Big data-based electronic bill blockchained data analysis system and method

Abstract

The application discloses a big data-based electronic bill blockchaining data analysis system and method, and relates to the technical field of big data analysis.The application converts unstructured business-related vouchers of a bill issuing party and account entry data of a bill user into standardized semantic labels by collecting the same, constructs a three-tuple semantic model to form a bill voucher semantic chain, adopts a double hashing algorithm to encrypt and generate a structure hash value and a semantic hash value, stores the evidence on a chain to construct a semantic verification benchmark, compares bidirectionally according to a compliance rule knowledge base, triggers a risk early warning and records a violation clue, pushes the early warning through multiple channels, restricts the circulation of a violation bill, and removes the restriction after correction and re-verification.The system comprises data acquisition and processing, semantic model construction, block chain evidence storage, compliance verification and early warning, and circulation control modules.The application realizes multi-source data semantic unification and full-dimension verification, forms a closed-loop management process, and improves the compliance and credibility of electronic bill blockchaining application.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, specifically to a blockchain-based data analytics system and method for electronic invoices based on big data. Background Technology

[0002] With the deep integration of the digital economy and fiscal digitalization, electronic invoices have become the core carrier of corporate financial accounting, and the demand for reliable and efficient management throughout their entire lifecycle is becoming increasingly urgent. Blockchain technology, with its characteristics of distributed ledger, cryptographic encryption, and immutability, is gradually becoming the core support for the reliable storage and circulation of electronic invoices.

[0003] When an electronic invoice corresponds to multiple unstructured business-related vouchers, existing technologies can only achieve on-chain storage, format parsing, and surface element verification of a single voucher. This results in a hidden vulnerability in the compliance verification of the invoice user's accounting, where the form is compliant but the substance is not, which in turn leads to the problem of distorted financial accounting. Summary of the Invention

[0004] The purpose of this invention is to provide a blockchain-based data analysis system and method for electronic invoices based on big data, in order to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a blockchain-based data analysis method for electronic invoices based on big data, the data analysis method comprising the following steps:

[0006] Step S1: Collect the unstructured business-related vouchers of the invoice issuer and the accounting data of the invoice user based on the core elements of the invoice, and convert them into standardized semantic tags;

[0007] Step S2: Extract the core elements of the bill and construct a triplet semantic model. Map the core elements of the bill, standardized semantic tags, and the bill user's accounting data to form a semantic chain of the bill voucher.

[0008] Step S3: Generate a structure hash value for the unstructured business-related voucher of the invoice issuer, generate a semantic hash value for the standardized semantic tags, and construct a semantic verification benchmark;

[0009] Step S4: Based on the preset compliance rule knowledge base, compare and analyze the semantic chain of the invoice and voucher with the semantic verification benchmark. If a logical contradiction is detected, trigger a semantic conflict risk warning and record relevant violation clues.

[0010] Step S5: Send an alert to the bill user to restrict the circulation of non-compliant bills. The restriction will be lifted after the corrected accounting operation is completed and the verification is passed again.

[0011] Furthermore, the specific steps of step S1 are as follows:

[0012] Step S1-1: Extract all voucher data that are directly related to the core elements of the invoice in the business process, forming unstructured business-related vouchers for the invoice issuer, and simultaneously collect the entire process data for the invoice user's accounting. The core elements of the invoice include invoice ID, voucher ID, invoice number, invoice date, amount, invoice issuer name, and invoice user name. The unstructured business-related vouchers include scanned copies of contracts, logistics documents, and fund flow vouchers. The entire process data for the invoice user's accounting includes accounting application data, accounting processing vouchers, and audit record data.

[0013] Step S1-2: The collected unstructured business-related vouchers of the invoicing party are processed in a unified manner according to a preset format. The unified processing is to transform unstructured vouchers with different storage formats and presentation forms into parsable data with a unified structure through accurate character extraction, semantic noise filtering, and data structure regularization. Accurate character extraction uses OCR recognition technology combined with keyword matching algorithm to extract the core business information in the voucher. Semantic noise filtering removes redundant text and invalid symbols that are not related to the invoice business. Data structure regularization restructures the extracted information in a structured manner according to the format of "voucher type-business field-field value".

