Method, device, and computer storage medium for handling data circulation transaction violations

Abstract

This application relates to the technical field of big data and large models, and provides a method for handling illegal acts in data circulation and trading. The method includes: constructing an evidence chain corresponding to the type of historical illegal acts based on legal documents related to historical illegal acts in data circulation and trading; predicting the type of illegal acts to which the target data circulation and trading belong by monitoring the process of the target data circulation and trading; determining the evidence types associated with the evidence of the target data circulation and trading according to the type of illegal acts to which the target data circulation and trading belong and the evidence chain corresponding to the type of historical illegal acts; constructing an evidence chain for the target data circulation and trading according to the evidence types associated with the evidence of the target data circulation and trading; calculating the violation weight based on the evidence chain of the target data circulation and trading and comparing it with the violation weight calculated from the evidence chain of historical illegal acts with the same type of illegal acts to determine whether the target data circulation and trading are illegal. The technical solution of this application can effectively determine and trace illegal acts in the process of data circulation and trading.

Description

Technical Field

[0001] The present invention relates to the technical field of big data and big models, and in particular to a method, device and computer storage medium for processing data circulation transaction violations. Background Art

[0002] Data, as the fifth largest production factor alongside land, capital, technology, and labor, contains enormous value. Data circulation and trading are the key to releasing the value of data as a production factor. There may be many risks of violations in the process of data circulation and trading, such as abuse by data demanders, secondary data trafficking, data registration and release information that is inconsistent with the actual data content, etc. Therefore, it is necessary to determine and trace the violations in the process of data circulation and trading.

[0003] At present, although the industry has proposed many plans to regulate violations in the process of data circulation transactions, these plans either cannot quickly and accurately identify potential violations in transactions due to the wide variety of violations in the process of data circulation transactions, or cannot trace all relevant evidence of violations to construct violation scenarios and reconstruct violations because violations in the process of data circulation transactions involve a large number of complex operations, each of which will generate a lot of evidence. Summary of the invention

[0004] The present application provides a method, device and computer storage medium for processing data circulation transaction violations, which can effectively determine and trace violations in the data circulation transaction process.

[0005] On the one hand, the present application provides a method for handling data circulation transaction violations, the method comprising:

[0006] Based on the legal documents related to historical violations of data circulation transactions, build a chain of evidence corresponding to the type of each historical violation;

[0007] By monitoring the process of target data circulation transactions, predicting the type of illegal behavior to which the target data circulation transactions belong;

[0008] Determine the type of evidence associated with the evidence of the target data circulation transaction according to the type of violation to which the target data circulation transaction belongs and the chain of evidence corresponding to the historical violations of the same violation type;

[0009] Constructing an evidence chain for the target data circulation transaction according to the evidence type associated with the evidence for the target data circulation transaction;

[0010] Whether the target data circulation transaction is in violation is determined based on the violation weight of the target data circulation transaction calculated by the evidence chain of the target data circulation transaction and the violation weight of the historical violation calculated by the evidence chain of the historical violation.

[0011] On the other hand, the present application provides a device for processing data circulation transaction violations, the device comprising:

[0012] The first chain building module is used to build a chain of evidence corresponding to the type of each historical violation based on the legal documents related to the historical violations of data circulation transactions;

[0013] A prediction module, used to predict the type of illegal behavior of the target data circulation transaction by monitoring the process of the target data circulation transaction;

[0014] A first determination module is used to determine the type of evidence associated with the evidence of the target data circulation transaction according to the type of violation to which the target data circulation transaction belongs and the chain of evidence corresponding to the historical violations of the same violation type;

[0015] A second chain building module, used to build an evidence chain for the target data circulation transaction according to the evidence type associated with the evidence of the target data circulation transaction;

[0016] The second determination module is used to determine whether the target data circulation transaction is in violation of the regulations based on the violation weight of the target data circulation transaction calculated by the evidence chain of the target data circulation transaction and the violation weight of the historical violation calculated by the evidence chain of the historical violation.

[0017] In a third aspect, the present application provides a device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the technical solution of the method for handling data circulation transaction violations as described above when executing the computer program.

[0018] In a fourth aspect, the present application provides a computer storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the steps of the technical solution of the method for handling violations of data circulation transactions as described above.

