Data processing method and device, storage medium, terminal and product

Abstract

Embodiments of the present specification provide a data processing method and device, a terminal, a computer readable storage medium and a computer program product. The method is applied to a first server, and the method comprises: establishing a target consortium chain. Receiving a data storage request sent by a second server, and verifying the identity of the second server, so that the second server stores the to-be-regulated data into the target consortium chain if the identity is verified. Wherein, the to-be-regulated data comprises one or more of transaction data, financial data and credit data. The to-be-regulated data stored in the target consortium chain is classified by a classification model, so as to determine that the category of the to-be-regulated data is abnormal data or normal data. If the category of the to-be-regulated data is abnormal data, the to-be-regulated data is determined as target data, and warning information about the target data is generated.

Description

Technical Field

[0001] This specification relates to the field of data processing technology, and in particular to a data processing method, apparatus, terminal, computer-readable storage medium, and computer program product. Background Technology

[0002] Consumer finance (or consumer loans) refers to loan services aimed at consumption, used to meet users' daily spending needs. Based on whether consumer finance transactions rely on specific scenarios and whether the loan funds are directly channeled into the consumption scenario, consumer finance can be further divided into consumer loans and cash loans.

[0003] Internet consumer finance companies aim to provide consumer finance services to consumers. In the process of lending to users and investing in companies, these companies generate relevant transaction data, financial data, credit data, and other financial data, which they are required to report to regulatory agencies. Regulatory agencies analyze this financial data to monitor and assess the risks of internet consumer finance companies.

[0004] However, the process of internet consumer finance companies reporting financial data and regulatory agencies analyzing that data still needs further improvement.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this specification, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] This specification provides a data processing method, apparatus, terminal, computer-readable storage medium, and computer program product that can improve the accuracy and efficiency of data processing.

[0007] Other features and advantages of the embodiments described herein will become apparent from the following detailed description, or may be learned in part by practice of this specification.

[0008] According to a first aspect of the embodiments of this specification, a data processing method is provided, which is applied to a first server. The method includes: establishing a target consortium blockchain; receiving a data storage request from a second server and authenticating the second server; if the second server is authenticated, confirming the data storage request so that the second server stores the data to be regulated in the target consortium blockchain; classifying the data to be regulated stored in the target consortium blockchain using a classification model to obtain a category of the data to be regulated, wherein the data to be regulated includes one or more of transaction data, financial data, and credit data, and the category includes abnormal data and normal data; if the category of the data to be regulated is abnormal data, determining the data to be regulated as target data, and generating early warning information about the target data.

[0009] In one embodiment of this specification, when the category of the data to be monitored is abnormal data, the method further includes: obtaining labeled target data, wherein the labeled target data is obtained by labeling the target data according to the category of the target data; when the category of the labeled target data is abnormal data, inputting the labeled target data into the classification model so that the classification model performs adversarial learning based on the labeled target data; when the category of the labeled target data is normal data, inputting the labeled target data into the classification model so that the classification model performs online learning based on the labeled target data.

[0010] In one embodiment of this specification, the above-mentioned inputting the labeled target data into the classification model so that the classification model performs adversarial learning based on the labeled target data includes: adding interfering content to the labeled target data to obtain adversarial data; and inputting the adversarial data into the classification model so that the classification model performs adversarial learning based on the adversarial data.

[0011] In one embodiment of this specification, the method further includes: when the category of the data to be regulated is normal data, performing online learning based on the data to be regulated through the classification model to update the parameters in the classification model.

[0012] In one embodiment of this specification, the data to be regulated stored in the target consortium blockchain includes an identity identifier; the method further includes: analyzing and processing the data to be regulated containing the target identity identifier through a smart contract in the target consortium blockchain, wherein the analysis and processing includes downscaling and / or upscaling; and determining the credit rating of the target identity identifier based on the results of the analysis and processing.

[0013] In one embodiment of this specification, the method further includes: training a machine learning model using labeled historical regulatory data to obtain the classification model; the above-mentioned training of the machine learning model using labeled historical regulatory data to obtain the classification model includes: training the machine learning model based on the labeled historical regulatory data through ensemble learning to obtain the classification model.

[0014] According to a second aspect of the embodiments of this specification, a data processing method is provided, which is applied to a second server. The method includes: acquiring data to be monitored, wherein the data to be monitored includes one or more of transaction data, financial data, and credit data; sending a data storage request to a first server, so that the first server authenticates the second server, and confirms the data storage request if the second server passes the authentication; storing the data to be monitored in a target consortium blockchain if the first server confirms the data storage request, so that the first server classifies the data to be monitored stored in the target consortium blockchain using a classification model to obtain a category of the data to be monitored, wherein the category includes abnormal data and normal data; and determining that the data to be monitored is target data if the category of the data to be monitored is abnormal data, and generating a warning message about the target data.