[0014] Steps S1-3: Based on the preset unified semantic tag system, the core semantic information is accurately extracted and mapped for the pre-processed unstructured voucher data and the standardized invoice-using accounting data, generating standardized semantic tags with unified format and consistent semantic dimensions. The unified semantic tag system includes business type, amount dimension, circulation status, and responsible entity.

[0015] Furthermore, the specific steps of step S2 are as follows:

[0016] Step S2-1: Extract the core element information from the electronic invoice and construct a core element set of the invoice according to the structure of "invoice number - core element type - element value"; the core element types include basic information type, amount type, subject type, and business type;

[0017] Step S2-2: Construct a triplet semantic model, using the core elements of the invoice as the association core, and establish a triple mapping relationship of "core elements of the invoice - standardized semantic tags - invoice user's accounting data"; calculate the matching degree between the standardized semantic tags and the core elements of the invoice and the invoice user's accounting data through a semantic similarity algorithm, retain the mapping relationship with the matching degree higher than the preset threshold, and eliminate invalid associations; the semantic similarity algorithm adopts the cosine similarity calculation method.

[0018] Step S2-3: Based on the ternary mapping relationship, the core elements of the bill, standardized semantic tags, and the bill user's accounting data are linked together in the order of business logic to form a semantic chain of bill vouchers; the semantic chain is constructed according to the business process of "bill initiation - business execution - voucher generation - accounting processing".

[0019] Furthermore, the specific steps of step S3 are as follows:

[0020] Step S3-1: Use the SHA-256 hash algorithm to perform encryption calculation on the unified unstructured business-related voucher of the invoice issuer to generate a unique structure hash value; the structure hash value corresponds one-to-one with the unstructured business-related voucher of the invoice issuer. If any modification is made to the content of the unstructured business-related voucher of the invoice issuer, the structure hash value will be changed synchronously.

[0021] Step S3-2: Serialize the standardized semantic tag set generated in step S1, and encrypt the serialized tag data using the SM3 hash algorithm to generate a semantic hash value;

[0022] Step S3-3: The invoice ID, voucher ID, standardized semantic tag, structural hash value, and semantic hash value are encapsulated in a structured manner according to a preset format to form a blockchain evidence storage data unit; the evidence storage data unit is broadcast to the entire network through the P2P network of the blockchain node, and after being confirmed by the consensus mechanism, it is written into the distributed ledger to form a semantic verification benchmark.

[0023] Furthermore, the specific steps of step S4 are as follows:

[0024] Step S4-1: Construct a pre-defined compliance rule knowledge base, which includes three categories: business logic rules, financial accounting rules, and regulatory compliance rules. The business logic rules clarify the logical relationship requirements between invoices, unstructured business-related vouchers of the invoice issuer, and the accounting data of the invoice user. The financial accounting rules comply with accounting standards and corporate financial systems.

[0025] Step S4-2: Perform a bidirectional comparison and analysis between the semantic chain of the bill certificate formed in step S2 and the semantic verification benchmark generated in step S3; on the one hand, verify whether the hash value of each node data in the semantic chain is consistent with the double hash value of the blockchain notarization; on the other hand, verify the business logic coherence and data consistency of the semantic chain based on the compliance rule knowledge base; the data consistency includes the consistency of amount, subject, and time series.

[0026] Step S4-3: If a hash value mismatch or logical contradiction that violates compliance rules is detected during the comparison analysis, the system will automatically trigger a semantic conflict risk warning; at the same time, it will record the violation clues, including conflict rule entries, hash comparison results, and timestamp information, forming a complete violation tracing chain.

[0027] Furthermore, the specific steps of step S5 are as follows:

[0028] Step S5-1: The system sends early warning notifications to the financial manager and personnel in charge of the invoice-using party via SMS, platform messages, and email.

[0029] Step S5-2: The invoice user corrects the accounting operation based on the warning notification and violation clues, supplements or modifies the relevant voucher data, and submits a re-verification application; the system re-verifies the corrected data according to the verification logic of steps S1-S4. If the verification passes, the circulation restriction is automatically lifted, and the correction record and re-verification result are associated and stored on the blockchain; if the verification fails, the restriction measures will be retained until the violation is rectified.