[0019] As can be seen from the technical solution provided in the present application above, based on the legal documents related to historical violations of data circulation transactions, an evidence chain corresponding to the type to which each historical violation belongs is constructed. Since the legal documents related to historical violations of data circulation transactions are in a state of being updated at any time or regularly, it is possible to dynamically update the evidence chain of violations of data circulation transactions, so that the subsequent determination of violations of data circulation transactions based on this has the latest basis, improving the correctness of the determination of violations of data circulation transactions. On the one hand, by monitoring the process of the target data circulation transaction and predicting the type of violation to which the target data circulation transaction belongs, the efficiency of subsequent determination and traceability of violations of the target data circulation transaction can be improved; on the other hand, based on the type of violation to which the target data circulation transaction belongs and the evidence chain corresponding to historical violations with the same type of violation, an evidence chain of the target data circulation transaction is constructed, and the violation weight is calculated according to the evidence chain of the target data circulation transaction and compared with the violation weight calculated from the evidence chain of historical violations with the same type of violation to determine whether the target data circulation transaction is in violation, realizing the determination and traceability of violations. In summary, compared with the prior art, the technical solution of the present application can effectively determine and trace violations in the process of data circulation transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 is a flowchart of a method for handling violations of data circulation transactions provided by an embodiment of the present application;

[0022] Figure 2 is a schematic diagram of the evidence chain of violations provided by an embodiment of the present application;

[0023] Figure 3 is a schematic structural diagram of a device for handling violations of data circulation transactions provided by an embodiment of the present application;

[0024] Figure 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0026] In this specification, adjectives such as first and second can only be used to distinguish one element or action from another element or action, and do not necessarily require or imply any actual such relationship or order. Where circumstances permit, reference to an element or component or step (etc.) should not be construed as being limited to only one of the element, component, or step, but can be one or more of the element, component, or step, etc.

[0027] In this specification, for ease of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationship.

[0028] During the data circulation and transaction process, many illegal risks may be faced. For example, the data demander misuses the data, resells the data secondarily, the information registered and published about the data does not match the actual content of the data, and so on. At present, although the industry has proposed many solutions for supervising illegal behaviors in the data circulation and transaction process, however, either due to the variety of illegal behaviors in the data circulation and transaction process, these solutions cannot quickly and accurately identify potential illegal behaviors in the transaction, or due to the large number of complex operations involved in the illegal behaviors in the data circulation and transaction process, and each operation will generate a lot of evidence, so it is impossible to trace all the evidence related to the illegal behavior to construct an illegal scenario and reconstruct the illegal behavior.

[0029] In view of the above problems of the prior art, the present application proposes a method for handling illegal behaviors in data circulation and transaction, and its flowchart is as shown in the appendix Figure 1 shown, mainly including steps S101 to S105, which are described in detail as follows:

[0030] Step S101: Based on the legal documents related to the historical illegal behaviors of data circulation and transaction, construct an evidence chain corresponding to the type of each historical illegal behavior.

[0031] In the existing solution for constructing the evidence chain of violations, professionals need to spend a great deal of time and effort extracting the entities and relationships related to violations from legal documents. Since the legal documents related to historical violations in data circulation and transactions are in a state of being updated at any time or regularly, therefore, based on the legal documents related to historical violations in data circulation and transactions, this application proposes to construct an evidence chain corresponding to the type of each historical violation, which can dynamically update the evidence chain of violations in data circulation and transactions, so that subsequent judgments on violations in data circulation and transactions based on this have the latest basis, improving the correctness of judgments on violations in data circulation and transactions. As an embodiment of this application, constructing an evidence chain corresponding to the type of each historical violation based on the legal documents related to historical violations in data circulation and transactions can be achieved through steps S1011 to S1013, and the details are as follows:

[0032] Step S1011: Construct an entity-relationship triple for violations , a prior relationship topology triple and based on the prior relationship topology triple produce an annotated data set containing the entity-relationship triple , where is a possible illegal operation for a violation is the executor of , is the evidence generated by the execution of , and are two illegal operations with a relationship . The

[0033] Input the annotated data set into a preset model to train the preset model to obtain a trained language model;

[0034] In the embodiment of this application, an illegal operation usually refers to a specific behavior, action or process, that is, a behavior specifically implemented by a person or entity. For example, specific behaviors such as illegally accessing data and tampering with records in a system can be called "illegal operations". Compared with illegal operations, a violation is usually a broader concept, which may include the motivation, background and results of the operation. In other words, a violation not only includes specific operations, but also includes the overall background and impact of these operations. For example, "an employee of a certain data trading platform accessed the company's database without authorization, downloaded customer data, resulting in data leakage." is a "violation" because it involves the motivation and results of the operation.

