CN119228393B - Information protection method for supply chain purchasing relationship chain data - Google Patents
Information protection method for supply chain purchasing relationship chain dataInfo
- Publication number
- CN119228393B CN119228393B CN202411152381.5A CN202411152381A CN119228393B CN 119228393 B CN119228393 B CN 119228393B CN 202411152381 A CN202411152381 A CN 202411152381A CN 119228393 B CN119228393 B CN 119228393B
- Authority
- CN
- China
- Prior art keywords
- enterprise name
- enterprise
- preset
- alternative
- signature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明涉及信息保护技术领域，尤其涉及一种供应链采购关系链数据的信息保护方法，包括创建备选企业名称集合；根据MinHash算法生成备选企业名称签名集合，待评估企业名称签名，创建第一混淆签名集合；根据MinHash算法生成购方企业名称签名，创建第二混淆签名集合；对第二混淆签名集合中的备选企业名称签名进行组合生成购方企业组合，并根据第一混淆签名集合中的备选企业名称签名与购方企业组合生成交易关系组合；将所述交易关系组合发送给第三方数据源，得到每一种交易关系组合的信用评分，选取待评估企业与购方企业的交易关系组合的评分，本发明克服了现有技术中对于需要保护的企业交易关系信息的保护效果差的问题。
The present invention relates to the field of information protection technology, and in particular to an information protection method for supply chain procurement relationship chain data, comprising creating a set of candidate enterprise names; generating a set of candidate enterprise name signatures and a signature of an enterprise name to be evaluated according to a MinHash algorithm, and creating a first obfuscated signature set; generating a signature of a purchasing enterprise name according to a MinHash algorithm, and creating a second obfuscated signature set; combining the candidate enterprise name signatures in the second obfuscated signature set to generate a purchasing enterprise combination, and generating a transaction relationship combination based on the candidate enterprise name signatures in the first obfuscated signature set and the purchasing enterprise combination; sending the transaction relationship combination to a third-party data source, obtaining a credit score for each transaction relationship combination, and selecting a score for the transaction relationship combination of the enterprise to be evaluated and the purchasing enterprise. The present invention overcomes the problem of poor protection effect on enterprise transaction relationship information that needs to be protected in the prior art.
Description
Technical Field
The invention relates to the technical field of information protection, in particular to an information protection method for supply chain purchasing relationship chain data.
Background
With the development of supply chain finance and credit financing, financial institutions increasingly rely on data-driven approaches to credit assessment of enterprise customers. In this process, the procurement relationship tether data of the enterprise becomes a key factor in assessing the credit worthiness of the enterprise. For example, if a good or core business is included in a business's trading subscribers, this will help to promote the credit score of the business and potentially provide more favorable financing conditions for it.
While businesses may be willing to authorize financial institutions to use their procurement relationship-based data, they often do not want this information to be revealed to other third parties, as this may affect the business confidentiality and market competitiveness of the business. While protecting corporate purchasing relationship chain information, financial institutions also need to actively utilize third party data to enhance risk assessment capabilities for corporate and its purchasers, which is critical to improving information protection capabilities for supply chain purchasing relationship chain data.
Chinese patent publication No. CN115943411a discloses a noise transaction for protecting data comprising a processor configured to generate a blockchain request comprising data for a blockchain, create a tag value identifying whether the blockchain request comprises a noise request of dummy data or a noise-free request of non-noise data, store the tag value within the blockchain request, and a network interface configured to send the blockchain request to one or more blockchain peers.
It can be seen that the prior art has the following problems that the alternative enterprise name set is small in size and lacks a reasonable set expansion mode, and meanwhile, the confusion effect on the transaction relation combination information to be protected is poor, so that the protection effect on the transaction relation information of the enterprise to be protected is poor.
Disclosure of Invention
Therefore, the invention provides an information protection method for supply chain purchasing relationship chain data, which is used for solving the problem of poor protection effect on enterprise transaction relationship information to be protected in the prior art.
In order to achieve the above object, the present invention provides an information protection method for supply chain purchasing relationship chain data, including:
creating an alternative enterprise name set comprising the names of the enterprises to be evaluated, the names of n buyer enterprises having trade relations with the enterprises to be evaluated and the names of other enterprises in the same industry as the enterprises to be evaluated;
Processing the alternative enterprise name set according to M i nHash algorithm to generate an alternative enterprise name signature set;
Processing names of enterprises to be evaluated according to M i nHash algorithm, generating enterprise name signatures to be evaluated, determining qualified M alternative enterprise name signatures according to first semantic similarity between alternative enterprise name signatures in the alternative enterprise name signature set and the enterprise name signatures to be evaluated, and creating a first confusion signature set comprising the M alternative enterprise name signatures;
Processing names of N buyer enterprises having transaction relation with an enterprise to be evaluated according to M i nHash algorithm, generating N buyer enterprise name signatures, determining qualified N candidate enterprise name signatures according to second semantic similarity between the candidate enterprise name signatures in the candidate enterprise name signature set and single buyer enterprise name signatures, and creating a second confusion signature set comprising N multiplied by N candidate enterprise name signatures;
combining alternative business name signatures in a second set of mixed signatures The purchasing enterprises are combined and signed according to the alternative enterprise names in the first mixed signature setCombined generation of purchasing party enterprisesA transaction relation combination;
The said The transaction relation combinations are sent to a third party data source, credit scores of each transaction relation combination are obtained, and scores of the transaction relation combinations of the enterprise to be evaluated and the buyer enterprise are selected;
When the creation of the alternative enterprise name set is completed, determining expansion of the alternative enterprise name set according to the number of enterprise names in the alternative enterprise name set;
when the alternative enterprise name set, the names of the enterprises to be evaluated and the names of the purchase enterprises having transaction relation with the enterprises to be evaluated are processed according to M i nHash algorithm, determining the hash function number in M i nHash algorithm according to the number of the enterprise names in the alternative enterprise name set;
When (when) After the transaction relation combination is generated, the quantity is combined according to the transaction relationAnd determining adjustment of the preset semantic similarity.
