algorithms such as Word2Vec to map policy texts to a low-dimensional vector space and combining with SVM classifiers to achieve basic policy matching.

[0003] There are still bottlenecks in dynamic policy adaptability and cross-chain collaboration efficiency. First, static quantification models lead to inaccurate policy effectiveness evaluation: traditional methods ignore the dynamic decay characteristics of policy effectiveness, such as timeliness factors and regional adaptation coefficients, and only calculate policy impact values based on fixed weights. Second, a single-chain architecture is difficult to support the audit requirements of multiple government roles: the government scenario needs to simultaneously meet the triple requirements of data storage and evidence, fingerprint anchoring, and compliance auditing, while existing single-chain solutions have conflicts between performance and security due to rigid consensus mechanisms. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a government data processing method to solve the problem of inaccurate policy effectiveness evaluation by constructing a dynamic decay compensation mechanism.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a government data processing method, which includes collecting government data, calculating policy effectiveness weights using a dynamic quantification algorithm, constructing a policy knowledge graph based on the policy effectiveness weights, and obtaining a structured policy vector through a graph node embedding algorithm;

[0008] Based on the structured policy vector and government data, generating an anti-tampering blockchain storage and evidence triple through a multi-chain collaborative storage and evidence mechanism;

[0009] According to the blockchain storage and evidence triple, performing real-time decision matching using the cosine similarity algorithm, calculating the similarity value between the government affair status vector and the structured policy vector, and generating a decision execution record when the similarity value meets the policy compliance benchmark requirements;

[0010] Based on the decision execution records, a multi-chain collaborative audit mechanism is launched to identify and locate illegal operation nodes and generate audit reports;

[0011] Based on the audit report, the audit data and policy effectiveness weights are optimized through the policy analysis engine, and government data optimization recommendations are generated.

[0012] As a preferred solution of the government data processing method described in the present invention, the government data includes administrative supervision data, public service data, social and economic data, spatial geographic data and policy and regulatory data.

[0013] As a preferred solution of the government data processing method described in the present invention, the steps of calculating the policy effectiveness weight using a dynamic quantization algorithm, constructing a policy knowledge graph based on the policy effectiveness weight, and obtaining a structured policy vector through a graph node embedding algorithm are as follows:

[0014] Based on government data, a dynamic quantitative algorithm is used to calculate the policy effectiveness weight, and graph verification and visualization rendering are performed on the policy data set to generate a knowledge graph storage file;

[0015] The knowledge graph storage file is parsed through the graph node embedding algorithm, and a random walk strategy with weight constraints is used to generate node sequences. The node feature representation is learned based on the contextual relationship in the node sequence, and finally a structured policy vector is generated by aggregation.

[0016] As a preferred solution of the government data processing method described in the present invention, the steps of generating a tamper-proof blockchain evidence triplet based on the structured policy vector and government data through a multi-chain collaborative evidence mechanism are as follows:

[0017] Receive structured policy vectors and government data inputs, build a block data structure through the authority proof consensus mechanism, and splice the blockchain height index and timestamp information in the block data structure to generate the operation chain address identifier and operation chain history record;

[0018] Based on the operation chain address identifier, the structured policy vector and related government data are obtained, and the secure hash algorithm is calculated through the Byzantine fault-tolerant consensus to generate a digest hash value;

[0019] The summary hash value is concatenated with the consensus node digital signature and the current block height encoding through structured metadata assembly, and the Merkle tree root hash aggregation algorithm is used to generate a summary chain block identifier containing the summary chain data fingerprint;

[0020] Based on the government data associated with the summary chain blockchain identifier, a verifiable policy compliance proof is generated through a zero-knowledge concise non-interactive knowledge argumentation algorithm, and an audit chain evidence block containing the audit chain compliance proof is constructed;

[0021] The operation chain address identifier, summary chain block identifier and audit chain evidence block are merged through the cross-chain evidence anchoring method to generate a blockchain evidence triplet.

[0022] As a preferred solution of the government data processing method described in the present invention, wherein: based on the blockchain evidence triples, the cosine similarity algorithm is used to perform real-time decision matching, calculate the similarity value between the government matter state vector and the structured policy vector, and generate a decision execution record when the similarity value meets the policy compliance benchmark requirement. The steps are as follows:

[0023] Based on blockchain evidence triples, the structured policy vector is extracted through the operation chain address identifier and the digest hash integrity is verified, dynamically generating integrity-verified policy vectors and related government data;

[0024] The integrity-verified policy vectors and related government data are spatially aligned using a multi-dimensional feature alignment method, and the cosine similarity algorithm is used to calculate the dot product value and the modulus ratio in steps to generate a similarity quantification indicator.