[0035] The entity-relationship triple for violations includes , and , where​​​​​ For the possible illegal operations of violations, is the execution subject of is the evidence generated by the execution. Taking the violation of "an employee of a certain data trading platform accessed the company's database without authorization, downloaded customer data, resulting in data leakage." as an example, "an employee of a certain data trading platform" is the execution subject , "accessing the company's database without authorization" is the illegal operation , "customer data" is the evidence generated by the execution . In the relational topology triple , the relationship is and a certain specific connection or dependency relationship existing between them, including causal relationship, logical relationship, time sequence relationship, etc. Taking the violation of "an employee of a certain data trading platform accessed the company's database without authorization, downloaded customer data, resulting in data leakage." as an example, "accessing the company's database without authorization" and "downloading customer data" are the illegal operations and of this violation. Since "accessing the company's database without authorization" is a prerequisite or precondition for the illegal operation , and only after the operation of accessing the company's database is completed can the illegal operation of "downloading customer data" occur. Therefore, describes and this causal or dependency relationship between the two.

[0036] Step S1012: Input the labeled data set containing entity-relationship triples into the preset model to train the preset model, and obtain the trained language model.

[0037] To avoid the error propagation caused by first identifying entities and then predicting relationships, the preset model of this application selects a model based on Seq2Seq. The labeled data set containing entity-relationship triples can be input into the model based on Seq2Seq to train the model based on Seq2Seq, so as to obtain the trained language model. The specific training method can be any existing method, and this application does not limit it.

[0038] Step S1013: Adopt the trained language model and construct an evidence chain corresponding to the type of each historical violation by querying the legal documents related to the historical violations.

[0039] In the embodiments of the present application, the legal documents related to historical violations may be public databases, such as the legal documents related to historical violations of data circulation and transactions publicly available in databases such as the China Judgments Online. Specifically, by using a pre-trained language model and querying the legal documents related to historical violations, the evidence chain corresponding to each type of historical violation can be constructed through the following steps S1 to S3:

[0040] Step S1: According to the type of violation, query the factual text related to the violation in the database of legal documents related to historical violations.

[0041] As mentioned above, the database of legal documents related to historical violations may be a public database such as the China Judgments Online. If these databases store relevant data in a key-value storage manner, then when querying, the type of violation can be used as the key to query the factual text related to the violation.

[0042] Step S2: Use the factual text related to the violation queried in the database of legal documents related to historical violations as the input of the pre-trained language model to identify the relationship between named entities and extraction operations, and output an entity relationship triple , where is a possible violation operation for a certain type of violation, is the execution subject of is the evidence generated by the execution of

[0043] As mentioned above, since the pre-trained language model is trained on a labeled dataset containing entity relationship triples <,, > made using a prior relationship topology triple <,, > for a preset model (e.g., a model based on Seq2Seq), therefore, by inputting the factual text related to the violation queried in the database of legal documents related to historical violations into the pre-trained language model, it can identify named entities and extract the relationship between operations, and then output an entity relationship triple <,, >, where is a possible violation operation for a certain type of violation, is the execution subject of, and is the evidence generated by the execution of.

[0044] Step S3: Use the entity relationship triple as a node, and according to the prior relationship topology triple , query from the results of the current case document whether there is an entity relationship triple with the operation being . If it exists, establish an edge between the two nodes to form an evidence chain of historical violations, where and are two operations with the relationship .

[0045] If there is an entity-relationship triple with an operation of found in the results of the current case documents, then there is likely an evidence chain with the edge as a link. Therefore, establish the edge between the two nodes to facilitate tracing of violations during determination and ultimately form an evidence chain of violations. Among them, and are two operations with the relationship . Here, they may be the same or different operations.

[0046] Considering that the weight assignment of the evidence chain is very important for the determination of violations, the weights of different nodes and edges reflect their importance and credibility in historical cases, which is conducive to assisting decision-makers in making more reasonable decisions on violation governance. Therefore, when establishing an edge between two nodes to form an evidence chain of historical violations, specifically, it can be: examine the number of times the edge between the two nodes and appears in all evidence chains with the same violation type count and the total number of nodes and edges in all evidence chains with the same violation type N ; calculate count / N , and assign count / N as the weight to the edge between the two nodes and to construct an evidence chain of historical violations. Taking the 2 evidence chains with the same violation type shown in Figure 2 as an example, assume that node 4 (labeled 4 in the circle) and node 7 (labeled 7 in the circle) are the two nodes of the edge to be established (denoted as , i.e., = ). If the direction indicated by the arrow represents an evidence chain, then the number of times it appears in the 2 evidence chains shown in the figure is 2, i.e., count =2, and the total number of times all nodes and the edge to be established appear in all evidence chains is 20, i.e., N =20. Then the weight of the edge is 2 / 20, i.e., =0.1. The calculation method of the weight of a node in an evidence chain is similar to that of the weight of an edge, that is, the ratio of the number of times any node appears in all evidence chains with the same violation type to the total number of nodes and edges in all evidence chains with the same violation type.

[0047] Step S102: Predict the type of violation behavior to which the target data circulation transaction belongs by monitoring the process of the target data circulation transaction.