Further, the alternative enterprise name set is determined to be expanded according to a comparison result that the number of enterprise names in the alternative enterprise name set is smaller than or equal to the first preset number of enterprise names.
Further, according to the comparison result that the first relative difference is smaller than or equal to the first preset relative difference, the alternative enterprise name set is determined to be expanded in a first expansion mode, according to the comparison result that the first relative difference is larger than the first preset relative difference, the alternative enterprise name set is determined to be expanded in a second expansion mode, the first expansion mode is that names of all enterprises covered by taking an enterprise to be evaluated as a circle center and taking a preset distance as a radius are added to the alternative enterprise name set, and the second expansion mode is that the alternative enterprise name set is expanded according to an operation range text of the enterprise to be evaluated;
Wherein the first relative difference is determined by the number of business names and a first preset number of business names.
Further, the preset distance is calculated and set according to the following formula
Wherein J represents a preset distance and Δl represents the first relative difference.
Further, cosine similarity between the enterprise name to be expanded in the enterprise name set to be expanded and the business scope text of the enterprise to be evaluated is calculated according to the following formula, and setting is performed
Wherein Y represents the cosine similarity, A represents the feature vector of the name of the enterprise to be expanded, and B represents the feature vector of the business scope text of the enterprise to be evaluated;
and determining that the enterprise name to be expanded is added to an alternative enterprise name set according to the comparison result that the cosine similarity is larger than a preset cosine similarity.
Further, the hash function number in the MinHash algorithm is determined to be the first hash function number according to a comparison result that the number of enterprise names in the alternative enterprise name set is smaller than or equal to the second preset enterprise name number, and the hash function number in the MinHash algorithm is determined to be the second hash function number according to a comparison result that the number of enterprise names in the alternative enterprise name set is larger than the second preset enterprise name number.
Further, calculating first semantic similarity between an alternative enterprise name signature in the alternative enterprise name signature set and the enterprise name signature to be evaluated according to the following formula, and setting x1=d1/D2, wherein X1 represents the first semantic similarity, D1 represents the number of hash values which are the same at the same position in the alternative enterprise name signature and the enterprise name signature to be evaluated, and D2 represents the total number of hash values of the alternative enterprise name signature and the enterprise name signature to be evaluated;
And determining that the alternative enterprise name signature is unqualified according to a comparison result that the first semantic similarity is smaller than or equal to a first preset semantic similarity, and determining that the alternative enterprise name signature is qualified according to a comparison result that the first semantic similarity is larger than the first preset semantic similarity.
Further, calculating second semantic similarity between the alternative enterprise name signature and the single buyer enterprise name signature in the alternative enterprise name signature set according to the following formula, and setting x2=e1/E2, wherein X2 represents the second semantic similarity, E1 represents the number of hash values which are the same at the same position in the alternative enterprise name signature and the single buyer enterprise name signature, and E2 represents the total number of hash values of the alternative enterprise name signature and the single buyer enterprise name signature;
and determining that the alternative enterprise name signature is unqualified according to a comparison result that the second semantic similarity is smaller than or equal to a second preset semantic similarity, and determining that the alternative enterprise name signature is qualified according to a comparison result that the second semantic similarity is larger than the second preset semantic similarity.
Further, the amounts are combined according to the trade relationshipAnd determining the preset semantic similarity by the comparison result smaller than or equal to the number of the preset transaction relation combinations.
Further, when the preset semantic similarity is determined to be adjusted, the preset semantic similarity is determined to be adjusted in a first adjustment mode according to a comparison result that the second relative difference is smaller than or equal to the second preset relative difference, the preset semantic similarity is determined to be adjusted in a second adjustment mode according to a comparison result that the second relative difference is larger than the second preset relative difference, and the first adjustment mode is that according to the first adjustment coefficientThe first preset semantic similarity is adjusted, and the second adjustment mode is that according to a second adjustment coefficientAdjusting a second preset semantic similarity, wherein ΔP represents a second relative difference, the second relative difference being determined by the number of trade relationship combinationsAnd combining the quantity with a preset transaction relation to determine.