[0025] Compare similar quantitative indicators to policy compliance benchmark requirements. When it is determined that similar quantitative indicators meet the continuous compliance criteria, dynamically generate approval execution instructions and decision execution records.

[0026] As a preferred solution of the government data processing method described in the present invention, wherein: based on the decision execution record, the multi-chain collaborative audit mechanism is started to identify and locate the illegal operation nodes and generate an audit report. The steps are as follows:

[0027] Through the operation chain address identifier in the decision execution record, the structured policy vector and government data are extracted and verified to generate a policy data set and a decision verification status mark;

[0028] Based on policy data sets and decision verification status marks, the actual execution status of government affairs is compared with the policy compliance benchmark, deviation items are identified, and the operation nodes are located through traceability of the responsibility nodes to generate a set of violation marks;

[0029] Based on the set of violation marks, the operation chain history, summary chain data fingerprint and audit chain compliance proof are integrated to generate an audit report.

[0030] As a preferred solution of the government data processing method of the present invention, wherein: according to the audit report, the audit data and policy effectiveness weights are optimized through the policy analysis engine, and a government data optimization proposal is generated, the steps are as follows:

[0031] Based on the audit report, the policy analysis engine identifies high-frequency violation features and weight conflict points, and generates a structured audit feature vector;

[0032] Locate the weight items to be adjusted based on the structured audit feature vectors, calculate the weight compensation amount according to the type of violation, and generate a policy effectiveness weight optimization table and a compensation description document;

[0033] Integrate the policy effectiveness weight optimization table and the compensation description document to generate a government affairs data optimization proposal.

[0034] In a second aspect, the present invention provides a government affairs data processing system, including,

[0035] A policy vector calculation module, configured to collect government affairs data, calculate the policy effectiveness weight using a dynamic quantization algorithm, construct a policy knowledge graph based on the policy effectiveness weight, and obtain a structured policy vector through a graph node embedding algorithm;

[0036] A blockchain evidence storage construction module, configured to generate tamper-proof blockchain evidence storage triples through a multi-chain collaborative evidence storage mechanism based on the structured policy vector and government affairs data;

[0037] A similarity calculation and comparison module, configured to perform real-time decision matching using a cosine similarity algorithm according to the blockchain evidence storage triples, calculate the similarity value between the government affairs item status vector and the structured policy vector, and generate a decision execution record when the similarity value reaches the policy compliance benchmark requirement;

[0038] A violation operation identification module, configured to start a multi-chain collaborative audit mechanism based on the decision execution record, identify and locate the violation operation nodes, and generate an audit report;

[0039] An optimization proposal generation module, configured to optimize the audit data and the policy effectiveness weight through a policy analysis engine according to the audit report, and generate a government affairs data optimization proposal.

[0040] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the government affairs data processing method described in the first aspect of the present invention is implemented.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the government affairs data processing method described in the first aspect of the present invention is implemented.

[0042] The beneficial effects of the present invention are as follows: By using a dynamic quantization algorithm to fuse the timeliness feature and the geographical parameters to construct a policy knowledge graph and generate a structured policy vector, the effectiveness evaluation deviation of the static model is effectively solved, and the policy adaptation accuracy is improved. Description of the Drawings

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0044] Figure 1 It is a flowchart of a government affairs data processing method.

[0045] Figure 2 It is a schematic diagram of a government affairs data processing system.

[0046] Figure 3 It is a flowchart of a multi-chain collaborative evidence storage machine.

[0047] Figure 4 It is a flowchart of real-time decision matching and auditing. Specific Embodiments

[0048] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0049] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0050] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that mutually excludes other embodiments.

[0051] Refer to Figures 1 to 4 , which is an embodiment of the present invention. This embodiment provides a government affairs data processing method, including the following steps:

[0052] S1: Collect government affairs data, calculate the policy effectiveness weight using a dynamic quantization algorithm, construct a policy knowledge graph based on the policy effectiveness weight, and obtain a structured policy vector through a graph node embedding algorithm;

[0053] S1.1: The government affairs data includes administrative supervision data, public service data, social and economic data, spatial geographical data, and policy and regulation data;

[0054] It should be noted that the collection and integration of government affairs data are specifically manifested as follows: administrative supervision data records the registration and change of market entities, the issuance of administrative penalty decisions, and the archiving of daily supervision and inspection records to form structured forms, such as those containing the enterprise credit rating status; public service data precipitates the approval forms generated by the handling of people's livelihood matters, such as the detailed service records related to education and medical care; social and economic data aggregates the economic operation monitoring reports released by the statistical department, such as those covering regional GDP indicators; spatial and geographical data comes from the administrative division vector maps provided by surveying and mapping institutions; policy and regulation data is based on the text of the articles issued by the legislative body, such as the full text of departmental regulations for legal effect verification.