[0048] In the process of data circulation transactions, if the determination of violation behavior depends on manual investigation and evidence collection in each link before and after the data circulation transaction, and the determination of violation behavior is completed based on the obtained evidence, it is not only time-consuming and laborious but also error-prone. To solve this problem, this application obtains the evidence of several types of historical violation behaviors similar to the evidence information involved in the data circulation transaction, and uses the Large Language Model (LLM) to predict the type of violation behavior corresponding to this transaction based on the obtained evidence of historical violation behaviors. Specifically, predicting the type of violation behavior to which the target data circulation transaction belongs by monitoring the process of the target data circulation transaction can be achieved through steps S1021 to S1024, which are described in detail as follows:

[0049] Step S1021: Collect the evidence information of the target data circulation transaction.

[0050] In the embodiment of this application, the target data is the object of a certain operation, and it is necessary to determine whether the certain operation is a violation and can be traced in the future. The evidence information of the target data circulation transaction will be used as the basis for determining the violation behavior of the target data. When collecting the evidence information of the target data circulation transaction, it is generally automatically collected by monitoring the data element circulation transaction market, or it can also be the evidence provided by the user's request for audit. Considering that the evidence information of the collected data circulation transaction is often too broad, for example, the evidence collected in each data circulation transaction may be text with more than a certain number (such as 2000) of characters and low readability, which will introduce noise to the violation determination and increase the difficulty of violation determination. Therefore, in the embodiment of this application, when collecting the evidence information of the target data circulation transaction, the LLM is used to summarize the evidence information collected in the previous stage, that is, the relevant evidence of the target data circulation transaction currently being monitored. Based on the summary of the evidence information collected in the previous stage, the original or initially collected evidence information of the target data circulation transaction is summarized without losing its original meaning into a text of a predetermined number (such as 100 - 200) of characters. In this way, the evidence information of the summarized target data circulation transaction is more concise and rich in information, reducing the noise introduced by the violation determination and increasing the difficulty of violation determination.

[0051] Step S1022: Map the evidence information of the target data circulation transaction to the digital vector space to obtain the vector corresponding to the evidence information of the target data circulation transaction.

[0052] When mapping the evidence information of the target data circulation transaction to the digital vector space, a historical violation nearest neighbor search operation can be used to map the evidence information of the target data circulation transaction to a digital vector space through an embedding layer, obtaining the vector corresponding to the evidence information of the target data circulation transaction. Considering that the FastText model is insensitive to the length of text input and can generate a dense matrix, facilitating the calculation of the Euclidean distance between similar vectors, therefore, when mapping the evidence information of the target data circulation transaction (which can be the evidence information summarized by the aforementioned examples) to a digital vector space through the embedding layer, the FastText model is used as the embedding model. It should be noted that since the downstream task is to predict the type of violations involved in data circulation transactions, in the embodiments of the present application, the evidence information of historical data circulation transactions can be selected to train embedding models such as the FastText model.

[0053] Step S1023: Calculate the similarity between the vector corresponding to the evidence information of the target data circulation transaction and the vector corresponding to the evidence information of historical violation behaviors, obtaining K types of historical violation behaviors similar to the target data circulation transaction, where K is a natural number greater than 1.

[0054] Step S1024: The large language model predicts the possible violation types of the target data circulation transaction based on the K types of historical violation behaviors similar to the target data circulation transaction.

[0055] Specifically, the LLM can reason about the evidence information of the target data circulation transaction, the K types of historical violation behaviors similar to the target data circulation transaction and their evidence information according to the prompt, and finally predict the possible violation types of the target data circulation transaction for further determination by the subsequent violation behavior determination and traceability function module.

[0056] Step S103: Determine the evidence types associated with the evidence of the target data circulation transaction according to the type of violation behavior to which the target data circulation transaction belongs and the evidence chain corresponding to the historical violation behaviors with the same type of violation behavior.

[0057] Specifically, the implementation of step S103 can be: according to the type of violation behavior to which the target data circulation transaction belongs, search for the violation behavior corresponding to the target data circulation transaction among the historical violation behaviors of data circulation transactions, that is, the violation behavior with the same type of violation behavior; starting from the corresponding node in the evidence chain of the violation behavior corresponding to the target data circulation transaction, traverse all the nodes connected to the corresponding node; obtain the evidence-related information and weights of all the nodes connected to the corresponding node and the information and weights of the connected edges, and determine the evidence types associated with the evidence of the target data circulation transaction according to the operations in the connected nodes.

[0058] Step S104: Construct an evidence chain for the target data circulation transaction based on the evidence types associated with the evidence of the target data circulation transaction.