Compared with the prior art, the method has the beneficial effects that the number of enterprises similar to the enterprise name to be evaluated is increased by expanding the candidate enterprise name set, more noise data are provided when MinHash operation and mixed signature set creation are carried out, so that the mixed degree of the enterprise to be evaluated and the enterprise of the purchasing party is improved, the business secrets of the enterprise to be evaluated and the enterprise of the purchasing party are better protected, the strength of data protection is improved, the size of the candidate enterprise name set is flexibly adjusted according to the actual situation and the protection requirement by setting the first preset enterprise name number, the effect of information protection is avoided from being influenced by the fact that the number of enterprise names is too small, and the excessive calculation time and the waste of calculation resources are avoided.
Further, the most suitable expansion strategy is accurately selected by setting different expansion modes, the anonymization degree and the protection effect of the enterprise to be evaluated and the enterprise of the purchasing party are effectively improved, the expansion modes are flexibly determined according to the actual situation and the protection requirement by setting the first relative difference, the effect of information protection is prevented from being influenced by too few enterprise names, and the excessive calculation time and the waste of calculation resources caused by too many enterprise names are avoided.
Further, the preset distance is accurately calculated according to the first relative difference, so that the determination of the preset distance is more efficient and accurate, the expansion effect is ensured, and meanwhile, the excessive expansion of the candidate enterprise name set is avoided.
Further, the invention measures the similarity between the feature vector of the enterprise name to be expanded and the feature vector of the business scope text of the enterprise to be evaluated through the cosine similarity, ensures that the enterprise added into the set has a certain correlation with the enterprise to be evaluated in terms of business so as to more accurately inquire the enterprise close to the enterprise to be evaluated, adds the enterprise name to be expanded into the alternative enterprise name set only when the cosine similarity exceeds the preset cosine similarity, thereby protecting information, blurring potential supply chain relation, simultaneously preventing the enterprise name completely irrelevant to the enterprise to be evaluated from being added into the alternative enterprise name set, avoiding introducing excessive noise data, and being beneficial to maintaining the quality and practicality of the alternative enterprise name set.
Further, the accuracy of the MinHash signature is affected by the number of hash functions, so that the generated signature can accurately reflect similarity among names by selecting the proper number of hash functions while the calculation efficiency is kept, when the alternative enterprise name set is smaller, good signature effects are provided by using fewer hash functions, so that calculation resources are saved, and when the alternative enterprise name set is larger, finer signatures are provided by using more hash functions to cope with the complexity of the alternative enterprise name set.
Further, the method and the device for the enterprise privacy protection by the business name signature are used for selecting the alternative business name signature which is highly similar to the enterprise to be assessed by setting the first preset semantic similarity, so that the enterprise added in the first confusion signature set can effectively confuse the real identity of the enterprise to be assessed, the quality of information protection is improved, and the third party data source is more difficult to distinguish which are real transaction relations when receiving the information, so that the privacy of the enterprise is better protected.
Further, the method and the system ensure that only the alternative enterprise name signatures above a certain similarity level are considered to be qualified and added into the second mixed signature set by setting the second preset semantic similarity X02, thereby being beneficial to protecting the privacy of a purchasing enterprise in a transaction relationship with an enterprise to be evaluated and reducing the potential risk of information leakage.
Further, the invention controls the scale of the generated transaction relation combinations by comparing the transaction relation combination quantity with the preset transaction relation combination quantity, wherein too many generated combinations can reduce the efficiency of data processing and analysis, too little combination quantity is insufficient to provide enough anonymization protection, and the preset semantic similarity is adjusted to help to achieve the proper scale of the mixed signature set.
Further, the invention calculates and compares the second relative difference with the second preset relative difference to finely manage the adjustment of the preset semantic similarity, ensures that the generated transaction relation combination is not too much or too little, and keeps the rationality of the confusion signature set, thereby accurately adjusting the transaction relation combination quantity.
Further, the invention accurately calculates the adjustment coefficient according to the second relative difference to finely adjust the preset semantic similarity, ensures that the generated transaction relation combination is not too much or too little, and maintains the rationality of the confusion signature set, thereby accurately adjusting the transaction relation combination quantity, ensuring the information protection effect and avoiding the waste of calculation resources.
Drawings
FIG. 1 is a flow chart of a method for protecting information of supply chain purchasing relationship chain data according to an embodiment of the present invention;
FIG. 2 is a logic block diagram of an alternative enterprise name set expansion process in an information protection method for supply chain purchasing relationship chain data according to an embodiment of the present invention;
FIG. 3 is a logic block diagram of a preset semantic similarity adjustment process in an information protection method for supply chain purchasing relationship chain data according to an embodiment of the present invention;
Detailed Description
The invention will be further described with reference to examples for the purpose of making the objects and advantages of the invention more apparent, it being understood that the specific examples described herein are given by way of illustration only and are not intended to be limiting.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
Referring to fig. 1-3, fig. 1 is a flowchart of a method for protecting information of supply chain purchasing relationship chain data according to an embodiment of the present invention, fig. 2 is a logic block diagram of an alternative enterprise name set expansion process in the method for protecting information of supply chain purchasing relationship chain data according to an embodiment of the present invention, and fig. 3 is a logic block diagram of a preset semantic similarity adjustment process in the method for protecting information of supply chain purchasing relationship chain data according to an embodiment of the present invention.