[0055] S1.2: Based on government affairs data, use a dynamic quantization algorithm to calculate the policy effectiveness weight, and perform graph spectrum verification and visualization rendering on the policy data set to generate a knowledge graph storage file;

[0056] Furthermore, the government affairs data is input into the dynamic quantization algorithm to calculate the policy effectiveness weight. The dynamic quantization algorithm is based on the time effect fluctuation factor and the department collaboration coefficient; the policy effectiveness weight is assigned to the nodes of the policy data set, and the graph spectrum verification includes entity conflict detection and relationship logic verification; the policy data set that has completed the verification is subjected to visualization rendering through the force-directed layout algorithm. The visualization rendering outputs graph structure data with topological coordinates, and the graph structure data is encapsulated into a knowledge graph storage file.

[0057] The formula for the policy effectiveness weight is:

[0058]

[0059] Among them, represents the policy effectiveness weight, and the domain of definition is (0, 1); represents the policy basic weight, and the domain of definition is (0.3, 0.9); represents the time decay coefficient, and the domain of definition is (0, 0.5); represents the policy release duration; represents the collaborative gain upper limit; represents the actual number of collaborating departments; represents the required number of collaborating departments.

[0060] S1.3: Parse the knowledge graph storage file through the graph node embedding algorithm, adopt a random walk strategy with weight constraints to generate a node sequence, learn the node feature representation based on the context relationship in the node sequence, and finally aggregate to generate a structured policy vector.

[0061] Furthermore, the graph node embedding algorithm loads the knowledge graph storage file to parse the graph structure topology. The nodes in the knowledge graph storage file carry the policy effectiveness weight attribute. The random walk strategy with weight constraints uses the policy effectiveness weight as the transition probability, generates a node sequence to record the entity relationships in the walk path, constructs the probability distributions of the central node and neighboring nodes based on the context relationships in the node sequence to learn the node feature representation, and aggregates the node feature representations generated by multiple rounds of walks to perform a vector dimension reduction operation, generating a structured policy vector to encapsulate the dimension information.

[0062] It should be noted that the construction process is to extract a subsequence group through a sliding window with a fixed width based on the node sequence generated by the random walk strategy with weight constraints. The node at the central position of the subsequence group is called the current central node, and the set of nodes arranged continuously before and after the central node is called the neighboring nodes. The goal is defined as: by adjusting the node feature representation, maximizing the inner product value between the central node feature representation and the neighboring nodes, and minimizing the inner product value between the central node feature representation and the non-neighboring nodes. The negative sampling method is used to optimize the feature representation. Each time, a non-neighboring node is randomly selected as a negative sample node for the valid node pairs of the central node and the neighboring nodes, and the node feature representation vector coordinates are updated through gradient calculation. Finally, a low-dimensional dense feature representation matrix of all nodes is output, and each node feature representation is encapsulated as a real number vector with a fixed dimension.

[0063] S2: Based on the structured policy vector and government affairs data, generate tamper-proof blockchain evidence storage triples through a multi-chain collaborative evidence storage mechanism;

[0064] S2.1: Receive the input of the structured policy vector and government affairs data, construct the block data structure through the authoritative proof consensus mechanism, and splice the blockchain height index and timestamp information in the block data structure to generate an operation chain address identifier and an operation chain historical record;

[0065] Furthermore, after receiving the input of the structured policy vector and government affairs data, the following process is executed through the authoritative proof consensus mechanism. The block data structure contains the blockchain height index and timestamp information; the blockchain height index and timestamp information are spliced to generate a hash string of the operation chain address identifier; the operation chain address identifier is associated with the block data structure to form an operation chain historical record.

[0066] Among them, the authoritative proof consensus mechanism is a blockchain governance mode in which the government agency CA certificate node constructs the block data structure according to legal authority after completing identity verification, triggers the pre-authorized node to perform block verification and signature operations based on legal rules through rotation in a fixed time period to form an operation chain historical record, and finally generates a blockchain evidence storage block with legal effect.