[0030] Furthermore, the data analysis system includes a data acquisition and processing module, a semantic model construction module, a blockchain evidence storage module, a compliance verification and early warning module, and a flow control module;

[0031] The data acquisition and processing module is used to collect unstructured business-related vouchers from the invoice issuer and accounting data from the invoice user, and generate standardized semantic tags after unified processing. The semantic model construction module is used to construct a triplet semantic model, establish a mapping relationship between the core elements of the invoice, semantic tags, and accounting data, and form a semantic chain of invoice vouchers. The blockchain notarization module is used to generate double hash values ​​and associate key information on the blockchain to form a semantic verification benchmark. The compliance verification and early warning module is used to perform comparative analysis based on the compliance rule knowledge base, trigger risk warnings, and record violation clues. The circulation control module is used to push early warning notifications, restrict the circulation of illegal invoices, and handle re-verification and restriction lifting operations.

[0032] Furthermore, the data acquisition and processing module includes a voucher data acquisition unit and a semantic tag generation unit; the voucher data acquisition unit is used to collect unstructured business vouchers associated with the core elements of the invoice and the entire process data of the invoice user's accounting, and establish a data acquisition ledger; the semantic tag generation unit is used to perform unified processing on the collected data, extract core information based on a unified semantic tag system, and generate standardized semantic tags.

[0033] Furthermore, the semantic model construction module includes a core element extraction unit and a semantic chain construction unit; the core element extraction unit is used to extract core element information from electronic invoices and construct element sets and associated indexes; the semantic chain construction unit is used to construct a triplet semantic model, establish mapping relationships between multi-source data, and form a semantic chain of invoices and vouchers according to business logic.

[0034] The blockchain evidence storage module includes a hash generation unit and an on-chain evidence storage unit. The hash generation unit is used to generate structural hash values ​​and semantic hash values ​​for the original voucher and standardized semantic tags respectively using a dual hash algorithm. The on-chain evidence storage unit is used to encapsulate the evidence storage data unit and write it into the distributed ledger through the blockchain consensus mechanism to form a semantic verification benchmark.

[0035] Furthermore, the compliance verification and early warning module includes a rule knowledge base unit and a comparison and early warning unit; the rule knowledge base unit is used to store and manage three types of rules: business logic, financial accounting, and regulatory compliance, and supports dynamic rule updates; the comparison and early warning unit is used to perform bidirectional comparison between the semantic chain of invoices and vouchers and the semantic verification benchmark, detect logical contradictions and trigger early warnings, and record clues of violations.

[0036] The circulation control module includes an early warning push unit and a restriction management unit. The early warning push unit is used to push early warning notifications to the ticket user through multiple channels to ensure that the information reaches the user in a timely manner. The restriction management unit is used to restrict the circulation of illegal tickets, process re-verification applications, perform restriction lifting or retention operations based on the verification results, and record relevant process data.

[0037] Compared with the prior art, the beneficial effects of the present invention are:

[0038] 1. This invention collects unstructured vouchers associated with invoices and data from the entire accounting process, processes this data in a unified manner to generate standardized semantic tags, and constructs a triplet semantic model to form a semantic chain for invoices and vouchers. This achieves semantic unification and deep association of multi-source heterogeneous data, solving the problem of incomplete verification caused by data dispersion and insufficient association in existing technologies, and providing a complete data link for compliance analysis.

[0039] 2. This invention encrypts the original credentials and semantic tags using a dual hash algorithm, storing key information on the blockchain to form a semantic verification benchmark, and conducting bidirectional comparative analysis in conjunction with a compliance rule knowledge base. Leveraging the immutability of blockchain and the precision of compliance rules, it achieves full-dimensional verification from data integrity to business compliance, effectively mitigating the hidden risk of formal compliance but substantive non-compliance.

[0040] 3. This invention forms a complete management process of "early warning-rectification-verification-removal" through early warning push, restriction of illegal circulation, and closed-loop rectification and verification mechanism; ensuring that illegal invoices are processed in a timely manner, while retaining complete clues of violations and rectification records, thereby improving the compliance and credibility of the blockchain application of electronic invoices. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating the blockchain-based data analysis method for electronic invoices based on big data, as described in this invention.