[0015] According to a third aspect of the embodiments of this specification, a data processing apparatus is provided, configured on a first server, the apparatus comprising: an establishment module for: establishing a target consortium blockchain; a receiving module for: receiving a data storage request from a second server and authenticating the second server; a confirmation module for: confirming the data storage request if the second server is authenticated, so that the second server stores the data to be monitored in the target consortium blockchain; a classification module for: classifying the data to be monitored stored in the target consortium blockchain using a classification model to obtain a category of the data to be monitored, wherein the data to be monitored includes one or more of transaction data, financial data, and credit data, and the category includes abnormal data and normal data; and a generation module for: determining the data to be monitored as target data if the category of the data to be monitored is abnormal data, and generating early warning information about the target data.

[0016] According to a fourth aspect of the embodiments of this specification, a data processing apparatus is provided, the apparatus being configured on a second server, the apparatus comprising: an acquisition module, configured to: acquire data to be monitored, wherein the data to be monitored includes one or more of transaction data, financial data, and credit data; a sending module, configured to: send a data storage request to a first server, so that the first server authenticates the second server, and confirms the data storage request if the second server passes the authentication; and a storage module, configured to: store the data to be monitored in a target consortium blockchain if the first server confirms the data storage request, so that the first server classifies the data to be monitored stored in the target consortium blockchain using a classification model to obtain a category of the data to be monitored, wherein the category includes abnormal data and normal data; and, so that if the category of the data to be monitored is abnormal data, the first server determines the data to be monitored as target data and generates a warning message about the target data.

[0017] According to a fifth aspect of the embodiments of this specification, a terminal is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the data processing method described in the first aspect and the data processing method described in the second aspect.

[0018] According to a sixth aspect of the embodiments of this specification, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, it implements the data processing method described in the first aspect and the data processing method described in the second aspect.

[0019] According to a seventh aspect of the embodiments of this specification, a computer program product is provided that, when the computer program product is run on a computer or processor, causes the computer or processor to implement the data processing method described in the first aspect and the data processing method described in the second aspect.

[0020] The data processing methods, apparatus, terminals, computer-readable storage media, and computer program products provided in the embodiments of this specification have the following technical effects:

[0021] The exemplary embodiments provided in this specification offer a solution applicable to regulatory agencies that classify data to be regulated and issue early warnings for abnormal data via a first server. Specifically, the data processing method includes: classifying the data to be regulated stored in the target consortium blockchain using a classification model to determine whether the data is abnormal or normal. The data to be regulated includes one or more of transaction data, financial data, and credit data. If the data to be regulated is classified as abnormal, it is determined to be target data, and early warning information about the target data is generated. This improves the accuracy and efficiency of processing data to be regulated.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification. It is obvious that the drawings described below are merely some embodiments of this specification, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0024] Figure 1 This is an interactive diagram illustrating a data processing method provided in an exemplary embodiment of this specification;

[0025] Figure 2 This is a flowchart of processing target data provided in an exemplary embodiment of this specification;

[0026] Figure 3 This is a scenario diagram illustrating a data processing method provided in an exemplary embodiment of this specification;

[0027] Figure 4 This is a structural diagram of a data processing apparatus provided in an exemplary embodiment of this specification;

[0028] Figure 5 This is a structural diagram of a data processing apparatus provided in another exemplary embodiment of this specification;

[0029] Figure 6 This is a structural diagram of a data processing apparatus provided in yet another exemplary embodiment of this specification;

[0030] Figure 7 This is a schematic block diagram of a terminal provided in an exemplary embodiment of this specification. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this specification clearer, the embodiments of this specification will be described in further detail below with reference to the accompanying drawings.

[0032] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.

[0033] In the description of this specification, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of these terms in this specification based on the specific circumstances. Furthermore, in the description of this specification, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0034] Internet consumer finance companies typically need to process and extract transaction data, financial data, credit data, etc. (hereinafter referred to as data subject to regulation) to form classified reports and submit them to regulatory agencies, such as the People's Bank of China and the China Banking Regulatory Commission (CBRC), so that regulatory agencies can understand the transaction risks and compliance status of financial companies in a timely manner.

[0035] The traditional regulatory reporting path is as follows: Internet consumer finance companies establish transaction nodes -> transaction nodes generate data to be regulated -> establish reporting nodes -> send the data to be regulated to regulatory agencies through the reporting nodes.

[0036] However, in the above path, if there is a significant difference in the establishment time between the reporting node and the transaction node, the data awaiting supervision in the middle may be tampered with, or staff may engage in financial fraud. The reported data awaiting supervision may lack timeliness, accuracy, and authority, making it difficult for the data finally reported to the regulatory agency to reflect the true transaction situation of the internet consumer finance company. This may increase the financial risk of the internet consumer finance company and hinder the regulatory agency from accurately, timely, and efficiently supervising the internet consumer finance company.

[0037] This specification provides a data processing method, apparatus, terminal, computer-readable storage medium, and computer program product that can improve the accuracy and efficiency of data processing.

[0038] in, Figure 1 An interactive diagram of a data processing method provided in one embodiment of this specification is shown.