[0067] S2.2: Obtain the structured policy vector and associated government affairs data based on the operation chain address identifier, and generate a digest hash value through the Byzantine fault-tolerant consensus calculation of the secure hash algorithm;

[0068] Furthermore, locate the block data structure in the operation chain history according to the operation chain address identifier, and extract the encapsulated structured policy vector and associated government affairs data; submit the extracted content to the Byzantine fault-tolerant consensus node network, and the node network completes the consistency verification through redundant data comparison; after the verification passes, the Byzantine fault-tolerant consensus node network collaboratively executes the secure hash algorithm to calculate the structured policy vector and the associated government affairs data byte stream, and generates a digest hash value with a fixed number of digits.

[0069] S2.3: Concatenate the digest hash value with the consensus node digital signature and the current block height encoding through structured metadata assembly, and use the Merkle root hash aggregation algorithm to generate a digest chain block identifier containing the digest chain data fingerprint;

[0070] Furthermore, perform the following process through structured metadata assembly. Use the byte stream of the digest hash value as the base block, and continuously append the consensus node digital signatures of the Byzantine fault-tolerant consensus node network at the backend of the base block; continue to append the current block height encoding at the backend of the consensus node digital signature to form a single continuous byte stream. The concatenation process uses a tight connection method without delimiters, and each data block is aligned according to a predefined length: the length of the digest hash value is fixed, the length of the consensus node digital signature follows the asymmetric encryption algorithm specification, and the current block height encoding is converted into a fixed-length string. Input the fixed-length string into the Merkle root hash aggregation algorithm process, generate the leaf node hash value through the first hash, aggregate the parent node hash value through the second hash, and iterate to the root node to output a 256-bit digest value containing the digest chain data fingerprint; encapsulate the digest value to generate a digest chain block identifier and attach a uniqueness proof of the data fingerprint. S2.4: Based on the government affairs data associated with the digest chain blockchain identifier, generate a verifiable policy compliance proof through the zero-knowledge succinct non-interactive knowledge argument algorithm, and construct an audit chain deposit block containing the audit chain compliance proof;

[0071] Index and associate the government affairs data based on the digest chain identifier; the zero-knowledge succinct non-interactive knowledge argument algorithm compiles the policy compliance logic circuit into a verifiable constraint architecture; input the associated government affairs data into the constraint architecture to perform encryption operations to generate a verifiable policy compliance proof; combine the verifiable policy compliance proof, the digest chain identifier, and the timestamp to construct the data structure of the audit chain deposit block; finally, form an audit chain deposit block containing the audit chain compliance proof and record it in the chain structure.

[0072] The audit chain evidence storage block containing the audit chain compliance certificate is a chained storage unit encapsulated by a cryptographic structure with three core data elements: a verifiable policy compliance certificate generated by the zero-knowledge succinct non-interactive knowledge argument algorithm, a digest chain identifier for associated government affairs data, and an operation timestamp. The block header records the audit chain compliance certificate type identifier field, and the block body uses a Merkle tree structure to anchor the verifiable policy compliance certificate and the digest chain identifier, ultimately forming an immutable evidence storage entity.

[0073] S2.5: Merge the operation chain address identifier, the digest chain block identifier, and the audit chain evidence storage block through a cross-chain evidence storage anchoring method to generate a blockchain evidence storage triple.

[0074] Furthermore, the cross-chain evidence storage anchoring method synchronously obtains the three data entities of the operation chain address identifier, the digest chain block identifier, and the audit chain evidence storage block; the operation chain address identifier extracts timestamp information, the digest chain block identifier parses the Merkle proof path data, and the audit chain evidence storage block extracts the compliance proof feature code; the three perform a space-time alignment operation through a distributed ledger repeater: generate a chronological index chain based on the timestamp information sorting, and perform a cross-hash binding on the Merkle proof path and the compliance proof feature code; the anchor data and the original identifier text are merged and encoded to generate a blockchain evidence storage triple.

[0075] It should be noted that the blockchain evidence storage triple is an indivisible data unit formed by merging the operation chain address identifier, the digest chain data fingerprint encapsulated by the digest chain block identifier, and the audit chain proof extracted from the audit chain evidence storage block through the cross-chain evidence storage anchoring method. This data unit structurally encapsulates the timestamp positioning function of the operation chain address identifier, the Merkle tree verification function of the digest chain block identifier, and the compliance audit function of the audit chain evidence storage block. After the three are bound, the operation chain, the digest chain, and the audit chain are uniquely associated through the blockchain evidence storage triple.