[0042] Figure 2 This is a schematic diagram of the structure of the blockchain-based electronic invoice data analysis system based on big data according to the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Example 1: As Figure 1 As shown, this invention provides a technical solution: a blockchain-based data analysis method for electronic invoices based on big data. The data analysis method includes the following steps:

[0045] Step S1: Collect the unstructured business-related vouchers of the invoice issuer and the accounting data of the invoice user based on the core elements of the invoice, and convert them into standardized semantic tags;

[0046] The specific steps of step S1 are as follows:

[0047] Step S1-1: Extract all voucher data that are directly related to the core elements of the invoice in the business process, forming unstructured business-related vouchers for the invoice issuer, and simultaneously collect the entire process data for the invoice user's accounting. The core elements of the invoice include invoice ID, voucher ID, invoice number, invoice date, amount, invoice issuer name, and invoice user name. The unstructured business-related vouchers include scanned copies of contracts, logistics documents, and fund flow vouchers. The entire process data for the invoice user's accounting includes accounting application data, accounting processing vouchers, and audit record data.

[0048] Step S1-2: The collected unstructured business-related vouchers of the invoicing party are processed in a unified manner according to a preset format. The unified processing is to transform unstructured vouchers with different storage formats and presentation forms into parsable data with a unified structure through accurate character extraction, semantic noise filtering, and data structure regularization. Accurate character extraction uses OCR recognition technology combined with keyword matching algorithm to extract the core business information in the voucher. Semantic noise filtering removes redundant text and invalid symbols that are not related to the invoice business. Data structure regularization restructures the extracted information in a structured manner according to the format of "voucher type-business field-field value".

[0049] Steps S1-3: Based on the preset unified semantic tag system, the core semantic information of the pre-processed unstructured voucher data and the standardized invoice user's accounting data is accurately extracted and mapped to generate standardized semantic tags with unified format and consistent semantic dimensions. The unified semantic tag system includes business type, amount dimension, circulation status, and responsible entity.

[0050] Step S2: Extract the core elements of the bill and construct a triplet semantic model. Map the core elements of the bill, standardized semantic tags, and the bill user's accounting data to form a semantic chain of the bill voucher.

[0051] The specific steps of step S2 are as follows:

[0052] Step S2-1: Extract the core element information from the electronic invoice and construct a core element set of the invoice according to the structure of "invoice number - core element type - element value"; the core element types include basic information type, amount type, subject type, and business type;

[0053] Step S2-2: Construct a triplet semantic model, using the core elements of the invoice as the association core, and establish a triple mapping relationship of "core elements of the invoice - standardized semantic tags - invoice user's accounting data"; calculate the matching degree between the standardized semantic tags and the core elements of the invoice and the invoice user's accounting data through a semantic similarity algorithm, retain the mapping relationship with the matching degree higher than the preset threshold, and eliminate invalid associations; the semantic similarity algorithm adopts the cosine similarity calculation method.

[0054] Step S2-3: Based on the ternary mapping relationship, the core elements of the bill, standardized semantic tags, and the bill user's accounting data are linked together in the order of business logic to form a semantic chain of bill vouchers; the semantic chain is constructed according to the business process of "bill initiation - business execution - voucher generation - accounting processing";

[0055] Step S3: Generate a structure hash value for the unstructured business-related voucher of the invoice issuer, generate a semantic hash value for the standardized semantic tags, and construct a semantic verification benchmark;

[0056] The specific steps of step S3 are as follows:

[0057] Step S3-1: Use the SHA-256 hash algorithm to perform encryption calculation on the unified unstructured business-related voucher of the invoice issuer to generate a unique structure hash value; the structure hash value corresponds one-to-one with the unstructured business-related voucher of the invoice issuer. If any modification is made to the content of the unstructured business-related voucher of the invoice issuer, the structure hash value will be changed synchronously.

[0058] Step S3-2: Serialize the standardized semantic tag set generated in step S1, and encrypt the serialized tag data using the SM3 hash algorithm to generate a semantic hash value;

[0059] Step S3-3: The invoice ID, voucher ID, standardized semantic tag, structural hash value, and semantic hash value are encapsulated in a structured manner according to a preset format to form a blockchain evidence storage data unit; the evidence storage data unit is broadcast to the entire network through the P2P network of the blockchain node, and after being confirmed by the consensus mechanism, it is written into the distributed ledger to form a semantic verification benchmark.

[0060] Step S4: Based on the preset compliance rule knowledge base, compare and analyze the semantic chain of the invoice and voucher with the semantic verification benchmark. If a logical contradiction is detected, trigger a semantic conflict risk warning and record relevant violation clues.