The information protection method for the supply chain purchasing relationship chain data comprises the following steps:
Step S1, creating an alternative enterprise name set comprising names of enterprises to be evaluated, names of n purchase enterprises having transaction relation with the enterprises to be evaluated and names of other enterprises in the same industry as the enterprises to be evaluated;
step S2, processing the alternative enterprise name set according to a MinHash algorithm to generate an alternative enterprise name signature set;
Step S3, the names of enterprises to be evaluated are processed according to M i nHash algorithm, enterprise name signatures to be evaluated are generated, M qualified alternative enterprise name signatures are determined according to first semantic similarity X1 between the alternative enterprise name signatures in the alternative enterprise name signature set and the enterprise name signatures to be evaluated, and a first mixed signature set comprising the M alternative enterprise name signatures is created;
Step S4, names of N purchase enterprises having transaction relation with enterprises to be evaluated are processed according to M i nHash algorithm, N purchase enterprise name signatures are generated, qualified N alternative enterprise name signatures are determined according to second semantic similarity X2 between the alternative enterprise name signatures in the alternative enterprise name signature set and single purchase enterprise name signatures, and a second confusion signature set comprising N multiplied by N alternative enterprise name signatures is created;
Step S5, combining the alternative enterprise name signatures in the second mixed signature set to generate The purchasing enterprises are combined and signed according to the alternative enterprise names in the first mixed signature setCombined generation of purchasing party enterprisesA transaction relation combination;
Step S6, the steps are carried out And sending the transaction relation combinations to a third party data source, obtaining credit scores of each transaction relation combination, and selecting scores of the transaction relation combinations of the enterprise to be evaluated and the buyer enterprise.
In the embodiment of the invention, the credit score is provided by a third party data source, the third party data source collects relevant data about each enterprise in the transaction relation combination, the relevant data comprise public financial reports, credit records, industry ranks and historical transaction data, features are extracted from the collected data, the third party data source processes the extracted features by using a credit score model, the credit score model is preferably a neural network, the extracted features are input into the credit score model, and the model outputs credit scores to reflect credit risks of the enterprises in the transaction relation combination.
Specifically, when the creation of the alternative enterprise name set is completed, determining whether to expand the alternative enterprise name set according to a comparison result of the enterprise name number L in the alternative enterprise name set and the first preset enterprise name number L1;
when L is less than or equal to L1, determining to expand the alternative enterprise name set;
When L > L1, determining that the alternative enterprise name set is not expanded;
In the embodiment of the present invention, the value of the first preset number of business names L1 is 1000, and a person skilled in the art can adjust the first preset number of business names L1 according to specific situations.
Specifically, the method and the system increase the number of enterprises similar to the enterprise name to be evaluated by expanding the alternative enterprise name set, provide more noise data when MinHash operation and confusion signature set creation are carried out, thereby improving the confusion degree of the enterprise to be evaluated and the enterprise of the purchasing party, better protecting business secrets of the enterprise to be evaluated and improving the strength of data protection, flexibly adjust the size of the alternative enterprise name set according to the actual situation and protection requirements by setting the first preset enterprise name number, avoid the effect of information protection from being influenced by too few enterprise names, and avoid the excessive calculation time waste of computational resources caused by too many enterprise names.
Specifically, when the alternative enterprise name set is determined to be expanded, calculating a first relative difference delta L between the enterprise name number L and a first preset enterprise name number L1, and determining an expansion mode for expanding the alternative enterprise name set according to a comparison result of the first relative difference delta L and the first preset relative difference delta L1, wherein delta l= (L1-L)/L1;
when DeltaL is less than or equal to DeltaL 1, determining to expand the alternative enterprise name set in a first expansion mode;
when the delta L > -delta L1, determining to expand the alternative enterprise name set in a second expansion mode;
The first expansion mode is to add names of all enterprises covered by taking the enterprise to be evaluated as a circle center and taking a preset distance J as a radius to an alternative enterprise name set, and the second expansion mode is to expand the alternative enterprise name set according to the business scope text of the enterprise to be evaluated.
In the embodiment of the present invention, the value of the first preset relative difference Δl1 is 0.4, and the first preset relative difference Δl1 is obtained when the number of business names L is 600, and a person skilled in the art can adjust the first preset relative difference Δl1 according to specific situations.
Specifically, the method and the system accurately select the most suitable expansion strategy by setting different expansion modes, effectively improve the anonymization degree and the protection effect of the enterprise to be evaluated and the enterprise of the purchasing party, flexibly determine the expansion mode according to the actual situation and the protection requirement by setting the first relative difference, avoid the influence of the too small number of enterprise names on the effect of information protection, and avoid the excessive number of enterprise names to cause the excessive operation time and waste of calculation resources.
Specifically, when it is determined to expand the set of alternative enterprise names in the first expansion manner, a preset distance J is calculated according to the following formula, and the setting is set
Specifically, the preset distance is accurately calculated according to the first relative difference, so that the preset distance is determined more efficiently and accurately, the expansion effect is ensured, and the excessive expansion of the candidate enterprise name set is avoided.