[0076] S3: According to the blockchain evidence storage triple, use the cosine similarity algorithm to perform real-time decision matching, calculate the similarity value between the government affairs matter status vector and the structured policy vector, and generate a decision execution record when the similarity value meets the policy compliance benchmark requirement;

[0077] S3.1: Based on the blockchain evidence storage triple, extract the structured policy vector through the operation chain address identifier and verify the digest hash integrity, and dynamically generate a policy vector and associated government affairs data that have passed the integrity verification;

[0078] Specifically, perform an operation chain address identifier location query operation based on the blockchain evidence triple. The operation chain address identifier indexes the distributed ledger to obtain the structured policy vector and associated government affairs data; parse the summary chain block identifier in the blockchain evidence triple to obtain the pre-stored summary hash value; immediately calculate the secure hash algorithm 3 output result of the sequential concatenation value of the associated government affairs data byte stream and the structured policy vector, and verify through the summary hash value comparison mechanism that the secure hash algorithm 3 output result of the sequential concatenation value is equal to the pre-stored summary hash value; dynamically generate the structured policy vector and associated government affairs data instance that have passed integrity verification, including the environmental assessment data record that has passed verification and the dataset bound to the land use approval policy vector.

[0079] S3.2: Perform spatial alignment on the policy vector and associated government affairs data that have passed integrity verification through the multi-dimensional feature alignment method, and generate a similarity quantization index by stepwise calculating the dot product value and the modulus ratio through the cosine similarity algorithm;

[0080] Specifically, place the structured policy vector and associated government affairs data that have passed integrity verification in a unified mathematical space through the multi-dimensional feature alignment method to perform coordinate transformation: perform a base vector direction calibration operation on the feature coordinate axes of the structured policy vector and the feature coordinate axes of the associated government affairs data, and at the same time scale the feature scales of different data sources; perform the stepwise calculation process of the cosine similarity algorithm: first calculate the sum of the products of the feature coordinates of the structured policy vector and the feature coordinates of the associated government affairs data element by element to obtain the dot product value; calculate the Euclidean norm of the feature coordinates of the structured policy vector and the Euclidean norm of the feature coordinates of the associated government affairs data respectively to obtain the vector modulus; divide the dot product value by the product of the modulus of the structured policy vector and the modulus of the associated government affairs data to obtain the modulus ratio; finally, multiply the dot product value by the modulus ratio to generate a similarity quantization index in the range of [0,1], and output a matching degree value to reflect the consistency degree between the spatial geographical policy terms and the actual data of the enterprise land use.

[0081] The formula for the similarity quantization index is:

[0082]

[0083] Among them, represents the similarity quantization index; represents the -dimensional feature coordinate of the structured policy vector; represents the -dimensional feature coordinate of the associated government affairs data; represents the number of feature space dimensions.

[0084] S3.3: Compare the similarity quantization index with the policy compliance benchmark requirements. When it is determined that the similarity quantization index meets the continuous compliance criteria, dynamically generate an approval execution instruction and a decision execution record.

[0085] Further, perform a multi-dimensional numerical comparison operation on the similarity quantization index and the set of compliance thresholds defined by the policy compliance benchmark requirements; monitor the change trajectory of the similarity quantization index within consecutive calculation periods through a sliding time window mechanism to determine whether the continuous compliance conditions set by the continuous compliance criterion are met; when the similarity quantization index trajectory is verified to meet the continuous compliance criterion, dynamically generate an approval execution instruction carrying a digital signature and a valid timestamp, where the approval execution instruction includes the responsible entity specified by the approval execution instruction and the boundary of the scope of action defined by the approval execution instruction; synchronously create a non-repudiable decision execution record, and the record content includes the operation time point, the trigger condition hash value, and the associated policy version identifier, and establish a causal association chain with the calculation result of the similarity quantization index in a cryptographically anchored manner.

[0086] The continuous compliance criterion is defined as that the similarity quantization index must reach the minimum threshold set by the policy compliance benchmark requirements in all consecutive monitoring periods, and at the same time, the fluctuation range of the similarity quantization index in adjacent periods meets the absolute tolerance upper limit of the policy compliance benchmark requirements, and the length of the time window and the tolerance parameter are set differently according to the policy type.

[0087] It should be noted that the policy compliance benchmark requirements set three elements: the minimum compliance threshold, the dynamic offset threshold, and the continuous monitoring period value. The minimum compliance threshold defines the single-period compliance boundary of the similarity quantization index; the dynamic offset threshold restricts the fluctuation range of the similarity quantization index in adjacent periods; the continuous monitoring period value enforces the requirement of continuously meeting the compliance conditions within the time window; the three work together to determine whether the continuous compliance criterion is met.