[0039] In an exemplary embodiment, such as Figure 1 As shown, the second server 11 is used by the internet consumer finance company (i.e., the second server 11 corresponds to the internet consumer finance company), and the first server 10 is used by the regulatory agency (i.e., the first server 10 corresponds to the regulatory agency). The target consortium blockchain 12 can be a consortium blockchain. The target consortium blockchain 12 can be established by the first server 10 (the regulatory agency).

[0040] Blockchain is a secure, shared, decentralized data ledger. Blockchain technology supports a specific group of participants sharing data and is a data structure composed of linked data blocks. It uses cryptography and other methods to ensure that data is immutable and tamper-proof. Blockchain uses distributed consensus algorithms to generate data, cryptography to ensure the security of data transmission and access, and smart contracts and algorithms to impose restrictions. Overall, blockchain is a decentralized and tamper-proof data storage method.

[0041] There are three types of blockchains: public blockchains, private blockchains, and consortium blockchains. A consortium blockchain is a system form that falls between public and private blockchains. It is a blockchain jointly managed by several organizations or institutions, each controlling one or more nodes to record transaction data. Only these organizations or institutions can read, write, and send transactions within the consortium blockchain.

[0042] In the embodiments described in this specification, using a consortium blockchain to store the data to be regulated can prevent the data from being tampered with, thereby improving data security and accuracy. Simultaneously, storing the data to be regulated in real-time on the target consortium blockchain also ensures the timeliness of reporting the data to regulatory agencies.

[0043] Smart contracts, which can be provided by internet consumer finance companies, are deployed on the target consortium blockchain 12. Through these smart contracts, different internet consumer finance companies can store their regulated data in the target consortium blockchain 12 using public keys; while regulatory agencies can retrieve this regulated data from the target consortium blockchain 12 using private keys. In other words, internet consumer finance companies have write access to the regulated data, while regulatory agencies have read (query) access.

[0044] Specifically, the write permissions for internet consumer finance companies can be authorized by regulatory agencies. In other words, regulatory agencies can decide which companies can store data to be regulated in the target consortium blockchain 12, and which companies cannot.

[0045] In the exemplary embodiments, reference continues to be made to... Figure 1 After the second server 11 (Internet consumer finance company) generates the data to be regulated, it executes S110: Obtain the data to be regulated.

[0046] Subsequently, the second server 11 can send a data storage request to the first server 10 (the regulatory body) to request the regulatory body's permission to store the company's data to be regulated in the target consortium blockchain 12, that is, to request the permission to write the data to be regulated into the target consortium blockchain 12. That is, the second server 11 executes S120: sending a data storage request.

[0047] After receiving the aforementioned data storage request, the first server 10 can authenticate the second server 11, for example, by verifying the legitimacy of the second server 11, verifying the relevant information of the internet consumer finance company corresponding to the second server 11, etc., which are not limited in this embodiment. That is, the first server 10 executes S130: authenticate the second server.

[0048] If the second server 11 is authenticated, the first server 10 can confirm the data storage request, thereby granting the second server 11 the permission to write data. That is, the first server 10 executes S140: if the second server is authenticated, confirm the data storage request.

[0049] After obtaining permission to write data, the second server 11 can write the data to be monitored into the target consortium blockchain 12. That is, the second server 11 executes S150: if the first server confirms the data storage request, it stores the data to be monitored into the target consortium blockchain.

[0050] In the exemplary embodiments, reference continues to be made to... Figure 1 Once the regulatory data is uploaded to the blockchain, the first server 10 can read the data to be regulated, that is, the first server 10 executes step S160: obtain the data to be regulated.

[0051] For example, after obtaining the data to be regulated, the first server 10 can analyze and process the data corresponding to different internet consumer finance companies according to the smart contract. The analysis and processing may include drill-down processing, roll-up processing, etc., which are not limited in this embodiment.

[0052] After analyzing and processing the regulatory data, the credit ratings of different internet consumer finance companies are determined. These credit ratings may include risk level, compliance level, etc., but this embodiment does not specify any limitations.

[0053] For example, different internet consumer finance companies can have different identity identifiers. The first server 10 can then analyze and process the regulatory data containing the target identity identifiers through the smart contract in the target consortium blockchain 12. The identity identifier can be a string or other form.

[0054] For example, suppose the identity identifier of internet consumer finance company A is FH789, and the identity identifier of internet consumer finance company B is BN653. Internet consumer finance company A stores the data to be regulated in the target consortium blockchain 12 through the second server 11', and internet consumer finance company B stores the data to be regulated in the target consortium blockchain 12 through the second server 11".

[0055] The first server 10 analyzes and processes the regulatory data of the target identity identifier FH789 through the smart contract in the target consortium chain 12, that is, it analyzes and processes the regulatory data of the aforementioned Internet consumer finance company A and obtains the company's credit rating.

[0056] The first server 10 analyzes and processes the regulatory data of the target identity BN653 through the smart contract in the target consortium chain 12, that is, it analyzes and processes the regulatory data of the aforementioned internet consumer finance company B and obtains the company's credit rating.