[0061] The specific steps of step S4 are as follows:

[0062] Step S4-1: Construct a pre-defined compliance rule knowledge base, which includes three categories: business logic rules, financial accounting rules, and regulatory compliance rules. The business logic rules clarify the logical relationship requirements between invoices, unstructured business-related vouchers of the invoice issuer, and the accounting data of the invoice user. The financial accounting rules comply with accounting standards and corporate financial systems.

[0063] Step S4-2: Perform a bidirectional comparison and analysis between the semantic chain of the bill certificate formed in step S2 and the semantic verification benchmark generated in step S3; on the one hand, verify whether the hash value of each node data in the semantic chain is consistent with the double hash value of the blockchain notarization; on the other hand, verify the business logic coherence and data consistency of the semantic chain based on the compliance rule knowledge base; the data consistency includes the consistency of amount, subject, and time series.

[0064] Step S4-3: If a hash value mismatch or a logical contradiction that violates compliance rules is detected during the comparison analysis, the system will automatically trigger a semantic conflict risk warning; at the same time, it will record the violation clues, including the conflict rule entries, hash comparison results, and timestamp information, forming a complete violation tracing chain.

[0065] Step S5: Send an alert to the invoice user to restrict the circulation of non-compliant invoices. The restriction will be lifted after the corrected accounting operation is completed and the verification is passed again.

[0066] The specific steps of step S5 are as follows:

[0067] Step S5-1: The system sends early warning notifications to the financial manager and personnel in charge of the invoice-using party via SMS, platform messages, and email.

[0068] Step S5-2: The invoice user corrects the accounting operation based on the warning notification and violation clues, supplements or modifies the relevant voucher data, and submits a re-verification application; the system re-verifies the corrected data according to the verification logic of steps S1-S4. If the verification passes, the circulation restriction is automatically lifted, and the correction record and re-verification result are associated and stored on the blockchain; if the verification fails, the restriction measures will be retained until the violation is rectified.

[0069] For example: targeted extraction of unstructured business vouchers associated with the core elements of invoices, including scanned copies of purchase contracts provided by suppliers, equipment transportation documents issued by logistics companies, and bank transaction records; simultaneous collection of data from the entire accounting process of manufacturing enterprises, including accounting application forms, accounting processing vouchers, and financial audit records.

[0070] The core information such as "equipment model, amount, and delivery period" in the contract is extracted using OCR recognition technology, and redundant text and invalid symbols in the legal clauses of the contract are filtered out; all unstructured vouchers are organized according to "voucher type - business field - field value".

[0071] Based on a unified semantic tagging system, standardized semantic tags are generated, including business type, amount dimension, circulation status, and responsible entity.

[0072] A set is constructed based on "invoice number - core element type - element value". Taking the core elements of the invoice as the core of association, a mapping relationship of "core elements of invoice - standardized semantic tags - accounting data" is established. The matching degree is calculated by the cosine similarity algorithm to retain effective associations.

[0073] Based on the business logic of "invoice initiation - business execution - voucher generation - accounting processing", multi-source data are linked to form a semantic chain of invoices and vouchers.

[0074] The SHA-256 hash algorithm is used to encrypt standardized purchase contracts, logistics documents and other vouchers to generate unique structural hash values; after serializing the standardized semantic tag set, semantic hash values ​​are generated using the SM3 hash algorithm.

[0075] The invoice ID, voucher ID, standardized semantic tag, and dual hash value are encapsulated into a data unit for evidence storage. This unit is then broadcast to the entire network via a blockchain P2P network. After confirmation by the consensus mechanism, it is written into the distributed ledger to form a semantic verification benchmark.

[0076] On the one hand, it verifies whether the hash value of each node's data in the semantic chain is consistent with the double hash value of the blockchain evidence; on the other hand, it verifies the compliance rules knowledge base and finds that the amount filled in the enterprise's invoice application form does not match the invoice amount, which violates the financial accounting rules.

[0077] The system automatically triggers semantic conflict risk warnings, records clues of violations, and forms a complete traceability chain.

[0078] Warning notices are sent to the financial managers and staff of manufacturing enterprises through three methods: SMS, enterprise financial platform messages, and email, informing them of the discrepancy between the recorded amount and the invoice amount and the path to inquire about clues of violations.