[0088] S4: Based on the decision execution record, start a multi-chain collaborative auditing mechanism to identify and locate the illegal operation nodes and generate an audit report;

[0089] S4.1: Through the operation chain address identifier in the decision execution record, extract and verify the structured policy vector and government affairs data, and generate a policy data set and a decision verification status flag;

[0090] Further, retrieve the structured policy vector byte stream and associated government affairs data content from the distributed ledger node through the operation chain address identifier stored in the decision execution record, and extract the pre-stored summary hash value based on the summary chain block identifier referenced by the decision execution record; immediately perform the secure hash algorithm calculation on the sequential concatenation value of the structured policy vector byte stream and the associated government affairs data content to generate a real-time calculation hash value, and perform a comparison operation between the pre-stored summary hash value and the real-time calculation hash value to verify the data integrity; after the verification passes, parse the structured policy vector byte stream to generate a policy data set; combine the verification conclusion of the continuous compliance criterion, append a decision verification status flag to the policy data set, and finally output an entity pair composed of the complete policy data set and the decision verification status flag.

[0091] S4.2: Based on the policy dataset and the decision verification status markers, compare the actual execution status of government affairs items with the policy compliance benchmarks, identify deviation items, trace the operation nodes through the responsible nodes, and generate a set of violation markers;

[0092] Furthermore, based on the policy dataset and the decision verification status markers, perform the following process: Compare the actual execution status of government affairs items with the policy compliance benchmarks item by item to identify deviation items; Trace the responsible nodes for the records bound to the policy dataset associated with the deviation items; Locate the operation nodes through the responsible nodes, and generate a set of violation markers consisting of deviation item identifiers, responsible node addresses, and operation node identifiers.

[0093] S4.3: Based on the set of violation markers, integrate the historical records of the operation chain, the data fingerprints of the summary chain, and the compliance certificates of the audit chain to generate an audit report.

[0094] Furthermore, based on the set of violation markers, perform cross-chain data association: Match the relevant entries in the historical records of the operation chain through the operation node identifiers in the set of violation markers; Index the data fingerprints of the summary chain through the responsible node addresses; Extract the proof segments mapped to the deviation item identifiers in the compliance certificates of the audit chain; Package the three types of verification vouchers with the set of violation markers. It should be noted that the audit report is a legal audit document generated by encapsulating four types of data, namely, the key-value pair entries in the set of violation markers, the operation node traces extracted from the historical records of the operation chain, the Merkle tree path proof of the data fingerprints of the summary chain, and the electronic signatures of the compliance certificates of the audit chain, through the cross-chain anchoring mechanism. Its core structure includes the evidence chapter of the violation matters and the cross-chain deposit appendix, and finally outputs a closed-loop file for deposit tracing.

[0095] S5: According to the audit report, optimize the audit data and the policy effectiveness weights through the policy analysis engine, and generate a government affairs data optimization proposal.

[0096] S5.1: Based on the audit report, identify the high-frequency violation features and weight conflict points through the policy analysis engine, and generate a structured audit feature vector;

[0097] Specifically, based on the violation item list and the evidence chapter recorded in the audit report, perform a high-frequency violation feature extraction algorithm to scan the violation item fields in all the key-value pairs of the set of violation markers; Count the occurrence frequencies of the same violation items, calculate the feature weights of each violation item; Synchronously detect the contradiction points between the required clause items of the policy compliance benchmarks and the audit evidence entries to identify the weight conflict points; Aggregate the high-frequency violation feature word frequency indicators and the contradiction degree scores of the weight conflict points to generate a structured audit feature vector that matches the requirements of the policy compliance benchmarks in terms of dimensions, which respectively represent the "planning permission deviation frequency factor", the "inter-departmental collaboration contradiction degree factor", and the "time-limit violation accumulation factor".

[0098] S5.2: Locate the weight items to be adjusted based on the structured audit feature vector, calculate the weight compensation amount according to the type of violation, and generate a policy effectiveness weight optimization table and a compensation description document;

[0099] Specifically, locate the policy effectiveness weight items whose values in each dimension of the structured audit feature vector exceed the allowable floating range; calculate the weight compensation amount formula according to the type of violation divided by the audit report; generate a policy effectiveness weight optimization table to record the adjusted weight values and the index of the revision basis; synchronously create a compensation description document to explain the weight adjustment logic and the mapping relationship of the compensation amount item by item.