[0057] It should be noted that the above-mentioned identity identifiers are merely examples. This embodiment does not limit the form and content of the identity identifiers, as long as they can identify and distinguish different Internet consumer finance companies.

[0058] In the exemplary embodiments, reference continues to be made to... Figure 1 After obtaining the data to be regulated, the first server 10 can also classify the data in real time using a classification model to determine its category. That is, the first server 10 executes S170: classifying the data to be regulated using a classification model to obtain its category.

[0059] The categories of data to be regulated can include normal data and abnormal data. If the data to be regulated is classified as normal data, it means that there is no risk of fraud; if the data to be regulated is classified as abnormal data, it means that there is a risk of fraud.

[0060] For example, the classification model described above can be obtained by training a machine learning model using ensemble learning. The samples used during training can be labeled historical regulatory data.

[0061] Machine learning is the science of developing algorithms and statistical models. Computer systems use machine learning algorithms to automatically analyze large amounts of behavioral data and derive patterns from them. This allows computer systems to output more accurate results based on given input datasets, thereby achieving purposes such as data prediction, classification, and clustering.

[0062] Traditional machine learning algorithms (such as decision trees, artificial neural networks, support vector machines, and Naive Bayes) aim to train a superior classifier. The basic idea of ​​ensemble learning is to combine multiple classifiers to achieve a single, better classifier. Ensemble learning can be categorized into types such as bagging (reducing variance), boosting (improving bias), and stacking (enhancing predictions).

[0063] The classification model described above can be a binary classification model. The algorithms used to train the classifier can include K-Nearest Neighbors Algorithm (KNN), Logistic Regression, Decision Trees, Support Vector Machines, and Naive Bayes, etc. This embodiment does not limit the training method or type of classifier. After training multiple (or a group of) classifiers, these classifiers are combined through ensemble learning to obtain the classification model.

[0064] When labeling the aforementioned historical regulatory data, the historical regulatory data can be categorized into normal data and abnormal data, with normal data labeled as "1" and abnormal data labeled as "0".

[0065] It should be noted that the labels for normal and abnormal data mentioned above are merely examples and are not intended to limit the scope of this embodiment.

[0066] In the exemplary embodiments, reference continues to be made to... Figure 1 After the first server 10 inputs the data to be monitored into the above classification model, it can determine whether the data to be monitored is normal data or abnormal data.

[0067] In an exemplary embodiment, when the category of the data to be regulated is normal data, the classification model can learn online based on the data to be regulated, thereby updating the parameters in the model and improving the accuracy of the model when classifying.

[0068] Online learning is a training method for deep learning models. It can update the model online using online data, adjust model parameters based on real-time data, and capture data changes in a timely manner, thereby increasing the model update frequency.

[0069] In an exemplary embodiment, when the category of the data to be monitored is abnormal data, the first server 10 may execute S180: determine that the data to be monitored is target data, and generate warning information about the target data.

[0070] In other words, if the data to be regulated is classified as abnormal, it will be treated as target data by the first server 10, which will then generate corresponding warning information. Upon receiving this warning information, the regulatory agency can then take targeted action on the target data.

[0071] In the embodiments described in this specification, a classification model for detecting anomalies in regulated data is trained based on historical data awaiting regulation. This model can classify the regulated data obtained from the target consortium blockchain and generate early warning information for anomalies. This improves the accuracy and authority of the regulated data processing process, reduces fraud during regulatory reporting, lowers the systemic financial risk of internet consumer finance companies, and enhances their compliance level.

[0072] refer to Figure 2 The flowchart shown illustrates the process of processing the target data.

[0073] S210, Obtain the labeled target data, wherein the labeled target data is obtained by labeling the target data according to the category of the target data.

[0074] In an exemplary embodiment, after receiving the warning information for the target data, the regulatory agency can further determine whether the output result of the classification model is correct, and re-label the target data manually to obtain the labeled target data.

[0075] For example, if a regulatory agency determines, through manual judgment, that the actual category of the target data is anomalous data, it means that the output of the classification model is correct, and the target data is labeled as anomalous data, for example, with the label "0".

[0076] If, after manual evaluation, the regulatory agency determines that the actual category of the target data is normal data, it means that the output of the classification model is incorrect. In this case, the regulatory agency will label the target data as normal data, for example, label it as "1".

[0077] For example, after the regulatory agency labels the target data, the first server 10 obtains the labeled target data.

[0078] S220: When the labeled target data is classified as anomalous data, the labeled target data is input into the classification model so that the classification model can perform adversarial learning based on the labeled target data.

[0079] In an exemplary embodiment, if the labeled target data is classified as anomalous data, the first server 10 can use the data to enable the classification model to perform adversarial training.

[0080] Adversarial learning typically uses data with perturbation as adversarial examples (adversarial data) and trains the model using these adversarial examples to enhance the model's robustness and accuracy.

[0081] Therefore, some distracting content (e.g., content unrelated to the data to be monitored) can be added to the labeled target data, or the target data can be deliberately labeled as normal data, and so on. This embodiment does not limit the method of adversarial learning for the classification model.