[0079] After verification, the company's finance personnel discovered an error in the amount entered during the accounting process. They corrected the entered amount, provided supplementary documentation, and submitted a re-verification request. The system re-verified the entire process according to steps S1-S4, confirming that the hash values ​​were consistent and all compliance rules were met.

[0080] The system automatically removes restrictions on the circulation of invoices, allowing companies to use the electronic invoices for financial accounting; at the same time, it links and stores the correction records and re-verification results on the blockchain to ensure that the process is traceable.

[0081] Example 2, as Figure 2 As shown, the present invention provides a blockchain-based data analysis system for electronic invoices based on big data. The data analysis system includes a data acquisition and processing module, a semantic model construction module, a blockchain evidence storage module, a compliance verification and early warning module, and a circulation control module.

[0082] The data acquisition and processing module is used to collect unstructured business-related vouchers from the invoice issuer and accounting data from the invoice user, and generate standardized semantic tags after unified processing. The semantic model construction module is used to construct a triplet semantic model, establish a mapping relationship between the core elements of the invoice, semantic tags, and accounting data, and form a semantic chain of invoice vouchers. The blockchain notarization module is used to generate double hash values ​​and associate key information on the blockchain to form a semantic verification benchmark. The compliance verification and early warning module is used to perform comparative analysis based on the compliance rule knowledge base, trigger risk warnings, and record violation clues. The circulation control module is used to push early warning notifications, restrict the circulation of illegal invoices, and handle re-verification and restriction lifting operations.

[0083] The data acquisition and processing module includes a voucher data acquisition unit and a semantic tag generation unit. The voucher data acquisition unit is used to collect unstructured business vouchers associated with the core elements of the voucher and the entire process data of the voucher user's accounting, and to establish a data acquisition ledger. The semantic tag generation unit is used to perform unified processing on the collected data, extract core information based on a unified semantic tag system, and generate standardized semantic tags.

[0084] The semantic model construction module includes a core element extraction unit and a semantic chain construction unit. The core element extraction unit is used to extract core element information from electronic invoices and construct element sets and associated indexes. The semantic chain construction unit is used to construct a triplet semantic model, establish mapping relationships between multi-source data, and form a semantic chain for invoices and vouchers according to business logic.

[0085] The blockchain evidence storage module includes a hash generation unit and an on-chain evidence storage unit. The hash generation unit is used to generate structural hash values ​​and semantic hash values ​​for the original voucher and standardized semantic tags respectively using a dual hash algorithm. The on-chain evidence storage unit is used to encapsulate the evidence storage data unit and write it into the distributed ledger through the blockchain consensus mechanism to form a semantic verification benchmark.

[0086] The compliance verification and early warning module includes a rule knowledge base unit and a comparison and early warning unit. The rule knowledge base unit is used to store and manage three types of rules: business logic, financial accounting, and regulatory compliance, and supports dynamic rule updates. The comparison and early warning unit is used to perform bidirectional comparison between the semantic chain of invoices and vouchers and the semantic verification benchmark, detect logical contradictions and trigger early warnings, and record clues of violations.

[0087] The circulation control module includes an early warning push unit and a restriction management unit. The early warning push unit is used to push early warning notifications to the ticket user through multiple channels to ensure that the information reaches the user in a timely manner. The restriction management unit is used to restrict the circulation of illegal tickets, process re-verification applications, perform restriction lifting or retention operations based on the verification results, and record relevant process data.

[0088] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A blockchain-based data analysis method for electronic invoices based on big data, characterized by: The data analysis method includes the following steps: Step S1: Collect the unstructured business-related vouchers of the invoice issuer and the accounting data of the invoice user based on the core elements of the invoice, and convert them into standardized semantic tags; Step S2: Extract the core elements of the bill and construct a triplet semantic model. Map the core elements of the bill, standardized semantic tags, and the bill user's accounting data to form a semantic chain of the bill voucher. Step S3: Generate a structure hash value for the unstructured business-related voucher of the invoice issuer, generate a semantic hash value for the standardized semantic tags, and construct a semantic verification benchmark; The specific steps of step S3 are as follows: Step S3-1: Use the SHA-256 hash algorithm to perform encryption calculation on the unified unstructured business-related voucher of the invoice issuer to generate a unique structure hash value; the structure hash value corresponds one-to-one with the unstructured business-related voucher of the invoice issuer. If any modification is made to the content of the unstructured business-related voucher of the invoice issuer, the structure hash value will be changed synchronously. Step S3-2: Serialize the standardized semantic tag set generated in step S1, and encrypt the serialized tag data using the SM3 hash algorithm to generate a semantic hash value; Step S3-3: The invoice ID, voucher ID, standardized semantic tag, structural hash value, and semantic hash value are encapsulated in a structured manner according to a preset format to form a blockchain evidence storage data unit; the evidence storage data unit is broadcast to the entire network through the P2P network of the blockchain node, and after being confirmed by the consensus mechanism, it is written into the distributed ledger to form a semantic verification benchmark. Step S4: Based on the preset compliance rule knowledge base, compare and analyze the semantic chain of the invoice and voucher with the semantic verification benchmark. If a logical contradiction is detected, trigger a semantic conflict risk warning and record relevant violation clues. Step S5: Send an alert to the bill user to restrict the circulation of non-compliant bills. The restriction will be lifted after the corrected accounting operation is completed and the verification is passed again.