[0100] It should be noted that the weight items to be adjusted refer to the policy effectiveness weight composition units in the structured audit feature vector that deviate from the allowable floating range of the policy compliance benchmark requirements, including high-frequency out-of-tolerance items and conflicting imbalance items. The two are located by the dimension value of the frequency factor of the structured audit feature vector > the threshold or the dimension value of the conflict coefficient > the policy compatibility threshold, and finally a policy effectiveness weight optimization table is generated.

[0101] S5.3: Integrate the policy effectiveness weight optimization table and the compensation description document to generate a government affairs data optimization proposal.

[0102] Specifically, extract the weight items to be adjusted and the adjusted weight values based on the policy effectiveness weight optimization table, analyze the weight compensation amount calculation logic through the compensation description document, and deduce the executable optimization steps; map the adjusted weight values to the corresponding government affairs data structure and define the expected adjustment target; synthesize the optimization steps and the expected adjustment target to form a structured government affairs data optimization proposal.

[0103] This embodiment also provides a government affairs data processing system, including:

[0104] A policy vector calculation module, configured to collect government affairs data, calculate the policy effectiveness weight using a dynamic quantization algorithm, construct a policy knowledge graph based on the policy effectiveness weight, and obtain a structured policy vector through a graph node embedding algorithm;

[0105] A blockchain evidence storage construction module, configured to generate tamper-proof blockchain evidence storage triples through a multi-chain collaborative evidence storage mechanism based on the structured policy vector and government affairs data;

[0106] A similarity calculation and comparison module, configured to perform real-time decision matching using a cosine similarity algorithm according to the blockchain evidence storage triples, calculate the similarity value between the government affairs item status vector and the structured policy vector, and generate a decision execution record when the similarity value meets the policy compliance benchmark requirements;

[0107] A violation operation identification module, configured to start a multi-chain collaborative audit mechanism based on the decision execution record, identify and locate the violation operation nodes and generate an audit report;

[0108] An optimization proposal generation module is used to optimize audit data and policy effectiveness weights through a policy analysis engine according to an audit report, and generate an optimization proposal for government affairs data.

[0109] This embodiment also provides a computer device, which is applicable to the case of the government affairs data processing method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the government affairs data processing method proposed in the above embodiment.

[0110] This computer device may be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0111] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the government affairs data processing method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read Only Memory (EPROM for short), Programmable Red-Only Memory (PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0112] In summary, the present invention: constructs a policy knowledge graph by using a dynamic quantization algorithm to fuse timeliness features and regional parameters and generates a structured policy vector, effectively solving the effectiveness evaluation deviation of the static model and improving the accuracy of policy adaptation.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for processing government affairs data, characterized in that: include, Collect government data, use dynamic quantification algorithms to calculate policy effectiveness weights, build a policy knowledge graph based on policy effectiveness weights, and obtain structured policy vectors through graph node embedding algorithms; Based on structured policy vectors and government data, a tamper-proof blockchain evidence triple is generated through a multi-chain collaborative evidence storage mechanism; Based on the blockchain evidence triples, the cosine similarity algorithm is used for real-time decision matching. The similarity value between the government affairs state vector and the structured policy vector is calculated. When the similarity value meets the policy compliance benchmark requirements, a decision execution record is generated. Based on the decision execution records, a multi-chain collaborative audit mechanism is launched to identify and locate illegal operation nodes and generate audit reports; Based on the audit report, the audit data and policy effectiveness weights are optimized through the policy analysis engine, and government data optimization recommendations are generated.

2. The government affairs data processing method according to claim 1, characterized in that: The government data includes administrative supervision data, public service data, socio-economic data, spatial geographic data and policy and regulatory data.

3. The government affairs data processing method according to claim 2, wherein: The dynamic quantification algorithm is used to calculate the policy effectiveness weight, a policy knowledge graph is constructed based on the policy effectiveness weight, and a structured policy vector is obtained through a graph node embedding algorithm. The steps are as follows: Based on government data, a dynamic quantitative algorithm is used to calculate the policy effectiveness weight, and graph verification and visualization rendering are performed on the policy data set to generate a knowledge graph storage file; The knowledge graph storage file is parsed through the graph node embedding algorithm, and a random walk strategy with weight constraints is used to generate node sequences. The node feature representation is learned based on the contextual relationship in the node sequence, and finally a structured policy vector is generated by aggregation.