Specifically, when it is determined that the candidate enterprise name set is expanded in the second expansion mode, the cosine similarity Y between the enterprise name to be expanded in the enterprise name set to be expanded and the business scope text of the enterprise to be evaluated is calculated according to the following formula, and the setting is set
Wherein A represents the characteristic vector of the name of the enterprise to be expanded, and B represents the characteristic vector of the business scope text of the enterprise to be evaluated.
Specifically, when the cosine similarity Y is calculated, determining whether to add the enterprise name to be expanded to an alternative enterprise name set according to a comparison result of the cosine similarity Y and a preset cosine similarity Y0;
When Y is less than or equal to Y0, determining that the enterprise name to be expanded is not added to the alternative enterprise name set;
When Y > Y0, determining to add the enterprise name to be expanded to an alternative enterprise name set;
In the embodiment of the invention, the enterprise name set to be expanded is created by randomly selecting 60% of names of all enterprises in the whole country, and the preset cosine similarity Y0 has a value of 0.6, so that a person skilled in the art can adjust the preset cosine similarity Y0 according to specific conditions.
Specifically, the invention measures the similarity between the feature vector of the enterprise name to be expanded and the feature vector of the business scope text of the enterprise to be evaluated through the cosine similarity, ensures that the enterprise added into the set has a certain correlation with the enterprise to be evaluated in terms of business so as to more accurately inquire the enterprise close to the enterprise to be evaluated, adds the enterprise name to be expanded into the alternative enterprise name set only when the cosine similarity exceeds the preset cosine similarity, thereby protecting information, blurring potential supply chain relation, simultaneously preventing the enterprise name completely irrelevant to the enterprise to be evaluated from being added into the alternative enterprise name set, avoiding introducing excessive noise data, and being beneficial to maintaining the quality and practicality of the alternative enterprise name set.
Specifically, when the alternative enterprise name set, the names of the enterprises to be evaluated and the names of the buyers with trade relation with the enterprises to be evaluated are processed according to the MinHash algorithm, determining the hash function number in the MinHash algorithm according to the comparison result of the enterprise name number L in the alternative enterprise name set and the second preset enterprise name number L2;
When L is less than or equal to L2, determining the number of hash functions in the MinHash algorithm as the first hash function number H1;
When L > L2, determining the number of hash functions in the MinHash algorithm as the second hash function number H2;
In the embodiment of the present invention, the first hash function number H1 is preferably 100, the second hash function number H2 is preferably 300, the second preset enterprise name number L2 has a value of 1200, and a person skilled in the art can adjust the first hash function number H1, the second hash function number H2, and the second preset enterprise name number L2 according to specific situations.
Specifically, the method and the device have the advantages that the accuracy of the MinHash signature is affected by the number of the Hash functions, the proper number of the Hash functions is selected to ensure that the generated signatures can accurately reflect similarity among names while the calculation efficiency is kept, when the alternative enterprise name set is smaller, the better signature effect is provided by using fewer Hash functions, so that calculation resources are saved, and when the alternative enterprise name set is larger, more Hash functions are used to provide finer signatures to cope with the complexity of the alternative enterprise name set.
Specifically, when a first mixed signature set is created, calculating a first semantic similarity X1 between an alternative enterprise name signature in the alternative enterprise name signature set and the enterprise name signature to be evaluated, determining whether the alternative enterprise name signature is qualified or not according to a comparison result of the first semantic similarity X1 and a first preset semantic similarity X01, and setting x1=d1/D2, wherein D1 represents the number of the same hash values at the same position in the alternative enterprise name signature and the enterprise name signature to be evaluated, and D2 represents the total number of the hash values of the alternative enterprise name signature and the enterprise name signature to be evaluated;
when X1 is less than or equal to X01, determining that the alternative enterprise name signature is unqualified;
When X1> X01, determining that the alternative enterprise name signature is qualified;
in the embodiment of the invention, the value of the first preset semantic similarity X1 is 0.9, and a person skilled in the art can adjust the first preset semantic similarity X1 according to specific conditions.
Specifically, the method and the device for the enterprise privacy protection based on the name signature of the enterprise, provided by the invention, have the advantages that the first preset semantic similarity is set to select the alternative enterprise name signature which is highly similar to the enterprise to be assessed, so that the enterprise added in the first confusion signature set can effectively confuse the true identity of the enterprise to be assessed, the quality of information protection is improved, and the third party data source is more difficult to distinguish which are true transaction relations when receiving the information, thereby better protecting the enterprise privacy.