2. The blockchain-based data analysis method for electronic invoices based on big data as described in claim 1, characterized in that: The specific steps of step S1 are as follows: Step S1-1: Extract all voucher data that are directly related to the core elements of the invoice in the business process, forming unstructured business-related vouchers for the invoice issuer, and simultaneously collect the entire process data for the invoice user's accounting. The core elements of the invoice include invoice ID, voucher ID, invoice number, invoice date, amount, invoice issuer name, and invoice user name. The unstructured business-related vouchers include scanned copies of contracts, logistics documents, and fund flow vouchers. The entire process data for the invoice user's accounting includes accounting application data, accounting processing vouchers, and audit record data. Step S1-2: The collected unstructured business-related vouchers of the invoicing party are processed in a unified manner according to a preset format. The unified processing is to transform unstructured vouchers with different storage formats and presentation forms into parsable data with a unified structure through accurate character extraction, semantic noise filtering, and data structure regularization. Accurate character extraction uses OCR recognition technology combined with keyword matching algorithm to extract the core business information in the voucher. Semantic noise filtering removes redundant text and invalid symbols that are irrelevant to the invoice business; data structure regularization reorganizes the extracted information into a structured format of "voucher type-business field-field value"; Steps S1-3: Based on the preset unified semantic tag system, the core semantic information is accurately extracted and mapped for the pre-processed unstructured voucher data and the standardized invoice-using accounting data, generating standardized semantic tags with unified format and consistent semantic dimensions. The unified semantic tag system includes business type, amount dimension, circulation status, and responsible entity.

3. The blockchain-based data analysis method for electronic invoices based on big data as described in claim 2, characterized in that: The specific steps of step S2 are as follows: Step S2-1: Extract the core element information from the electronic invoice and construct a set of core elements of the invoice according to the structure of "invoice number - core element type - element value"; the core element types include basic information type, amount type, subject type, and business type. Step S2-2: Construct a triplet semantic model, using the core elements of the bill as the association core, and establish a triple mapping relationship of "core elements of the bill - standardized semantic tags - bill user's accounting data"; calculate the matching degree between the standardized semantic tags and the core elements of the bill and the bill user's accounting data through a semantic similarity algorithm, retain the mapping relationship with the matching degree higher than the preset threshold, and eliminate invalid associations; the semantic similarity algorithm adopts the cosine similarity calculation method. Step S2-3: Based on the ternary mapping relationship, the core elements of the bill, standardized semantic tags, and the bill user's accounting data are linked together in the order of business logic to form a semantic chain of bill vouchers; the semantic chain is constructed according to the business process of "bill initiation - business execution - voucher generation - accounting processing".

4. The blockchain-based data analysis method for electronic invoices based on big data as described in claim 3, characterized in that: The specific steps of step S4 are as follows: Step S4-1: Construct a pre-defined compliance rule knowledge base, which includes three categories: business logic rules, financial accounting rules, and regulatory compliance rules. The business logic rules clarify the logical relationship requirements between invoices, unstructured business-related vouchers of the invoice issuer, and the accounting data of the invoice user. The financial accounting rules comply with accounting standards and corporate financial systems. Step S4-2: Perform a bidirectional comparison and analysis between the semantic chain of the bill certificate formed in step S2 and the semantic verification benchmark generated in step S3; on the one hand, verify whether the hash value of each node data in the semantic chain is consistent with the double hash value of the blockchain notarization; on the other hand, verify the business logic coherence and data consistency of the semantic chain based on the compliance rule knowledge base; the data consistency includes the consistency of amount, subject, and time series. Step S4-3: If a hash value mismatch or logical contradiction that violates compliance rules is detected during the comparison analysis, the system will automatically trigger a semantic conflict risk warning; at the same time, it will record the violation clues, including conflict rule entries, hash comparison results, and timestamp information, forming a complete violation tracing chain.