[0082] S230, if the category of the labeled target data is normal data, the labeled target data is input into the classification model so that the classification model can learn online based on the labeled target data.

[0083] In an exemplary embodiment, if the labeled target data is classified as normal data, the first server 10 can use the data to enable the classification model to perform online learning.

[0084] In the embodiments of this specification, when the target data is classified as anomalous data, the regulatory agency can judge the results and label the target data: if the actual category of the target data is anomalous data, it is labeled, and the classification model performs adversarial learning based on the labeled anomalous data to improve the classification model's ability to classify anomalous data; if the actual category of the target data is normal data, it is labeled, and the classification model performs online learning based on the labeled normal data and updates the model parameters to improve the accuracy of the classification model.

[0085] refer to Figure 3The diagram illustrates a scenario of the data processing method. The following is a summary of the above embodiments.

[0086] In an exemplary embodiment, such as Figure 3 As shown. In general, internet consumer finance companies (e.g., internet consumer finance company A, internet consumer finance company B) store the regulatory data generated in financing, lending and other transactions in real time to the target consortium blockchain 12 through the second server 11 (e.g., second server 11', second server 11")

[0087] The first server 10 (corresponding to the regulatory agency) can analyze and process the data to be regulated in the target consortium blockchain 12 through its processing module to determine the relevant risks and compliance levels of financial companies. Furthermore, the first server 10 can train a classification model using historical regulatory data to classify the data to be regulated in real time, thereby determining whether the data to be regulated is normal or abnormal.

[0088] In the event that the data to be monitored is abnormal, an early warning message can be generated through the first server 10, so that the regulatory agency can process the abnormal data in a timely manner.

[0089] The data processing method provided in the embodiments of this specification uses blockchain to implement the regulatory reporting process, which enhances the timeliness of regulatory reporting and the authority of the data to be regulated, thereby significantly improving the effectiveness and timeliness of financial regulation.

[0090] Furthermore, by combining machine learning methods such as ensemble learning, adversarial learning, and online learning to train and optimize classification models, it is possible to effectively classify data to be regulated, thereby reducing the problem of inadequate supervision caused by fraudulent or erroneous data in the data to be regulated, further improving the effectiveness of existing supervision, and reducing the financial systemic risks of internet consumer finance companies.

[0091] The following are embodiments of the apparatus described in this specification, which can be used to execute the embodiments of the methods described in this specification. For details not disclosed in the apparatus embodiments of this specification, please refer to the embodiments of the methods described in this specification.

[0092] in, Figure 4 A structural diagram of a data processing apparatus provided according to an exemplary embodiment of this specification is shown, the apparatus being configured on a first server.

[0093] The data processing device 400 in the embodiments of this specification includes: an establishment module 401, a receiving module 402, a confirmation module 403, a classification module 404, and a generation module 405, wherein:

[0094] Establish module 401, used for: establishing the target consortium chain.

[0095] The receiving module 402 is used to: receive data storage requests from the second server and authenticate the second server.

[0096] The confirmation module 403 is used to: confirm the data storage request if the second server is authenticated, so that the second server stores the data to be regulated in the target consortium blockchain.

[0097] The classification module 404 is used to classify the data to be regulated stored in the target consortium blockchain through a classification model to obtain the category of the data to be regulated. The data to be regulated includes one or more of transaction data, financial data and credit data, and the category includes abnormal data and normal data.

[0098] The generation module 405 is used to: determine the data to be monitored as target data when the category of the data to be monitored is abnormal data, and generate early warning information about the target data.

[0099] in, Figure 5 A structural diagram of a data processing apparatus provided according to another exemplary embodiment of this specification is shown.

[0100] Optionally, the above device further includes: a second acquisition module 406 and an input module 407.

[0101] The second acquisition module 406 is used to: acquire labeled target data, wherein the labeled target data is obtained by labeling the target data according to the category of the target data; the input module 407 is used to: input the labeled target data into the classification model when the category of the labeled target data is abnormal data, so that the classification model can perform adversarial learning based on the labeled target data; and input the labeled target data into the classification model when the category of the labeled target data is normal data, so that the classification model can perform online learning based on the labeled target data.

[0102] In one possible implementation, the input module 407 is specifically used to: add interfering content to the labeled target data to obtain adversarial data; and input the adversarial data into the classification model so that the classification model can perform adversarial learning based on the adversarial data.

[0103] Optionally, the above apparatus further includes an update module 408. The update module 408 is used to update the parameters in the classification model by performing online learning based on the data to be regulated when the category of the data to be regulated is normal data.

[0104] In an exemplary embodiment, based on the foregoing scheme, the data to be regulated stored in the target consortium blockchain includes an identity identifier.

[0105] Optionally, the above apparatus further includes: an analysis and processing module 409 and a determination module 410. The analysis and processing module 409 is used to: analyze and process the data to be regulated containing the target identity identifier through a smart contract in the target consortium blockchain, wherein the analysis and processing includes down-processing and / or up-processing; the determination module 410 is used to: determine the credit rating of the target identity identifier based on the results of the analysis and processing.