[0059] Specifically, constructing an evidence chain for the target data circulation transaction based on the evidence types associated with the evidence of the target data circulation transaction can be achieved through the following steps S1041 to S1044:

[0060] Step S1041: Collect all the evidence associated with the evidence of the target data circulation transaction from the data circulation trading platform according to the evidence types associated with the evidence of the target data circulation transaction.

[0061] Step S1042: Examine the relationships between the target evidences to confirm whether the relationships between the target evidences match the relationships between any two evidences in the evidence chain of historical violation behaviors, where the target evidences are any two evidences to be connected among all the evidences associated with the evidence of the target data circulation transaction collected from the data circulation trading platform.

[0062] It should be noted that among any two evidences to be connected among all the evidences associated with the evidence of the target data circulation transaction collected from the data circulation trading platform, one is the currently collected evidence and the other is the previously obtained evidence.

[0063] Step S1043: If the relationships between the target evidences are the same as the relationships between two evidences in the evidence chain of historical violation behaviors, then connect the target evidences to construct a link in the evidence chain of the target data circulation transaction.

[0064] In the embodiments of the present application, the relationships between any two evidences in the evidence chain of historical violation behaviors can be described by using the relationship topology triples mentioned in the embodiments of constructing the evidence chain corresponding to each type of historical violation behavior. Therefore, if the target evidences have operations and and there is a relationship topology triple in the evidence chain of historical violation behaviors with the same type of violation behavior, then the relationships between the target evidences should be the same as the relationships between two evidences in the evidence chain of historical violation behaviors. Thus, connect the target evidences (i.e., the entity relationship triples corresponding to operations and ) to construct a link in the evidence chain of the target data circulation transaction.

[0065] Step S1044: Repeat steps S1042 and S1043 until all the evidences associated with the evidence of the target data circulation transaction have been examined.

[0066] Step S105: Determine whether the target data circulation transaction is in violation of the regulations based on the violation weight of the target data circulation transaction calculated from the evidence chain of the target data circulation transaction and the violation weight of the historical violation calculated from the evidence chain of the historical violation.

[0067] Step S104 illustrates the process of constructing a link in the evidence chain of the target data circulation transaction. By similar methods, after constructing the complete evidence chain of the target data circulation transaction, the weights of all nodes and all edges in the evidence chain of the target data circulation transaction are accumulated to obtain the violation weight of the target data circulation transaction. Then, the violation weight of the target data circulation transaction is compared with the violation weights of all historical violations with the same violation type. If the violation weight of the target data circulation transaction is greater than or equal to the minimum violation weight of the historical violations with the same violation type, the target data circulation transaction is determined to be in violation.

[0068] From the above attached Figure 1 It can be seen from the example of the method for handling violations of data circulation transactions that, based on the legal documents related to the historical violations of data circulation transactions, the evidence chain corresponding to the type of each historical violation is constructed. Since the legal documents related to the historical violations of data circulation transactions are in a state of being updated at any time or regularly, the evidence chain of the violations of data circulation transactions can be dynamically updated, so that the subsequent determination of violations of data circulation transactions based on this has the latest basis, and the correctness of the determination of violations of data circulation transactions is improved. On the one hand, by monitoring the process of target data circulation transactions and predicting the type of violations to which the target data circulation transactions belong, the efficiency of subsequent determination and tracing of violations of target data circulation transactions can be improved; on the other hand, based on the type of violations to which the target data circulation transactions belong and the evidence chain corresponding to the historical violations of the same type of violations, the evidence chain of the target data circulation transactions is constructed, and the violation weight is calculated according to the evidence chain of the target data circulation transactions and compared with the violation weight calculated by the evidence chain of the historical violations of the same type of violations, to determine whether the target data circulation transactions are in violation, and to achieve the determination and tracing of violations. In summary, compared with the prior art, the technical solution of the present application can effectively determine and trace the violations in the process of data circulation transactions.

[0069] Please see attached Figure 3 , is a data circulation transaction violation processing device provided in an embodiment of the present application, the device may include a first link building module 301, a prediction module 302, a first determination module 303, a second link building module 304 and a second determination module 305, which are described in detail as follows:

[0070] The first chain building module 301 is used to build an evidence chain corresponding to the type of each historical violation based on the legal documents related to the historical violations of data circulation transactions;

[0071] Prediction module 302, used to predict the type of illegal behavior of the target data circulation transaction by monitoring the process of the target data circulation transaction;

[0072] A first determination module 303 is used to determine the type of evidence associated with the evidence of the target data circulation transaction according to the type of the violation to which the target data circulation transaction belongs and the chain of evidence corresponding to the historical violations of the same violation type;

[0073] The second chain building module 304 is used to build an evidence chain for the target data circulation transaction according to the evidence type associated with the evidence of the target data circulation transaction;

[0074] The second determination module 305 is used to determine whether the target data circulation transaction is in violation of the regulations based on the violation weight of the target data circulation transaction calculated by the evidence chain of the target data circulation transaction and the violation weight of the historical violation calculated by the evidence chain of the historical violation.