Specifically, when a second mixed signature set is created, calculating a second semantic similarity X2 between an alternative enterprise name signature and a single buyer enterprise name signature in the alternative enterprise name signature set, determining whether the alternative enterprise name signature is qualified according to a comparison result of the second semantic similarity X2 and a second preset semantic similarity X02, and setting x2=e1/E2, wherein E1 represents the number of the same hash values at the same position in the alternative enterprise name signature and the single buyer enterprise name signature, and E2 represents the total number of the hash values of the alternative enterprise name signature and the single buyer enterprise name signature;
when X2 is less than or equal to X02, determining that the alternative enterprise name signature is unqualified;
when X2> X02, determining that the alternative enterprise name signature is qualified;
in the embodiment of the invention, the value of the second semantic similarity X2 is 0.8, and a person skilled in the art can adjust the second semantic similarity X2 according to specific conditions.
Specifically, the method and the system ensure that only the alternative enterprise name signatures above a certain similarity level are considered to be qualified and added into the second mixed signature set by setting the second preset semantic similarity X02, thereby being beneficial to protecting the privacy of a purchasing enterprise having a transaction relationship with an enterprise to be evaluated and reducing the potential risk of information leakage.
Specifically, whenAfter the transaction relation combination is generated, the quantity is combined according to the transaction relationThe comparison result of the combination quantity P of the transaction relation and the preset transaction relation determines whether the preset semantic similarity is adjusted or not;
When (when) When the semantic similarity is determined to be adjusted, the preset semantic similarity is determined to be adjusted;
When (when) When the semantic similarity is determined to be not adjusted, the preset semantic similarity is determined to be not adjusted;
In the embodiment of the present invention, the preset transaction relation combination number P has a value of 10000, and a person skilled in the art can adjust the preset transaction relation combination number P according to specific situations.
Specifically, the invention controls the scale of the generated transaction relation combinations by comparing the transaction relation combination quantity with the preset transaction relation combination quantity, wherein too many generated combinations can reduce the efficiency of data processing and analysis, too little combination quantity is insufficient to provide enough anonymization protection, and the preset semantic similarity is adjusted to help to achieve the proper scale of the mixed signature set.
Specifically, when it is determined to adjust the preset semantic similarity, the transaction relationship combination number is calculatedCombining the quantity P and the second relative difference delta P with the preset transaction relation, determining an adjustment mode for adjusting the preset semantic similarity according to the comparison result of the second relative difference delta P and the second preset relative difference delta P0, and setting
When delta P is less than or equal to delta P0, determining to adjust the preset semantic similarity in a first adjustment mode;
when the delta P is equal to delta P0, determining to adjust the preset semantic similarity in a second adjustment mode;
the first adjustment mode is to adjust the first preset semantic similarity X01 according to a first adjustment coefficient T1, and the second adjustment mode is to adjust the second preset semantic similarity X02 according to a second adjustment coefficient T2.
In the embodiment of the present invention, the second preset relative difference Δp0 takes a value of 0.4, and the second preset relative difference Δp0 isTaken in the case of 6000, the person skilled in the art can adjust the second preset relative difference Δp0 according to the specific case.
Specifically, the invention calculates the second relative difference and compares the second relative difference with the second preset relative difference to finely manage the adjustment of the preset semantic similarity, ensures that the generated transaction relation combination is not too much or too little, and maintains the rationality of the confusion signature set, thereby accurately adjusting the transaction relation combination quantity.
Specifically, when it is determined that the preset semantic similarity is adjusted in the first adjustment manner, a first adjustment coefficient T1 is calculated according to the following formula, and the setting is made
The adjusted first preset semantic similarity is set to xx01=x01×t1.
Specifically, when it is determined that the preset semantic similarity is adjusted in the second adjustment manner, a second adjustment coefficient T2 is calculated according to the following formula, and the setting is set
The adjusted second preset semantic similarity is set to xx02=x02×t2.
Specifically, the invention accurately calculates the adjustment coefficient according to the second relative difference to finely adjust the preset semantic similarity, ensures that the generated transaction relation combination is not too much or too little, and maintains the rationality of the mixed signature set, thereby accurately adjusting the number of the transaction relation combinations, ensuring the effect of information protection and avoiding the waste of calculation resources.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, and various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An information protection method for supply chain purchasing relationship chain data, comprising the following steps:
creating an alternative enterprise name set comprising the names of the enterprises to be evaluated, the names of n buyer enterprises having trade relations with the enterprises to be evaluated and the names of other enterprises in the same industry as the enterprises to be evaluated;
processing the alternative enterprise name set according to a MinHash algorithm to generate an alternative enterprise name signature set;
processing names of enterprises to be evaluated according to a MinHash algorithm, generating enterprise name signatures to be evaluated, determining qualified M alternative enterprise name signatures according to first semantic similarity between the alternative enterprise name signatures in the alternative enterprise name signature set and the enterprise name signatures to be evaluated, and creating a first confusion signature set comprising the M alternative enterprise name signatures;
According to a MinHash algorithm, the names of N purchase enterprises having transaction relation with an enterprise to be evaluated are processed, N purchase enterprise name signatures are generated, qualified N alternative enterprise name signatures are determined according to second semantic similarity between the alternative enterprise name signatures in the alternative enterprise name signature set and the single purchase enterprise name signature, and a second confusion signature set comprising N multiplied by N alternative enterprise name signatures is created;
combining alternative business name signatures in a second set of mixed signatures The purchasing enterprises are combined and signed according to the alternative enterprise names in the first mixed signature setCombined generation of purchasing party enterprisesA transaction relation combination;
The said The transaction relation combinations are sent to a third party data source, credit scores of each transaction relation combination are obtained, and scores of the transaction relation combinations of the enterprise to be evaluated and the buyer enterprise are selected;
When the creation of the alternative enterprise name set is completed, determining expansion of the alternative enterprise name set according to the number of enterprise names in the alternative enterprise name set;
When the alternative enterprise name set, the names of the enterprises to be evaluated and the names of the purchase enterprises having transaction relation with the enterprises to be evaluated are processed according to the MinHash algorithm, determining the number of hash functions in the MinHash algorithm according to the number of enterprise names in the alternative enterprise name set;
When (when) After the transaction relation combination is generated, the quantity is combined according to the transaction relationAnd determining adjustment of the preset semantic similarity.