[0106] Optionally, the above apparatus further includes a training module 411. The training module 411 is used to train a machine learning model using labeled historical regulatory data to obtain a classification model.

[0107] In one possible implementation, the training module 411 is specifically used to: train a machine learning model based on labeled historical regulatory data through ensemble learning to obtain a classification model.

[0108] It should be noted that the data processing apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when executing the data processing method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the data processing apparatus and data processing method embodiments provided in the above embodiments belong to the same concept. Therefore, for details not disclosed in the apparatus embodiments of this specification, please refer to the embodiments of the training method of the target word detection model described above in this specification, which will not be repeated here.

[0109] in, Figure 6 A structural diagram of a data processing apparatus provided according to another exemplary embodiment of this specification is shown, the apparatus being configured on a second server.

[0110] The data processing device 600 in the embodiments of this specification includes: an acquisition module 610, a transmission module 620, and a storage module 630.

[0111] The acquisition module 610 is used to: acquire data to be regulated, wherein the data to be regulated includes one or more of transaction data, financial data and credit data.

[0112] The sending module 620 is used to: send a data storage request to the first server so that the first server can authenticate the second server, and confirm the data storage request if the second server is successfully authenticated.

[0113] The storage module 630 is configured to: upon confirmation of a data storage request by the first server, store the data to be monitored in the target consortium blockchain, so that the first server classifies the data to be monitored in the target consortium blockchain using a classification model to obtain the category of the data to be monitored, wherein the category includes abnormal data and normal data; and, if the category of the data to be monitored is abnormal data, determine that the data to be monitored is target data and generate early warning information about the target data.

[0114] It should be noted that the data processing apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when executing the data processing method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the data processing apparatus and data processing method embodiments provided in the above embodiments belong to the same concept. Therefore, for details not disclosed in the apparatus embodiments of this specification, please refer to the above data processing method embodiments of this specification, which will not be repeated here.

[0115] The example numbers in this specification are for descriptive purposes only and do not represent the superiority or inferiority of the examples.

[0116] This specification also provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the methods described above.

[0117] Figure 7 This schematically illustrates a structural diagram of a terminal according to an exemplary embodiment of this specification. Please refer to... Figure 7 As shown, terminal 700 includes a processor 701 and a memory 702.

[0118] In this embodiment, processor 701 is the control center of the computer system and can be a processor of a physical machine or a processor of a virtual machine. Processor 701 may include one or more processing cores, such as a 4-core processor or an 8-core processor. Processor 701 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 701 may also include a main processor and coprocessors. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0119] In the embodiments described in this specification, the processor 701 is specifically used for:

[0120] Establish a target consortium blockchain; receive a data storage request from a second server and authenticate the second server; if the second server is authenticated, confirm the data storage request so that the second server stores the data to be regulated in the target consortium blockchain; classify the data to be regulated stored in the target consortium blockchain using a classification model to obtain the category of the data to be regulated, wherein the data to be regulated includes one or more of transaction data, financial data, and credit data, and the category includes abnormal data and normal data; if the category of the data to be regulated is abnormal data, determine the data to be regulated as target data and generate early warning information about the target data.

[0121] Furthermore, in one embodiment of this specification, when the category of the data to be monitored is abnormal data, the processor 701 is further configured to: obtain labeled target data, wherein the labeled target data is obtained by labeling the target data according to the category of the target data; when the category of the labeled target data is abnormal data, input the labeled target data into the classification model so that the classification model performs adversarial learning based on the labeled target data; when the category of the labeled target data is normal data, input the labeled target data into the classification model so that the classification model performs online learning based on the labeled target data.

[0122] Optionally, the processor 701 is specifically used to: add interfering content to the labeled target data to obtain adversarial data; and input the adversarial data into the classification model so that the classification model can perform adversarial learning based on the adversarial data.

[0123] Optionally, the processor 701 is further configured to: when the category of the data to be regulated is normal data, perform online learning based on the data to be regulated through the classification model to update the parameters in the classification model.

[0124] In an exemplary embodiment, based on the foregoing scheme, the data to be regulated stored in the aforementioned target consortium blockchain includes an identity identifier.

[0125] Optionally, the processor 701 is further configured to: analyze and process the data to be regulated containing the target identity identifier through the smart contract in the target consortium blockchain, wherein the analysis and processing includes down-processing and / or up-processing; and determine the credit rating of the target identity identifier based on the results of the analysis and processing.

[0126] Optionally, the processor 701 is further configured to: train a machine learning model using labeled historical regulatory data to obtain the classification model; the above-mentioned training of the machine learning model using labeled historical regulatory data to obtain the classification model includes: training the machine learning model based on the labeled historical regulatory data using ensemble learning to obtain the classification model.