[0075] From the above attached Figure 3 It can be seen from the example of the data circulation transaction violation processing device that, based on the historical violation-related legal documents of the data circulation transaction, the evidence chain corresponding to the type of each historical violation is constructed. Since the historical violation-related legal documents of the data circulation transaction are in a state of being updated at any time or regularly, the evidence chain of the violation of the data circulation transaction can be dynamically updated, so that the subsequent determination of the violation of the data circulation transaction based on this has the latest basis, and the correctness of the determination of the violation of the data circulation transaction is improved. On the one hand, by monitoring the process of the target data circulation transaction and predicting the type of violation to which the target data circulation transaction belongs, the efficiency of the subsequent determination and tracing of the violation of the target data circulation transaction can be improved; on the other hand, based on the type of violation to which the target data circulation transaction belongs and the evidence chain corresponding to the historical violation with the same violation type, the evidence chain of the target data circulation transaction is constructed, and the violation weight is calculated according to the evidence chain of the target data circulation transaction and compared with the violation weight calculated by the evidence chain of the historical violation with the same violation type, it is determined whether the target data circulation transaction is in violation, and the determination and tracing of the violation is realized. In summary, compared with the prior art, the technical solution of the present application can effectively determine and trace the violation in the process of data circulation transaction.

[0076] Figure 4 Schematic diagram of the structure of the device provided by an embodiment of the present application. Figure 4As shown, the device 4 of this embodiment mainly includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40, such as a program for the method of handling data circulation transaction violations. When the processor 40 executes the computer program 42, the steps in the above-mentioned embodiment of the method for handling data circulation transaction violations are implemented, such as Figure 1 the steps S101 to S105 shown. Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as Figure 3 the functions of the first chain building module 301, the prediction module 302, the first determination module 303, the second chain building module 304, and the second determination module 305 shown.

[0077] Exemplarily, the computer program 42 for the method of handling illegal data circulation transactions mainly includes: constructing an evidence chain corresponding to each type of historical illegal behavior based on legal documents related to historical illegal data circulation transactions; predicting the type of illegal behavior to which the target data circulation transaction belongs by monitoring the process of the target data circulation transaction; determining the evidence types associated with the evidence of the target data circulation transaction according to the type of illegal behavior to which the target data circulation transaction belongs and the evidence chain corresponding to historical illegal behaviors of the same type of illegal behavior; constructing an evidence chain for the target data circulation transaction according to the evidence types associated with the evidence of the target data circulation transaction; and determining whether the target data circulation transaction is illegal based on the illegal weight of the target data circulation transaction calculated from the evidence chain of the target data circulation transaction and the illegal weight of the historical illegal behavior calculated from the evidence chain of the historical illegal behavior. The computer program 42 can be divided into one or more modules / units, and one or more modules / units are stored in the memory 41 and executed by the processor 40 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 42 in the device 4. For example, the computer program 42 can be divided into the functions of a first evidence chain construction module 301, a prediction module 302, a first determination module 303, a second evidence chain construction module 304, and a second determination module 305 (modules in the virtual device), and the specific functions of each module are as follows: The first evidence chain construction module 301 is used to construct an evidence chain corresponding to each type of historical illegal behavior based on legal documents related to historical illegal data circulation transactions; the prediction module 302 is used to predict the type of illegal behavior to which the target data circulation transaction belongs by monitoring the process of the target data circulation transaction; the determination module 303 is used to determine the evidence types associated with the evidence of the target data circulation transaction according to the type of illegal behavior to which the target data circulation transaction belongs and the evidence chain corresponding to historical illegal behaviors of the same type of illegal behavior; the second evidence chain construction module 304 is used to construct an evidence chain for the target data circulation transaction according to the evidence types associated with the evidence of the target data circulation transaction; and the determination module 305 is used to calculate the illegal weight based on the evidence chain of the target data circulation transaction and compare it with the illegal weight calculated from the evidence chain of historical illegal behaviors of the same type of illegal behavior to determine whether the target data circulation transaction is illegal.

[0078] The device 4 may include but is not limited to the processor 40 and the memory 41. Those skilled in the art can understand that Figure 4 this is merely an example of the device 4 and does not constitute a limitation on the device 4. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the computing device may also include input / output devices, network access devices, buses, etc.