2. The method for protecting information of supply chain purchasing relationship chain data according to claim 1, wherein the expanding the candidate enterprise name set is determined to expand the candidate enterprise name set under the condition that the number of enterprise names in the candidate enterprise name set is less than or equal to a first preset number of enterprise names.
3. The method for protecting information of supply chain purchasing relationship chain data according to claim 2, wherein the determining to expand the candidate enterprise name set includes determining to expand the candidate enterprise name set in a first expansion manner on the condition that a first relative difference is less than or equal to a first preset relative difference, wherein the first expansion manner is that names of all enterprises covered by taking an enterprise to be evaluated as a center and a preset distance as a radius are added to the candidate enterprise name set;
Wherein the first relative difference is determined by the number of business names and a first preset number of business names.
4. The method of claim 3, wherein determining that the set of candidate business names is expanded comprises determining that the set of candidate business names is expanded in a second expansion manner based on the business scope text of the business to be evaluated if the first relative difference is greater than the first preset relative difference.
5. The method for protecting information of supply chain purchasing relationship chain data according to claim 4, wherein the preset distance is calculated according to the following formula, and the setting is set
Wherein J represents a preset distance, Δl represents the first relative difference, and Δl1 represents the first preset relative difference.
6. The method for protecting information of supply chain purchasing relationship chain data according to claim 5, wherein expanding the candidate enterprise name set according to the business scope text of the enterprise to be evaluated includes determining to add the enterprise name to the candidate enterprise name set if cosine similarity between the enterprise name to be expanded in the enterprise name set and the business scope text of the enterprise to be evaluated is greater than a preset cosine similarity;
The cosine similarity between the enterprise name to be expanded and the business scope text of the enterprise to be evaluated in the enterprise name set to be expanded is calculated according to the following formula, and the setting is carried out
Wherein Y represents the cosine similarity, A represents the feature vector of the name of the enterprise to be expanded, and B represents the feature vector of the business scope text of the enterprise to be evaluated.
7. The method for protecting information of supply chain purchasing relationship chain data according to claim 6, wherein determining the number of hash functions in the MinHash algorithm includes determining that the number of hash functions in the MinHash algorithm is the first number of hash functions if the number of business names in the candidate business name set is less than or equal to the second preset number of business names, and determining that the number of hash functions in the MinHash algorithm is the second number of hash functions if the number of business names in the candidate business name set is greater than the second preset number of business names.
8. The information protection method of supply chain purchasing relationship chain data according to claim 7, wherein a first semantic similarity between an alternative enterprise name signature in the alternative enterprise name signature set and the enterprise name signature to be evaluated is calculated according to the following formula, and x1=d1/D2 is set, wherein X1 represents the first semantic similarity, D1 represents the number of hash values that are the same at the same position in the alternative enterprise name signature and the enterprise name signature to be evaluated, and D2 represents the total number of hash values of the alternative enterprise name signature and the enterprise name signature to be evaluated;
The determining the qualified M candidate enterprise name signatures comprises determining that the candidate enterprise name signatures are not qualified under the condition that the first semantic similarity is smaller than or equal to a first preset semantic similarity, and determining that the candidate enterprise name signatures are qualified under the condition that the first semantic similarity is larger than the first preset semantic similarity.
9. The method for protecting information of supply chain purchasing relationship chain data according to claim 8, wherein the second semantic similarity between the alternative enterprise name signature and the single purchase enterprise name signature in the alternative enterprise name signature set is calculated according to the following formula, X2 = E1/E2 is set, wherein X2 represents the second semantic similarity, E1 represents the number of hash values that are the same at the same location in the alternative enterprise name signature and the single purchase enterprise name signature, and E2 represents the total number of hash values of the alternative enterprise name signature and the single purchase enterprise name signature;
The determining the qualified N candidate enterprise name signatures comprises determining that the candidate enterprise name signatures are not qualified under the condition that the second semantic similarity is smaller than or equal to a second preset semantic similarity, and determining that the candidate enterprise name signatures are qualified under the condition that the second semantic similarity is larger than the second preset semantic similarity.