[0127] In the embodiments described in this specification, the processor 701 is specifically used for:

[0128] The process involves: acquiring data to be regulated, including one or more of transaction data, financial data, and credit data; sending a data storage request to a first server to authenticate the second server, and confirming the data storage request upon successful authentication by the second server; storing the data to be regulated in a target consortium blockchain upon confirmation by the first server, allowing the first server to classify the data to be regulated in the target consortium blockchain using a classification model to obtain categories of the data to be regulated, including abnormal data and normal data; and determining the data to be regulated as target data if the category of the data to be regulated is abnormal data, and generating a warning message regarding the target data.

[0129] Memory 702 may include one or more computer-readable storage media, which may be non-transitory. Memory 702 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage terminals or flash memory terminals. In some embodiments of this specification, the non-transitory computer-readable storage media in memory 702 is used to store at least one instruction, which is executed by processor 701 to implement the methods in the embodiments of this specification.

[0130] In some embodiments, terminal 700 further includes a peripheral terminal interface 703 and at least one peripheral terminal. The processor 701, memory 702, and peripheral terminal interface 703 can be connected via a bus or signal line. Each peripheral terminal can be connected to peripheral terminal interface 703 via a bus, signal line, or circuit board. Specifically, the peripheral terminal includes at least one of a display screen 704, a camera 705, and an audio circuit 706.

[0131] The peripheral terminal interface 703 can be used to connect at least one input / output (I / O) related peripheral terminal to the processor 701 and the memory 702. In some embodiments of this specification, the processor 701, memory 702, and peripheral terminal interface 703 are integrated on the same chip or circuit board; in some other embodiments of this specification, any one or two of the processor 701, memory 702, and peripheral terminal interface 703 can be implemented on separate chips or circuit boards. This specification does not specifically limit the embodiments in this regard.

[0132] Display screen 704 is used to display a user interface (UI). The UI may include graphics, text, icons, videos, and any combination thereof. When display screen 704 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 701 for processing. In this case, display screen 704 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments of this specification, there may be one display screen 704, which is used as the front panel of terminal 700; in other embodiments, there may be at least two display screens 704, respectively disposed on different surfaces of terminal 700 or in a folded design; in still other embodiments, display screen 704 may be a flexible display screen, disposed on a curved or folded surface of terminal 700. Furthermore, display screen 704 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 704 may be made of materials such as Liquid Crystal Display (LCD) or Organic Light-Emitting Diode (OLED).

[0133] Camera 705 is used to capture images or videos. Optionally, camera 705 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, virtual reality (VR) shooting, or other fusion shooting functions. In some embodiments of this specification, camera 705 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cool light flash, which can be used for light compensation at different color temperatures.

[0134] The audio circuit 706 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals that are input to the processor 701 for processing. For stereo sound acquisition or noise reduction purposes, there may be multiple microphones, each located at a different part of the terminal 700. The microphone may also be an array microphone or an omnidirectional microphone.

[0135] Power supply 707 is used to power the various components in terminal 700. Power supply 707 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 707 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0136] The terminal structure block diagrams shown in the embodiments of this specification do not constitute a limitation on the terminal 700. The terminal 700 may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0137] In this specification, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or order; the term "multiple" refers to two or more unless otherwise expressly defined. The terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; "linking" can be a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this specification according to the specific circumstances.

[0138] In the description of this specification, it should be understood that the terms "upper" and "lower" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this specification and simplifying the description, and do not indicate or imply that the device or unit referred to must have a specific orientation or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this specification.

[0139] This specification also provides a computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform one or more steps in the above embodiments. If the constituent modules of the above data processing apparatus are implemented as software functional units and sold or used as independent products, they can be stored in the above-described computer-readable storage medium.

[0140] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The aforementioned available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)).

[0141] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0142] The above description is merely a specific embodiment of this specification, but the scope of protection of this specification is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this specification should be included within the scope of protection of this specification. Therefore, equivalent variations made in accordance with the claims of this specification are still within the scope of this specification.

Claims

1. A data processing method, characterized by, The method is applied to a first server and comprises the following steps: establishing a target consortium chain; receiving a data storage request of a second server and authenticating the second server; confirming the data storage request if the second server is authenticated, so that the second server stores to-be-regulated data into the target consortium chain; classifying to-be-regulated data stored into the target consortium chain by a classification model to obtain a category of the to-be-regulated data, wherein the to-be-regulated data comprises one or more of transaction data, financial data and credit data, and the category comprises abnormal data and normal data; determining the to-be-regulated data as target data and generating early warning information about the target data if the category of the to-be-regulated data is abnormal data. In the case where the category of the to-be-regulated data is abnormal data, the method further comprises the following steps: obtaining labeled target data, wherein the labeled target data is obtained by labeling the target data according to the category of the target data; inputting the labeled target data into the classification model to enable the classification model to perform adversarial learning according to the labeled target data if the category of the labeled target data is abnormal data; inputting the labeled target data into the classification model to enable the classification model to perform online learning according to the labeled target data if the category of the labeled target data is normal data.