[0079] The so-called processor 40 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0080] The memory 41 may be an internal storage unit of the device 4, such as the hard disk or memory of the device 4. The memory 41 may also be an external storage device of the device 4, such as a plug-in hard disk equipped on the device 4, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 41 may also include both the internal storage unit of the device 4 and the external storage device. The memory 41 is used to store computer programs and other programs and data required by the device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0081] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above device can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0082] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0083] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0084] In the embodiments provided in this application, it should be understood that the disclosed devices / equipment and methods can be implemented in other ways. For example, the device / equipment embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0085] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, the functional units in each embodiment of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0087] When an integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned embodiment methods of this application, it can also be completed by instructing relevant hardware through a computer program. The computer program for the method of handling illegal data circulation and transaction behaviors can be stored in a computer storage medium. When this computer program is executed by a processor, it can implement the steps of each of the above method embodiments, that is, based on legal documents related to historical illegal behaviors of data circulation and transactions, construct an evidence chain corresponding to the type to which each historical illegal behavior belongs; by monitoring the process of the target data circulation and transaction, predict the type of illegal behavior to which the target data circulation and transaction belongs; according to the type of illegal behavior to which the target data circulation and transaction belongs and the evidence chain corresponding to historical illegal behaviors with the same type of illegal behavior, determine the evidence types associated with the evidence of the target data circulation and transaction; construct an evidence chain for the target data circulation and transaction according to the evidence types associated with the evidence of the target data circulation and transaction; determine whether the target data circulation and transaction is illegal according to the illegal weight of the target data circulation and transaction calculated based on the evidence chain of the target data circulation and transaction and the illegal weight of the historical illegal behavior calculated based on the evidence chain of the historical illegal behavior. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer storage medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer storage medium does not include electrical carrier signals and telecommunication signals.

[0088] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application. The specific implementation manners described above have further elaborated on the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above is only the specific implementation manner of the present application and is not used to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application should all be included in the protection scope of the present invention.

Claims

1. A method for handling data circulation transaction violations, characterized in that: The method comprises: Based on the legal documents related to historical violations of data circulation transactions, build a chain of evidence corresponding to the type of each historical violation; By monitoring the process of target data circulation transactions, predicting the type of illegal behavior to which the target data circulation transactions belong; Determine the type of evidence associated with the evidence of the target data circulation transaction according to the type of violation to which the target data circulation transaction belongs and the chain of evidence corresponding to historical violations of the same violation type; Constructing an evidence chain for the target data circulation transaction according to the evidence type associated with the evidence for the target data circulation transaction; Determine whether the target data circulation transaction is in violation of the law based on the violation weight of the target data circulation transaction calculated by the evidence chain of the target data circulation transaction and the violation weight of the historical violation calculated by the evidence chain of the historical violation; The process of monitoring the target data circulation transaction and predicting the type of violation to which the target data circulation transaction belongs includes: collecting evidence information of the target data circulation transaction; mapping the evidence information of the target data circulation transaction to a digital vector space to obtain a corresponding vector of the evidence information of the target data circulation transaction; calculating the similarity between the corresponding vector of the evidence information of the target data circulation transaction and the corresponding vector of the evidence information of the historical violation, and obtaining K types of historical violation similar to the target data circulation transaction, wherein K is a natural number greater than 1; and predicting the possible violation type of the target data circulation transaction according to the types of the K historical violation similar to the target data circulation transaction by a large language model; The method of determining the type of evidence associated with the evidence of the target data circulation transaction based on the type of violation to which the target data circulation transaction belongs and the chain of evidence corresponding to historical violations with the same type of violation includes: searching for violations corresponding to the target data circulation transaction in historical violations of data circulation transactions based on the type of violation to which the target data circulation transaction belongs; traversing all nodes connected to the corresponding node with the corresponding node in the chain of evidence corresponding to the target data circulation transaction as a starting point; obtaining evidence-related information and weights of all nodes connected to the corresponding node and information and weights of connected edges, and determining the type of evidence associated with the evidence of the target data circulation transaction based on operations in the connected nodes.

2. The method for handling data circulation transaction violations as claimed in claim 1, characterized in that: The legal documents related to historical violations of data circulation transactions are used to construct a chain of evidence corresponding to the type of each historical violation, including: Constructing entity-relationship triples for violation-oriented behavior <e p , r pq , e q >, prior relational topological triples <r p ,s pq , r q > and the relational topological triples based on the prior <r p ,s pq , r q > Make triples containing entity relationships <e p , r pq , e q >The labeled dataset, the r pq For the possible illegal operation of the illegal behavior, the e p For the r pq The execution subject, the e q To execute the pq The evidence generated by p and r q For two pq Illegal operations; Inputting the annotated data set into a preset model to train the preset model to obtain a trained language model; The trained language model is used and the legal documents related to the historical violations are queried to construct a chain of evidence corresponding to the type of each historical violation.