5. The blockchain-based data analysis method for electronic invoices based on big data as described in claim 4, characterized in that: The specific steps of step S5 are as follows: Step S5-1: The system sends early warning notifications to the financial manager and personnel in charge of the invoice-using party via SMS, platform messages, and email. Step S5-2: The invoice user corrects the accounting operation based on the warning notification and violation clues, supplements or modifies the relevant voucher data, and submits a re-verification application; the system re-verifies the corrected data according to the verification logic of steps S1-S4. If the verification passes, the circulation restriction is automatically lifted, and the correction record and re-verification result are associated and stored on the blockchain; if the verification fails, the restriction measures will be retained until the violation is rectified.

6. A blockchain-based data analysis system for electronic invoices based on big data, applied to the blockchain-based data analysis method for electronic invoices based on big data as described in any one of claims 1-5, characterized in that: The data analysis system includes a data acquisition and processing module, a semantic model construction module, a blockchain evidence storage module, a compliance verification and early warning module, and a flow control module. The data acquisition and processing module is used to collect unstructured business-related vouchers from the invoice issuer and accounting data from the invoice user, and generate standardized semantic tags after unified processing. The semantic model construction module is used to construct a triplet semantic model, establish a mapping relationship between the core elements of the invoice, semantic tags, and accounting data, and form a semantic chain of invoice vouchers. The blockchain notarization module is used to generate double hash values ​​and associate key information on the blockchain to form a semantic verification benchmark. The compliance verification and early warning module is used to perform comparative analysis based on the compliance rule knowledge base, trigger risk warnings, and record violation clues. The circulation control module is used to push early warning notifications, restrict the circulation of illegal invoices, and handle re-verification and restriction lifting operations.

7. The blockchain-based electronic invoice data analysis system according to claim 6, characterized in that: The data acquisition and processing module includes a voucher data acquisition unit and a semantic tag generation unit. The voucher data acquisition unit is used to collect unstructured business vouchers associated with the core elements of the voucher and the entire process data of the voucher user's accounting, and to establish a data acquisition ledger. The semantic tag generation unit is used to perform unified processing on the collected data, extract core information based on a unified semantic tag system, and generate standardized semantic tags.

8. The blockchain-based electronic invoice data analysis system according to claim 6, characterized in that: The semantic model construction module includes a core element extraction unit and a semantic chain construction unit. The core element extraction unit is used to extract core element information from electronic invoices and construct element sets and associated indexes. The semantic chain construction unit is used to construct a triplet semantic model, establish mapping relationships between multi-source data, and form a semantic chain for invoices and vouchers according to business logic. The blockchain evidence storage module includes a hash generation unit and an on-chain evidence storage unit. The hash generation unit is used to generate structural hash values ​​and semantic hash values ​​for the original voucher and standardized semantic tags respectively using a dual hash algorithm. The on-chain evidence storage unit is used to encapsulate the evidence storage data unit and write it into the distributed ledger through the blockchain consensus mechanism to form a semantic verification benchmark.

9. The blockchain-based electronic invoice data analysis system according to claim 6, characterized in that: The compliance verification and early warning module includes a rule knowledge base unit and a comparison and early warning unit. The rule knowledge base unit is used to store and manage three types of rules: business logic, financial accounting, and regulatory compliance, and supports dynamic rule updates. The comparison and early warning unit is used to perform bidirectional comparison between the semantic chain of invoices and vouchers and the semantic verification benchmark, detect logical contradictions and trigger early warnings, and record clues of violations. The circulation control module includes an early warning push unit and a restriction management unit. The early warning push unit is used to push early warning notifications to the ticket user through multiple channels to ensure that the information reaches the user in a timely manner. The restriction management unit is used to restrict the circulation of illegal tickets, process re-verification applications, perform restriction lifting or retention operations based on the verification results, and record relevant process data.

Images