2. The data processing method according to claim 1, characterized in that, The inputting of the labeled target data into the classification model to enable the classification model to perform adversarial learning according to the labeled target data comprises the following steps: adding interference content to the labeled target data to obtain adversarial data; inputting the adversarial data into the classification model to enable the classification model to perform adversarial learning according to the adversarial data.

3. The data processing method according to any one of claims 1 to 2, characterized in that, The method further comprises the following steps: performing online learning on the to-be-regulated data by the classification model to update parameters in the classification model if the category of the to-be-regulated data is normal data.

4. The data processing method according to any one of claims 1 to 2, characterized in that, The to-be-regulated data stored in the target consortium chain contains an identity; the method further comprises the following steps: analyzing and processing to-be-regulated data containing a target identity by a smart contract in the target consortium chain, wherein the analysis and processing comprises down-drilling processing and / or up-rolling processing; determining a credit level about the target identity according to a result of the analysis and processing.

5. The data processing method according to any one of claims 1 to 2, characterized in that, The method further comprises the following steps: training a machine learning model by labeled historical regulated data to obtain the classification model; The training of the machine learning model by the labeled historical regulated data to obtain the classification model comprises the following steps: training the machine learning model by the labeled historical regulated data in an integrated learning manner to obtain the classification model.

6. A data processing method, characterized by, The method is applied to a second server and comprises the following steps: obtaining to-be-regulated data, wherein the to-be-regulated data comprises one or more of transaction data, financial data and credit data; sending a data storage request to a first server to cause the first server to authenticate the second server and confirm the data storage request if the second server is authenticated; storing the to-be-regulated data to a target consortium chain if the first server confirms the data storage request, to cause the first server to classify the to-be-regulated data stored in the target consortium chain by a classification model to obtain a category of the to-be-regulated data, wherein the category includes abnormal data and normal data, and to cause the first server to determine the to-be-regulated data as target data and generate early warning information about the target data if the category of the to-be-regulated data is abnormal data; wherein, if the category of the to-be-regulated data is abnormal data, the method further comprises: obtaining labeled target data, wherein the labeled target data is obtained by labeling the target data according to the category of the target data; inputting the labeled target data into the classification model to cause the classification model to perform adversarial learning according to the labeled target data if the category of the labeled target data is abnormal data; inputting the labeled target data into the classification model to cause the classification model to perform online learning according to the labeled target data if the category of the labeled target data is normal data.

7. A data processing apparatus, characterized by, configured on a first server, comprising: a establishing module configured to establish a target consortium chain; a receiving module configured to receive a data storage request of a second server and authenticate the second server; a confirming module configured to confirm the data storage request if the second server is authenticated, to cause the second server to store to-be-regulated data to the target consortium chain; a classification module configured to classify the to-be-regulated data stored in the target consortium chain by a classification model to obtain a category of the to-be-regulated data, wherein the to-be-regulated data includes one or more of transaction data, financial data, and credit data, and the category includes abnormal data and normal data; a generating module configured to determine the to-be-regulated data as target data and generate early warning information about the target data if the category of the to-be-regulated data is abnormal data; the device further comprises a second obtaining module and an input module; the second obtaining module is configured to obtain labeled target data, wherein the labeled target data is obtained by labeling the target data according to the category of the target data; the input module is configured to input the labeled target data into the classification model to cause the classification model to perform adversarial learning according to the labeled target data if the category of the labeled target data is abnormal data, and to input the labeled target data into the classification model to cause the classification model to perform online learning according to the labeled target data if the category of the labeled target data is normal data.

8. A data processing apparatus, characterized by configured on a second server, comprising: An acquisition module is configured to acquire to-be-regulated data, wherein the to-be-regulated data comprises one or more of transaction data, financial data, and credit data; A sending module is configured to send a data storage request to a first server, so that the first server authenticates the second server, and confirms the data storage request if the second server is authenticated; A storage module is configured to store the to-be-regulated data to a target consortium chain if the first server confirms the data storage request, so that the first server classifies the to-be-regulated data stored in the target consortium chain through a classification model to obtain a category of the to-be-regulated data, wherein the category comprises abnormal data and normal data; and so that the first server determines the to-be-regulated data as target data and generates early warning information about the target data if the category of the to-be-regulated data is abnormal data. In the case where the category of the to-be-regulated data is abnormal data, the method further comprises: acquiring labeled target data, wherein the labeled target data is obtained by labeling the target data according to the category of the target data; in the case where the category of the labeled target data is abnormal data, inputting the labeled target data into the classification model, so that the classification model performs adversarial learning according to the labeled target data; in the case where the category of the labeled target data is normal data, inputting the labeled target data into the classification model, so that the classification model performs online learning according to the labeled target data.

9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the data processing method of any one of claims 1 to 5, and implement the data processing method of claim 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the data processing method of any one of claims 1 to 5, and implement the data processing method of claim 6.

11. A computer program product comprising instructions which, when the computer program product is run on a computer or processor, cause the computer or processor to carry out the data processing method of any one of claims 1 to 5, and implement the data processing method of claim 6.

Images