3. The method for handling data circulation transaction violations as claimed in claim 2, characterized in that: The method of using the trained language model and querying the legal documents related to the historical violations to construct a chain of evidence corresponding to the type of each historical violation includes: According to the type of the violation, searching for the text of the relevant facts of the violation in the database of the legal documents related to the historical violation; The violation-related factual text is used as the input of the trained language model to identify the relationship between named entities and extraction operations, and output entity relationship triples <e i , r ij , e j >, the r ij For a certain type of violation that may be a violation of the rules, the e i For the r ij The execution subject, the e j To execute the ij the evidence produced; The entity relationship triple <e i , r ij , e j >As nodes, according to the prior relationship topology triples <r ij ,s,r pq >, query whether there is an operation r in the result of the current case document pq If the entity relationship triple exists, an edge between the two nodes is established to form an evidence chain of historical violations. ij and r pq are two operations with relation s.

4. The method for handling data circulation transaction violations as claimed in claim 3, characterized in that: The step of establishing an edge between two nodes to form an evidence chain of historical violations includes: Consider the two nodes r of the edge to be established m and r j The number of times the edge between them appears in all evidence chains with the same violation type count and the total number of nodes and edges N in all evidence chains with the same violation type; Calculate count / N and assign the count / N as weight to the two nodes r m and r j to build a chain of evidence of historical violations.

5. The method for handling data circulation transaction violations as claimed in claim 1, characterized in that: The constructing the evidence chain of the target data circulation transaction according to the evidence type associated with the evidence of the target data circulation transaction includes: Step S1: collecting all evidence associated with the evidence of the target data circulation transaction from the data circulation transaction platform according to the type of evidence associated with the evidence of the target data circulation transaction; Step S2: Investigate the relationship between target evidences to confirm whether the relationship between the target evidences is consistent with the relationship between any two pieces of evidence in the chain of evidence of historical violations, wherein the target evidences are any two pieces of evidence to be connected from all evidences collected from the data circulation transaction platform and associated with the evidence of the target data circulation transaction; Step S3: If the target evidence has a relationship with two pieces of evidence in the evidence chain of the historical violation, the target evidence is connected to construct a link in the evidence chain of the target data circulation transaction; Repeat steps S2 and S3 until all evidence associated with the evidence of the target data circulation transaction has been examined.

6. A device for processing data circulation transaction violations, applied to the method for processing data circulation transaction violations as claimed in claim 1, characterized in that: The device comprises: The first chain building module is used to build a chain of evidence corresponding to the type of each historical violation based on the legal documents related to the historical violations of data circulation transactions; A prediction module is used to predict the type of illegal behavior to which the target data circulation transaction belongs by monitoring the process of target data circulation transaction, wherein the prediction of the type of illegal behavior to which the target data circulation transaction belongs by monitoring the process of target data circulation transaction includes: collecting evidence information of the target data circulation transaction; mapping the evidence information of the target data circulation transaction to a digital vector space to obtain a corresponding vector of the evidence information of the target data circulation transaction; calculating the similarity between the corresponding vector of the evidence information of the target data circulation transaction and the corresponding vector of the evidence information of historical illegal behaviors, and obtaining K types of historical illegal behaviors similar to the target data circulation transaction, wherein K is a natural number greater than 1; and predicting the possible illegal type of the target data circulation transaction according to the types of the K historical illegal behaviors similar to the target data circulation transaction by a large language model; A first determination module is used to determine the type of evidence associated with the evidence of the target data circulation transaction according to the type of violation to which the target data circulation transaction belongs and the chain of evidence corresponding to historical violations with the same type of violation, wherein the type of evidence associated with the evidence of the target data circulation transaction according to the type of violation to which the target data circulation transaction belongs and the chain of evidence corresponding to historical violations with the same type of violation comprises: searching for the violation corresponding to the target data circulation transaction in the historical violations of data circulation transactions according to the type of violation to which the target data circulation transaction belongs; taking the corresponding node in the chain of evidence corresponding to the violation corresponding to the target data circulation transaction as the starting point, traversing all nodes connected to the corresponding node; obtaining the evidence-related information and weights of all nodes connected to the corresponding node and the information and weights of the connected edges, and determining the type of evidence associated with the evidence of the target data circulation transaction according to the operations in the connected nodes; A second chain building module, used to build an evidence chain for the target data circulation transaction according to the evidence type associated with the evidence of the target data circulation transaction; The second determination module is used to determine whether the target data circulation transaction is in violation of the regulations based on the violation weight of the target data circulation transaction calculated by the evidence chain of the target data circulation transaction and the violation weight of the historical violation calculated by the evidence chain of the historical violation.

7. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images