4. The government affairs data processing method according to claim 3, characterized in that: The steps of generating a tamper-proof blockchain evidence triplet based on structured policy vectors and government data through a multi-chain collaborative evidence mechanism are as follows: Receive structured policy vectors and government data inputs, build a block data structure through the authority proof consensus mechanism, and splice the blockchain height index and timestamp information in the block data structure to generate the operation chain address identifier and operation chain history record; Based on the operation chain address identifier, the structured policy vector and related government data are obtained, and the secure hash algorithm is calculated through the Byzantine fault-tolerant consensus to generate a digest hash value; The summary hash value is concatenated with the consensus node digital signature and the current block height encoding through structured metadata assembly, and the Merkle tree root hash aggregation algorithm is used to generate a summary chain block identifier containing the summary chain data fingerprint; Based on the government data associated with the digest chain blockchain identifier, a verifiable policy compliance proof is generated through a zero-knowledge concise non-interactive knowledge argumentation algorithm, and an audit chain evidence block containing the audit chain compliance proof is constructed; The operation chain address identifier, summary chain block identifier and audit chain evidence block are merged through the cross-chain evidence anchoring method to generate a blockchain evidence triplet.

5. The government affairs data processing method according to claim 4, wherein: According to the blockchain evidence triples, the cosine similarity algorithm is used for real-time decision matching, and the similarity value between the government affairs state vector and the structured policy vector is calculated. When the similarity value reaches the policy compliance benchmark requirement, a decision execution record is generated. The steps are as follows: Based on the blockchain evidence triple, extract the structured policy vector through the operation chain address identifier and verify the integrity of the digest hash, and dynamically generate the integrity-verified policy vector and associated government affairs data; Perform spatial alignment on the integrity-verified policy vector and associated government affairs data through the multi-dimensional feature alignment method, and generate the similarity quantization index by calculating the dot product value and the modulus length ratio step by step through the cosine similarity algorithm; Compare the similarity quantization index with the policy compliance benchmark requirements. When it is determined that the similarity quantization index meets the continuous compliance criteria, dynamically generate the approval execution instruction and the decision execution record.

6. The government affairs data processing method according to claim 5, wherein: Based on the decision execution record, start the multi-chain collaborative audit mechanism, identify and locate the illegal operation nodes and generate an audit report. The steps are as follows: Extract and verify the structured policy vector and government affairs data through the operation chain address identifier in the decision execution record, and generate the policy data set and the decision verification status mark; Based on the policy data set and the decision verification status mark, compare the actual execution status of the government affairs item with the policy compliance benchmark, identify the deviation items, trace the operation nodes through the responsible nodes, and generate the illegal mark set; Based on the illegal mark set, integrate the operation chain historical record, the digest chain data fingerprint and the audit chain compliance certificate to generate an audit report.

7. The government affairs data processing method according to claim 6, wherein: According to the audit report, optimize the audit data and the policy effectiveness weight through the policy analysis engine and generate a government affairs data optimization proposal. The steps are as follows: Based on the audit report, identify the high-frequency illegal features and weight conflict points through the policy analysis engine to generate the structured audit feature vector; Based on the structured audit feature vector, locate the weight items to be adjusted, calculate the weight compensation amount according to the illegal type, and generate the policy effectiveness weight optimization table and the compensation description document; Integrate the policy effectiveness weight optimization table and the compensation description document to generate a government affairs data optimization proposal.

8. A government affairs data processing system, based on the government affairs data processing method according to any one of claims 1 to 7, characterized in that: Including: The policy vector calculation module is used to collect government affairs data, calculate the policy effectiveness weight by using the dynamic quantization algorithm, construct a policy knowledge graph based on the policy effectiveness weight, and obtain the structured policy vector through the graph node embedding algorithm; The blockchain evidence construction module is used to generate the tamper-proof blockchain evidence triple through the multi-chain collaborative evidence mechanism based on the structured policy vector and government affairs data; The similarity calculation and comparison module is used to perform real-time decision matching by using the cosine similarity algorithm according to the blockchain evidence triple, calculate the similarity value between the government affairs item state vector and the structured policy vector, and generate a decision execution record when the similarity value meets the policy compliance benchmark requirements; The illegal operation identification module is used to start the multi-chain collaborative audit mechanism based on the decision execution record, identify and locate the illegal operation nodes and generate an audit report; The optimization proposal generation module is used to optimize the audit data and the policy effectiveness weight through the policy analysis engine according to the audit report and generate a government affairs data optimization proposal.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the government affairs data processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the government affairs data processing method according to any one of claims 1 to 7.

Images