10. The method for protecting information in supply chain procurement relationship chain data according to claim 9, characterized by the fact that the determining an adjustment to a preset semantic similarity comprises combining the number in a trade relationshipDetermining to adjust the preset semantic similarity under the condition that the combination quantity of the preset transaction relations is smaller than or equal to the preset semantic similarity;
The determining of the preset semantic similarity includes determining to adjust the preset semantic similarity in a first adjustment mode under the condition that the second relative difference is smaller than or equal to a second preset relative difference, and determining to adjust the preset semantic similarity in a second adjustment mode under the condition that the second relative difference is larger than the second preset relative difference, wherein the first adjustment mode is according to a first adjustment coefficient The first preset semantic similarity is adjusted, and the second adjustment mode is that according to a second adjustment coefficientAdjusting a second preset semantic similarity, wherein ΔP represents a second relative difference, the second relative difference being determined by the number of trade relationship combinationsAnd combining the quantity with a preset transaction relation to determine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411152381.5A CN119228393B (en) | 2024-08-21 | 2024-08-21 | Information protection method for supply chain purchasing relationship chain data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411152381.5A CN119228393B (en) | 2024-08-21 | 2024-08-21 | Information protection method for supply chain purchasing relationship chain data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119228393A CN119228393A (en) | 2024-12-31 |
| CN119228393B true CN119228393B (en) | 2025-10-17 |
Family
ID=94067826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411152381.5A Active CN119228393B (en) | 2024-08-21 | 2024-08-21 | Information protection method for supply chain purchasing relationship chain data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119228393B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160908A (en) * | 2019-12-31 | 2020-05-15 | 深圳市网心科技有限公司 | Supply chain transaction privacy protection system and method based on block chain and related equipment |
| CN118282605A (en) * | 2024-03-29 | 2024-07-02 | 中国工商银行股份有限公司 | Data transmission method and system based on fragmentation obfuscation |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3688929B1 (en) * | 2019-05-31 | 2022-03-30 | Advanced New Technologies Co., Ltd. | System and method for providing privacy and security protection in blockchain-based private transactions |
| CN111160909B (en) * | 2019-12-31 | 2024-01-16 | 深圳市迅雷网络技术有限公司 | Blockchain supply chain transaction hidden static supervision system and method |
| CN115456631B (en) * | 2022-09-30 | 2023-07-21 | 佛山众陶联供应链服务有限公司 | Multi-level supply chain credit cross-level verification method and system based on blockchain |
-
2024
- 2024-08-21 CN CN202411152381.5A patent/CN119228393B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160908A (en) * | 2019-12-31 | 2020-05-15 | 深圳市网心科技有限公司 | Supply chain transaction privacy protection system and method based on block chain and related equipment |
| CN118282605A (en) * | 2024-03-29 | 2024-07-02 | 中国工商银行股份有限公司 | Data transmission method and system based on fragmentation obfuscation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119228393A (en) | 2024-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11966894B2 (en) | Apparatus for cryptographic resource transfer based on quantitative assessment regarding non-fungible tokens | |
| US20240330918A1 (en) | Systems and methods for validating asset destinations in blockchain networks | |
| US20220309505A1 (en) | Reissuing obligations to preserve privacy | |
| US10992478B2 (en) | Blockchain-based digital identity management method | |
| WO2019205876A1 (en) | Credit investigation system, credit investigation data storage method and device, device and medium | |
| CN111164629A (en) | Methods, apparatus, and computer-readable media for compliance-aware tokenization and control of asset value | |
| JP2017091515A (en) | Computer-implemented system and method for automatically identifying attributes for anonymization | |
| US20210374853A1 (en) | Atomically swapping ownership certificates | |
| CN107133865A (en) | A kind of acquisition of credit score, the output intent and its device of characteristic vector value | |
| US20240394704A1 (en) | Cosigning Using Tokenized Reputation Scores | |
| WO2024057150A1 (en) | User verification with non-fungible tokens | |
| JP4029934B2 (en) | Distributed computing system | |
| US20230245134A1 (en) | System and method for automatic product source tracing | |
| Upadhyay et al. | The dark side of non-fungible tokens: understanding risks in the NFT marketplace from a fraud triangle perspective | |
| US20250173726A1 (en) | Systems and methods for early fraud detection in deferred transaction services | |
| KR102626699B1 (en) | Business plan distribution management method, server and system based on blockchain | |
| Geva | Disintermediating electronic payments: Digital cash and virtual currencies | |
| CN119228393B (en) | Information protection method for supply chain purchasing relationship chain data | |
| US12002047B1 (en) | System and method for blockchain-verified digital-identity-and-derivatives archetype-based transaction processing and implementation with the aid of a digital computer | |
| EP4075363A1 (en) | Self learning machine learning scores adjustment via normalization thereof | |
| Pathak et al. | Improving e-commerce fraud detection: A GAN and reinforcement learning approach integrated with personality analysis for secure digital economy | |
| CN112231746B (en) | Joint data analysis method, device, system and computer readable storage medium | |
| Shukla et al. | Delend: A p2p loan management scheme using public blockchain in 6g network | |
| US20220027916A1 (en) | Self Learning Machine Learning Pipeline for Enabling Binary Decision Making | |
| CN113498592B (en) | Method and system for digital property authentication and management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |