CN118037301A - Method, device and equipment for supervising public account and readable storage medium - Google Patents
Method, device and equipment for supervising public account and readable storage medium Download PDFInfo
- Publication number
- CN118037301A CN118037301A CN202410209256.7A CN202410209256A CN118037301A CN 118037301 A CN118037301 A CN 118037301A CN 202410209256 A CN202410209256 A CN 202410209256A CN 118037301 A CN118037301 A CN 118037301A
- Authority
- CN
- China
- Prior art keywords
- transaction
- account
- supervision
- transaction amount
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 49
- 238000012549 training Methods 0.000 claims description 57
- 230000002159 abnormal effect Effects 0.000 claims description 19
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Life Sciences & Earth Sciences (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses a method, a device and equipment for supervising a public account and a readable storage medium, which can be applied to the financial field or other fields. And acquiring transaction flow information corresponding to the electronic protocol to be supervised of the target account, and taking the transaction flow information as historical transaction flow information. And inputting the transaction flow information into a pre-trained first supervision model to obtain the transaction range of the single transaction amount output by the first supervision model. And acquiring real-time account moving information corresponding to the electronic agreement to be supervised of the target account, wherein the real-time account moving information comprises real-time values of single transaction amount. And comparing the real-time value of the single transaction amount with the transaction range to obtain a supervision result. Therefore, according to the historical transaction flow information of the target account, the application predicts the transaction range of the single transaction amount of the target account by utilizing the convolutional neural network model, and determines the supervision result by comparing the real-time value of the single transaction amount with the transaction range, thereby improving the supervision efficiency and the accuracy of the supervision result.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a device, and a readable storage medium for supervising a public account.
Background
At present, the bank supervision platform establishes an electronic protocol number, and when a supervision account is opened, all the associated supervision accounts are connected through the electronic protocol number (year, month, day and business rule), so that the inquiry is convenient. The public account can be associated with a plurality of electronic protocol numbers, each electronic protocol number corresponds to a type of transaction type, and generally, when the public account is regulated, funds are regulated through rules corresponding to the associated electronic protocol numbers, but the regulation efficiency and the regulation accuracy are lower.
Disclosure of Invention
The application provides a method, a device, equipment and a readable storage medium for supervising a public account, which are as follows:
a method for supervising a public account is applied to a private chain corresponding to a target account, and comprises the following steps:
the method comprises the steps of obtaining transaction flow information corresponding to an electronic protocol to be supervised of a target account as historical transaction flow information, wherein the target account is any public account, and the transaction flow information at least comprises a historical value of a single transaction amount;
Inputting the transaction flow information into a pre-trained first supervision model to obtain a transaction range of a single transaction amount output by the first supervision model; the first supervision model comprises a convolutional neural network model which is obtained by training based on transaction flow sample data taking a historical transaction range of a single transaction amount as a label in advance, wherein the transaction flow sample data comprises transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts;
acquiring real-time account moving information corresponding to an electronic protocol to be supervised of the target account, wherein the real-time account moving information comprises a real-time value of a single transaction amount;
comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result;
and obtaining a supervision result at least based on the first comparison result.
Optionally, the training process of the first supervision model includes:
clustering candidate historical accounts to obtain a plurality of account classes, wherein the candidate historical accounts are historical accounts signed with the electronic protocol to be supervised;
classifying the target account to obtain an account class to which the target account belongs as a target account class;
taking the candidate historical account belonging to the target account class as a sample account;
acquiring transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts as transaction flow sample data;
Based on normal distribution, acquiring a historical transaction range of a single transaction amount in the transaction flow sample data;
marking the transaction flow sample data by taking the historical transaction range of the single transaction amount as a first label;
Training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the first label as target output;
And when a preset training completion condition is reached, obtaining a trained convolutional neural network model as the first supervision model, wherein the training completion condition comprises that the iteration number is larger than a preset maximum number threshold.
Optionally, obtaining a supervision result based at least on the first comparison result includes:
if the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, a preset first early warning instruction is generated, and the first early warning instruction is used for indicating that the single transaction of the target account is abnormal.
Optionally, the transaction flow information further includes a historical value of a daily transaction amount and a transaction date, the real-time dynamic account information further includes a real-time value of the daily transaction amount, and the method further includes:
Inputting the transaction flow information into a pre-trained second supervision model to obtain a transaction range of daily transaction amount output by the second supervision model, wherein the second supervision model comprises a convolutional neural network model which is obtained by training transaction flow sample data based on the historical transaction range of daily transaction amount as a label in advance;
And comparing the real-time value of the daily transaction amount with the transaction range to obtain a second comparison result.
Optionally, obtaining a supervision result at least based on the first comparison result, further includes:
if the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, generating a preset second early warning instruction, wherein the second early warning instruction is used for indicating that the daily transaction amount of the target account is abnormal;
If the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, and the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, a preset third early warning instruction is generated, and the third early warning instruction is used for indicating abnormal transaction of the target account.
Optionally, the training process of the second supervision model comprises:
Based on normal distribution, acquiring a historical transaction range of daily transaction amount in the transaction flow sample data;
Marking the transaction flow water sample data by taking the historical transaction range of the daily transaction amount as a second label;
Training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the second label as target output;
and when the training completion condition is reached, obtaining a trained convolutional neural network model as the second supervision model.
The utility model provides a supervision device to public account, includes each private chain that corresponds to public account, and wherein, the private chain that the target account corresponds includes:
The transaction flow obtaining unit is used for obtaining transaction flow information corresponding to an electronic protocol to be supervised of a target account as historical transaction flow information, wherein the target account is any one public account, and the transaction flow information at least comprises a historical value of a single transaction amount;
The single transaction prediction unit is used for inputting the transaction flow information into a pre-trained first supervision model to obtain a transaction range of a single transaction amount output by the first supervision model; the first supervision model comprises a convolutional neural network model which is obtained by training based on transaction flow sample data taking a historical transaction range of a single transaction amount as a label in advance, wherein the transaction flow sample data comprises transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts;
The system comprises a dynamic account information acquisition unit, a dynamic account management unit and a dynamic account management unit, wherein the dynamic account information acquisition unit is used for acquiring real-time dynamic account information corresponding to an electronic protocol to be supervised of the target account, and the real-time dynamic account information comprises real-time values of single transaction amount;
the first comparison unit is used for comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result;
And the supervision result acquisition unit is used for acquiring a supervision result at least based on the first comparison result.
Optionally, the apparatus further comprises a model building unit for:
clustering candidate historical accounts to obtain a plurality of account classes, wherein the candidate historical accounts are historical accounts signed with the electronic protocol to be supervised;
classifying the target account to obtain an account class to which the target account belongs as a target account class;
taking the candidate historical account belonging to the target account class as a sample account;
acquiring transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts as transaction flow sample data;
Based on normal distribution, acquiring a historical transaction range of a single transaction amount in the transaction flow sample data;
marking the transaction flow sample data by taking the historical transaction range of the single transaction amount as a first label;
Training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the first label as target output;
And when a preset training completion condition is reached, obtaining a trained convolutional neural network model as the first supervision model, wherein the training completion condition comprises that the iteration number is larger than a preset maximum number threshold.
A policing device for a public account, comprising: a memory and a processor;
the memory is used for storing programs;
the processor is used for executing the program to realize each step of the supervision method of the public account.
A readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a method of policing a public account.
According to the technical scheme, the method, the device, the equipment and the readable storage medium for supervising the public account acquire transaction flow information corresponding to the electronic protocol to be supervised of the target account, the transaction flow information is used as historical transaction flow information, the target account is any public account, and the transaction flow information at least comprises historical values of single transaction amount. And inputting the transaction flow information into a pre-trained first supervision model to obtain the transaction range of the single transaction amount output by the first supervision model. The first supervision model comprises a convolutional neural network model which is trained in advance based on transaction flow sample data which takes a historical transaction range of a single transaction amount as a label, and the transaction flow sample data comprises transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts. And acquiring real-time account moving information corresponding to the electronic agreement to be supervised of the target account, wherein the real-time account moving information comprises real-time values of single transaction amount. And comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result. And obtaining a supervision result based at least on the first comparison result. Therefore, according to the historical transaction flow information of the target account, the application predicts the transaction range of the single transaction amount of the target account by utilizing the convolutional neural network model, and determines the supervision result by comparing the real-time value of the single transaction amount with the transaction range, thereby improving the supervision efficiency and the accuracy of the supervision result.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a supervision system for public accounts according to an embodiment of the present application;
FIG. 2 is a flow chart of a specific method for model construction according to an embodiment of the present application;
fig. 3 is a flowchart of a specific method of a method for supervising a public account according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a supervision device for public accounts according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a supervision device for public accounts according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Fig. 1 is a schematic structural diagram of a supervision system for public accounts according to an embodiment of the present application, and as shown in fig. 1, the system includes private chains 10 corresponding to each pair of public accounts and a model building module 20.
In this embodiment, the model building module is configured to build the first supervision model and the second supervision model, and the specific method for building the first supervision model and the second supervision model by the model building module is described in the flow shown in fig. 2.
In this embodiment, a private chain of public accounts corresponds to a public account, and includes a public account module 101, an enterprise information module 102, an electronic agreement module 103, a fund supervision module 104, a prediction calculation module 105, and an early warning module 106.
The public account module 101 is used for storing basic information of a public account, limits of the public account (generally different product types, different single limits), account movement information and the like.
The enterprise information module 102 is configured to store enterprise information such as enterprise business license information, enterprise legal information, and the like of an enterprise for a public account. Specifically, basic information of the enterprise is recorded, including an operation range, a bank product code, an electronic agreement of the enterprise, account information of the enterprise, an operation permission time range of the enterprise, an operation address of the enterprise and the like. The information is mainly stored in an enterprise information table of the database.
The electronic agreement module 103 is configured to store an electronic agreement number registered for the public account number, specifically, record electronic agreements signed by all enterprises, and the information mainly includes an electronic agreement table of a database. The electronic agreement table records an electronic agreement number, an electronic agreement type, an electronic agreement signing time, an electronic agreement signing party, an electronic agreement validity period, a reference unit price agreed by the electronic agreement, and an actual price (the agreed actual price floats within a preset range of the signing agreement).
When an enterprise opens a public account, the submitted enterprise information includes a product code, and the signable electronic protocol type corresponding to the product code of the enterprise is in a defined range, and only the electronic protocol in the product code range can be selected for signing, for example: the electronic agreement of the time of lesson fees under the educational products records the reference unit price of lessons, or the electronic agreement of the dining fees records the reference unit price of dining fees, the electronic agreement of the receiving and delivering type service records the receiving and delivering reference unit price, etc. An account number of the enterprise must be selected for association when the enterprise signs up to manage the electronic agreement.
It should be noted that, an enterprise may have a plurality of electronic agreement numbers, where the product code is attribute information of the administrative account (e.g., the product code dedicated to the education institution and the product code dedicated to the real estate institution and the real estate property) and corresponds to the operating range one by one, and the electronic agreement number is in one-to-many relationship with the administrative account (typically, for public accounts, private accounts or private accounts may be used by the individual operator). If an enterprise is a education institution, the product code is education, and the contractable electronic agreement corresponds to the transaction type, and can be a school fee type, a material fee type, a meal fee type, a charge receiving type and the like.
The funds administration module 104 is used to store funds administration information for the public account, such as matching information with funds when drawing a class and refund clearing information.
The transaction flow water meter records transaction flow, which is a detailed record of transaction, and comprises an account name, an account number, a transaction direction (0 represents out and 1 represents in), transaction time (accurate to seconds, format such as yyyy-MM-dd HH: MM: ss), transaction opponent information (opponent account name, opponent account number and account state), transaction state (success/failure), a supervised enterprise product code, an electronic protocol number and a transaction type.
The prediction calculation module 105 is configured to implement a supervision procedure for the public account, and to supervise the transaction amount risk for the public account in real time, which can be specifically referred to the method shown in fig. 3.
In addition, the prediction calculation module is further used for analyzing the commonly used transaction types through transaction flow and single transaction amount, such as: 100-5000 yuan for an individual account is education expenses, and 10-500 tens of thousands for a property-like transaction (the transaction type is a subset of product codes, for example, the product codes are education, and the transaction type may be academic or educational appliance expenses). It should be noted that, for the public client manager to manage and maintain the electronic protocol, if the account dynamic account information corresponding to the electronic protocol is found to be abnormal, the account associated with the electronic protocol can be changed if necessary by artificial checking, and the changed account is taken as the supervision account.
The early warning module 106 is configured to send out early warning based on the analysis result of the prediction calculation module, so as to remind each product service responsible person or manager of fund supervision.
Fig. 2 is a flow chart of a model building method according to an embodiment of the present application, where the method may be applied to the model building module in the foregoing embodiment, and as shown in fig. 2, the method specifically includes:
s201, clustering the candidate historical accounts to obtain a plurality of account classes.
In this embodiment, the candidate history account is a history account signed with an electronic protocol to be monitored.
Alternatively, the candidate historical accounts may be clustered based on the basic information of the candidate historical accounts, where the obtaining of the basic information and the clustering method may refer to the prior art, and it may be understood that, in the account class obtained in this step, the attributes of the accounts belonging to the same account class are similar.
S202, classifying the target account to obtain an account class to which the target account belongs as a target account class.
S203, taking the candidate historical account belonging to the target account class as a sample account.
S204, transaction flow information corresponding to the electronic protocol to be supervised of the plurality of sample accounts is obtained and used as transaction flow sample data.
S205, based on normal distribution, acquiring a historical transaction range of a single transaction amount in transaction flow sample data.
S206, marking the transaction flow sample data by taking the historical transaction range of the single transaction amount as a first label.
S207, training a pre-constructed convolutional neural network model by taking transaction flow sample data as input and taking a first label as target output.
And S208, when a preset training completion condition is reached, obtaining a trained convolutional neural network model as a first supervision model, wherein the training completion condition comprises that the iteration number is greater than a preset maximum number threshold.
S209, based on normal distribution, acquiring a historical transaction range of daily transaction amount in transaction flow sample data.
S210, marking transaction flow sample data by taking a historical transaction range of daily transaction amount as a second label.
S211, training a pre-constructed convolutional neural network model by taking transaction flow water sample data as input and taking a second label as target output.
And S212, when the training completion condition is reached, obtaining a trained convolutional neural network model as a second supervision model.
According to the method for supervising the public account, which is provided by the embodiment of the application, the candidate historical account belonging to the target account is taken as the sample account, wherein the target account is the account belonging to the target account, namely, the method takes the historical account which is the same as the target account as the sample account, so that the accuracy of training samples is improved, the transaction flow sample data is respectively taken as input and output by taking the first label as the target, the pre-built convolutional neural network model is trained, the transaction flow sample data is taken as input, and the second label is taken as the target to output, the pre-built convolutional neural network model is trained, and the first supervising model and the second supervising model are obtained, wherein the first supervising model is used for outputting the transaction range of a single transaction amount after the transaction flow data is input, and the first supervising model is used for outputting the transaction range of daily transaction amount after the transaction flow data is input.
Fig. 3 is a flow chart of a method for supervising a public account according to an embodiment of the present application, as shown in fig. 3, the method specifically includes:
S301, transaction flow information corresponding to an electronic protocol to be supervised of a target account is obtained and used as historical transaction flow information.
In this embodiment, the target account is any one of the public accounts, and the transaction flow information includes a history value of a single transaction amount, a history value of a daily transaction amount, and a transaction date.
S302, inputting transaction flow information into a pre-trained first supervision model to obtain a transaction range of a single transaction amount output by the first supervision model.
In this embodiment, the first supervision model includes a convolutional neural network model trained in advance based on transaction flow sample data with a historical transaction range of a single transaction amount as a label, where the transaction flow sample data includes transaction flow information corresponding to electronic protocols to be supervised of multiple sample accounts.
S303, inputting transaction flow information into a pre-trained second supervision model to obtain a transaction range of daily transaction amount output by the second supervision model.
In this embodiment, the second supervision model includes a convolutional neural network model trained in advance based on transaction flow sample data tagged with a historical transaction range of daily transactions.
S304, acquiring real-time account moving information corresponding to the electronic protocol to be supervised of the target account.
In this embodiment, the real-time accounting information includes a real-time value of a single transaction amount and a real-time value of a daily transaction amount.
S305, comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result.
S306, comparing the real-time value of the daily transaction amount with the transaction range to obtain a second comparison result.
S307, if the real-time value of the single transaction amount indicated by the first comparison result exceeds the transaction range of the single transaction amount, a preset first early warning instruction is generated.
In this embodiment, the first early warning instruction is used to indicate that the single transaction of the target account is abnormal.
And S308, if the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, generating a preset second early warning instruction.
In this embodiment, the second early warning instruction is used to indicate that the daily transaction amount of the target account is abnormal.
S309, if the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, and the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, generating a preset third early warning instruction.
In this embodiment, the third early warning instruction is used to indicate that the transaction of the target account is abnormal.
According to the technical scheme, the method for supervising the public account, provided by the embodiment of the application, has the advantages that the transaction flow information is input into the first supervising model trained in advance, so that the transaction range of the single transaction amount output by the first supervising model is obtained. And acquiring a real-time value of the single transaction amount through the real-time account information, and comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result. Therefore, according to the historical transaction flow information of the target account, the application predicts the transaction range of the single transaction amount of the target account by utilizing the convolutional neural network model, and improves the real-time supervision efficiency of the single transaction amount by comparing the real-time value of the single transaction amount with the transaction range. Further, the supervision result of the target account is determined through the first comparison result, so that supervision efficiency and accuracy of the supervision result are improved.
And inputting transaction flow information into a pre-trained second supervision model to obtain a transaction range of daily transaction amount output by the second supervision model. And acquiring a real-time value of the daily transaction amount through the real-time dynamic account information, and comparing the real-time value of the daily transaction amount with the transaction range to obtain a second comparison result. Therefore, according to the historical transaction flow information of the target account, the application predicts the transaction range of the daily transaction amount of the target account by utilizing the convolutional neural network model, and improves the real-time supervision efficiency of the daily transaction amount by comparing the real-time value of the daily transaction amount with the transaction range. Further, the monitoring result of the target account is determined by combining the first comparison result and the second comparison result, so that the comprehensiveness and the flexibility of monitoring are improved.
Furthermore, various information of the public account is stored and calculated based on the private chain, the uplink information is credible and has no tampering, early warning and prediction are all in seal and can be circulated, and the safety of data is improved.
Fig. 4 is a schematic structural diagram of a device for supervising public accounts according to an embodiment of the present application, where as shown in fig. 4, the device may include private chains corresponding to respective public accounts, where the private chain corresponding to the target account includes:
a transaction flow obtaining unit 401, configured to obtain transaction flow information corresponding to an electronic protocol to be supervised of a target account, as historical transaction flow information, where the target account is any one of a public account, and the transaction flow information at least includes a historical value of a single transaction amount;
A single transaction prediction unit 402, configured to input the transaction flow information to a first pre-trained supervision model, and obtain a transaction range of a single transaction amount output by the first supervision model; the first supervision model comprises a convolutional neural network model which is obtained by training based on transaction flow sample data taking a historical transaction range of a single transaction amount as a label in advance, wherein the transaction flow sample data comprises transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts;
A dynamic account information obtaining unit 403, configured to obtain real-time dynamic account information corresponding to an electronic protocol to be supervised of the target account, where the real-time dynamic account information includes an actual value of a single transaction amount;
A first comparing unit 404, configured to compare the real-time value of the single transaction amount with the transaction range to obtain a first comparison result;
and the supervision result obtaining unit 405 is configured to obtain a supervision result based at least on the first comparison result.
Optionally, the apparatus further comprises a model building unit for: clustering candidate historical accounts to obtain a plurality of account classes, wherein the candidate historical accounts are historical accounts signed with the electronic protocol to be supervised; classifying the target account to obtain an account class to which the target account belongs as a target account class; taking the candidate historical account belonging to the target account class as a sample account; acquiring transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts as transaction flow sample data; based on normal distribution, acquiring a historical transaction range of a single transaction amount in the transaction flow sample data; marking the transaction flow sample data by taking the historical transaction range of the single transaction amount as a first label; training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the first label as target output; and when a preset training completion condition is reached, obtaining a trained convolutional neural network model as the first supervision model, wherein the training completion condition comprises that the iteration number is larger than a preset maximum number threshold.
Optionally, the supervision result obtaining unit is configured to obtain a supervision result based on at least the first comparison result, including: the supervision result acquisition unit is specifically configured to: if the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, a preset first early warning instruction is generated, and the first early warning instruction is used for indicating that the single transaction of the target account is abnormal.
Optionally, the transaction flow information further includes a historical value of a daily transaction amount and a transaction date, the real-time dynamic account information further includes a real-time value of the daily transaction amount, and the private chain further includes a single transaction prediction unit, where the single transaction prediction unit is configured to: inputting the transaction flow information into a pre-trained second supervision model to obtain a transaction range of daily transaction amount output by the second supervision model, wherein the second supervision model comprises a convolutional neural network model which is obtained by training transaction flow sample data based on the historical transaction range of daily transaction amount as a label in advance;
And the second comparison unit is used for comparing the real-time value of the daily transaction amount with the transaction range to obtain a second comparison result.
Optionally, the supervision result obtaining unit is configured to obtain a supervision result based on at least the first comparison result, and further includes: the supervision result acquisition unit is specifically configured to: and if the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, generating a preset second early warning instruction, wherein the second early warning instruction is used for indicating that the daily transaction amount of the target account is abnormal. If the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, and the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, a preset third early warning instruction is generated, and the third early warning instruction is used for indicating abnormal transaction of the target account.
Optionally, the model building unit is further configured to: based on normal distribution, acquiring a historical transaction range of daily transaction amount in the transaction flow sample data; marking the transaction flow water sample data by taking the historical transaction range of the daily transaction amount as a second label; training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the second label as target output; and when the training completion condition is reached, obtaining a trained convolutional neural network model as the second supervision model.
Fig. 5 shows a schematic structural diagram of a policing device for the pair of public accounts, which may include: at least one processor 501, at least one communication interface 502, at least one memory 503, and at least one communication bus 504;
In the embodiment of the present application, the number of the processor 501, the communication interface 502, the memory 503 and the communication bus 504 is at least one, and the processor 501, the communication interface 502 and the memory 503 complete communication with each other through the communication bus 504;
the processor 501 may be a central processing unit CPU, or an Application-specific integrated Circuit ASIC (Application SPECIFIC INTEGRATED Circuit), or one or more integrated circuits configured to implement embodiments of the present invention, etc.;
The memory 503 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory), etc., such as at least one magnetic disk memory;
the memory stores a program, and the processor can execute the program stored in the memory to implement each step of the method for supervising the public account provided by the embodiment of the application, which is as follows:
a method for supervising a public account is applied to a private chain corresponding to a target account, and comprises the following steps:
the method comprises the steps of obtaining transaction flow information corresponding to an electronic protocol to be supervised of a target account as historical transaction flow information, wherein the target account is any public account, and the transaction flow information at least comprises a historical value of a single transaction amount;
Inputting the transaction flow information into a pre-trained first supervision model to obtain a transaction range of a single transaction amount output by the first supervision model; the first supervision model comprises a convolutional neural network model which is obtained by training based on transaction flow sample data taking a historical transaction range of a single transaction amount as a label in advance, wherein the transaction flow sample data comprises transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts;
acquiring real-time account moving information corresponding to an electronic protocol to be supervised of the target account, wherein the real-time account moving information comprises a real-time value of a single transaction amount;
comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result;
and obtaining a supervision result at least based on the first comparison result.
Optionally, the training process of the first supervision model includes: clustering candidate historical accounts to obtain a plurality of account classes, wherein the candidate historical accounts are historical accounts signed with the electronic protocol to be supervised; classifying the target account to obtain an account class to which the target account belongs as a target account class; taking the candidate historical account belonging to the target account class as a sample account; acquiring transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts as transaction flow sample data; based on normal distribution, acquiring a historical transaction range of a single transaction amount in the transaction flow sample data; marking the transaction flow sample data by taking the historical transaction range of the single transaction amount as a first label; training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the first label as target output; and when a preset training completion condition is reached, obtaining a trained convolutional neural network model as the first supervision model, wherein the training completion condition comprises that the iteration number is larger than a preset maximum number threshold.
Optionally, obtaining a supervision result based at least on the first comparison result includes: if the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, a preset first early warning instruction is generated, and the first early warning instruction is used for indicating that the single transaction of the target account is abnormal.
Optionally, the transaction flow information further includes a historical value of a daily transaction amount and a transaction date, the real-time dynamic account information further includes a real-time value of the daily transaction amount, and the method further includes: inputting the transaction flow information into a pre-trained second supervision model to obtain a transaction range of daily transaction amount output by the second supervision model, wherein the second supervision model comprises a convolutional neural network model which is obtained by training transaction flow sample data based on the historical transaction range of daily transaction amount as a label in advance; and comparing the real-time value of the daily transaction amount with the transaction range to obtain a second comparison result.
Optionally, obtaining a supervision result at least based on the first comparison result, further includes: if the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, generating a preset second early warning instruction, wherein the second early warning instruction is used for indicating that the daily transaction amount of the target account is abnormal; if the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, and the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, a preset third early warning instruction is generated, and the third early warning instruction is used for indicating abnormal transaction of the target account.
Optionally, the training process of the second supervision model comprises: based on normal distribution, acquiring a historical transaction range of daily transaction amount in the transaction flow sample data; marking the transaction flow water sample data by taking the historical transaction range of the daily transaction amount as a second label; training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the second label as target output; and when the training completion condition is reached, obtaining a trained convolutional neural network model as the second supervision model.
It should be noted that, the specific implementation method of each step of the method for supervising a public account provided by the embodiment of the present application refers to the above embodiment, and is not described herein.
The embodiment of the application also provides a readable storage medium, which can store a computer program suitable for being executed by a processor, and when the computer program is executed by the processor, the steps of the method for supervising the public account provided by the embodiment of the application are realized as follows:
a method for supervising a public account is applied to a private chain corresponding to a target account, and comprises the following steps:
the method comprises the steps of obtaining transaction flow information corresponding to an electronic protocol to be supervised of a target account as historical transaction flow information, wherein the target account is any public account, and the transaction flow information at least comprises a historical value of a single transaction amount;
Inputting the transaction flow information into a pre-trained first supervision model to obtain a transaction range of a single transaction amount output by the first supervision model; the first supervision model comprises a convolutional neural network model which is obtained by training based on transaction flow sample data taking a historical transaction range of a single transaction amount as a label in advance, wherein the transaction flow sample data comprises transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts;
acquiring real-time account moving information corresponding to an electronic protocol to be supervised of the target account, wherein the real-time account moving information comprises a real-time value of a single transaction amount;
comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result;
and obtaining a supervision result at least based on the first comparison result.
Optionally, the training process of the first supervision model includes: clustering candidate historical accounts to obtain a plurality of account classes, wherein the candidate historical accounts are historical accounts signed with the electronic protocol to be supervised; classifying the target account to obtain an account class to which the target account belongs as a target account class; taking the candidate historical account belonging to the target account class as a sample account; acquiring transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts as transaction flow sample data; based on normal distribution, acquiring a historical transaction range of a single transaction amount in the transaction flow sample data; marking the transaction flow sample data by taking the historical transaction range of the single transaction amount as a first label; training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the first label as target output; and when a preset training completion condition is reached, obtaining a trained convolutional neural network model as the first supervision model, wherein the training completion condition comprises that the iteration number is larger than a preset maximum number threshold.
Optionally, obtaining a supervision result based at least on the first comparison result includes: if the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, a preset first early warning instruction is generated, and the first early warning instruction is used for indicating that the single transaction of the target account is abnormal.
Optionally, the transaction flow information further includes a historical value of a daily transaction amount and a transaction date, the real-time dynamic account information further includes a real-time value of the daily transaction amount, and the method further includes: inputting the transaction flow information into a pre-trained second supervision model to obtain a transaction range of daily transaction amount output by the second supervision model, wherein the second supervision model comprises a convolutional neural network model which is obtained by training transaction flow sample data based on the historical transaction range of daily transaction amount as a label in advance; and comparing the real-time value of the daily transaction amount with the transaction range to obtain a second comparison result.
Optionally, obtaining a supervision result at least based on the first comparison result, further includes: if the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, generating a preset second early warning instruction, wherein the second early warning instruction is used for indicating that the daily transaction amount of the target account is abnormal; if the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, and the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, a preset third early warning instruction is generated, and the third early warning instruction is used for indicating abnormal transaction of the target account.
Optionally, the training process of the second supervision model comprises: based on normal distribution, acquiring a historical transaction range of daily transaction amount in the transaction flow sample data; marking the transaction flow water sample data by taking the historical transaction range of the daily transaction amount as a second label; training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the second label as target output; and when the training completion condition is reached, obtaining a trained convolutional neural network model as the second supervision model.
It should be noted that the method, the device, the equipment and the readable storage medium for supervising the public account provided by the invention can be used in the financial field or other fields. Can be used in the financial field or other fields. For example, the method can be used in fund supervision application scenes in the financial field. Other fields are any field other than the financial field, for example, the network security technical field. The foregoing is merely exemplary, and the application fields of the method, the device, the apparatus and the readable storage medium for supervising a public account provided by the present invention are not limited.
It should be noted that, the customer information (including, but not limited to, customer device information, customer personal information, customer (public) account information, etc.) and account data (including, but not limited to, data analyzed by the customer, stored data, presented data, etc.) related to the present application are information and data authorized by the customer or sufficiently authorized by each party, and the collection, use and processing of the related data is required to comply with the relevant laws and regulations and standards of the relevant country and region.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The utility model provides a supervision method for public accounts, which is characterized in that the supervision method is applied to private chains corresponding to target accounts and comprises the following steps:
the method comprises the steps of obtaining transaction flow information corresponding to an electronic protocol to be supervised of a target account as historical transaction flow information, wherein the target account is any public account, and the transaction flow information at least comprises a historical value of a single transaction amount;
Inputting the transaction flow information into a pre-trained first supervision model to obtain a transaction range of a single transaction amount output by the first supervision model; the first supervision model comprises a convolutional neural network model which is obtained by training based on transaction flow sample data taking a historical transaction range of a single transaction amount as a label in advance, wherein the transaction flow sample data comprises transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts;
acquiring real-time account moving information corresponding to an electronic protocol to be supervised of the target account, wherein the real-time account moving information comprises a real-time value of a single transaction amount;
comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result;
and obtaining a supervision result at least based on the first comparison result.
2. The method of policing a public account of claim 1, wherein the training process of the first policing model comprises:
clustering candidate historical accounts to obtain a plurality of account classes, wherein the candidate historical accounts are historical accounts signed with the electronic protocol to be supervised;
classifying the target account to obtain an account class to which the target account belongs as a target account class;
taking the candidate historical account belonging to the target account class as a sample account;
acquiring transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts as transaction flow sample data;
Based on normal distribution, acquiring a historical transaction range of a single transaction amount in the transaction flow sample data;
marking the transaction flow sample data by taking the historical transaction range of the single transaction amount as a first label;
Training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the first label as target output;
And when a preset training completion condition is reached, obtaining a trained convolutional neural network model as the first supervision model, wherein the training completion condition comprises that the iteration number is larger than a preset maximum number threshold.
3. The method of supervising a public account according to claim 2, wherein the obtaining a supervising result based at least on the first comparison result comprises:
if the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, a preset first early warning instruction is generated, and the first early warning instruction is used for indicating that the single transaction of the target account is abnormal.
4. The method of claim 3, wherein the transaction flow information further comprises a historical value of daily transactions and a transaction date, the real-time dynamic account information further comprises a real-time value of daily transactions, the method further comprising:
Inputting the transaction flow information into a pre-trained second supervision model to obtain a transaction range of daily transaction amount output by the second supervision model, wherein the second supervision model comprises a convolutional neural network model which is obtained by training transaction flow sample data based on the historical transaction range of daily transaction amount as a label in advance;
And comparing the real-time value of the daily transaction amount with the transaction range to obtain a second comparison result.
5. The method of claim 4, wherein the obtaining a supervision result based at least on the first comparison result, further comprises:
if the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, generating a preset second early warning instruction, wherein the second early warning instruction is used for indicating that the daily transaction amount of the target account is abnormal;
If the first comparison result indicates that the real-time value of the single transaction amount exceeds the transaction range of the single transaction amount, and the second comparison result indicates that the real-time value of the daily transaction amount exceeds the transaction range of the daily transaction amount, a preset third early warning instruction is generated, and the third early warning instruction is used for indicating abnormal transaction of the target account.
6. The method of policing a public account of claim 5, characterized in that the training process of the second policing model comprises:
Based on normal distribution, acquiring a historical transaction range of daily transaction amount in the transaction flow sample data;
Marking the transaction flow water sample data by taking the historical transaction range of the daily transaction amount as a second label;
Training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the second label as target output;
and when the training completion condition is reached, obtaining a trained convolutional neural network model as the second supervision model.
7. The utility model provides a supervision device to public account, characterized by includes each private chain that corresponds to public account, and wherein, the private chain that the target account corresponds includes:
The transaction flow obtaining unit is used for obtaining transaction flow information corresponding to an electronic protocol to be supervised of a target account as historical transaction flow information, wherein the target account is any one public account, and the transaction flow information at least comprises a historical value of a single transaction amount;
The single transaction prediction unit is used for inputting the transaction flow information into a pre-trained first supervision model to obtain a transaction range of a single transaction amount output by the first supervision model; the first supervision model comprises a convolutional neural network model which is obtained by training based on transaction flow sample data taking a historical transaction range of a single transaction amount as a label in advance, wherein the transaction flow sample data comprises transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts;
The system comprises a dynamic account information acquisition unit, a dynamic account management unit and a dynamic account management unit, wherein the dynamic account information acquisition unit is used for acquiring real-time dynamic account information corresponding to an electronic protocol to be supervised of the target account, and the real-time dynamic account information comprises real-time values of single transaction amount;
the first comparison unit is used for comparing the real-time value of the single transaction amount with the transaction range to obtain a first comparison result;
And the supervision result acquisition unit is used for acquiring a supervision result at least based on the first comparison result.
8. The device for supervising a public account according to claim 7, further comprising a model building unit configured to:
clustering candidate historical accounts to obtain a plurality of account classes, wherein the candidate historical accounts are historical accounts signed with the electronic protocol to be supervised;
classifying the target account to obtain an account class to which the target account belongs as a target account class;
taking the candidate historical account belonging to the target account class as a sample account;
acquiring transaction flow information corresponding to electronic protocols to be supervised of a plurality of sample accounts as transaction flow sample data;
Based on normal distribution, acquiring a historical transaction range of a single transaction amount in the transaction flow sample data;
marking the transaction flow sample data by taking the historical transaction range of the single transaction amount as a first label;
Training a pre-constructed convolutional neural network model by taking the transaction flow sample data as input and the first label as target output;
And when a preset training completion condition is reached, obtaining a trained convolutional neural network model as the first supervision model, wherein the training completion condition comprises that the iteration number is larger than a preset maximum number threshold.
9. A device for policing a public account, comprising: a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the method for supervising a public account according to any one of claims 1 to 6.
10. A readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of supervising a public account according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410209256.7A CN118037301A (en) | 2024-02-26 | 2024-02-26 | Method, device and equipment for supervising public account and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410209256.7A CN118037301A (en) | 2024-02-26 | 2024-02-26 | Method, device and equipment for supervising public account and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118037301A true CN118037301A (en) | 2024-05-14 |
Family
ID=91003832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410209256.7A Pending CN118037301A (en) | 2024-02-26 | 2024-02-26 | Method, device and equipment for supervising public account and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118037301A (en) |
-
2024
- 2024-02-26 CN CN202410209256.7A patent/CN118037301A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993233B (en) | Method and system for predicting data auditing objective based on machine learning | |
| CN112184012B (en) | Enterprise risk early warning method, device, equipment and readable storage medium | |
| KR101996797B1 (en) | Method for providing transaction security analysis service for risk management in real estate transaction based on disclosure data and statistics | |
| US20100017239A1 (en) | Forecasting Discovery Costs Using Historic Data | |
| CN110751286A (en) | Training method and training system of neural network model | |
| CN111881158B (en) | Processing method, device, computer system and readable storage medium for managing report data | |
| CN104321794A (en) | A system and method using multi-dimensional rating to determine an entity's future commercial viability | |
| CN112419030B (en) | Method, system and equipment for evaluating financial fraud risk | |
| CN111210335A (en) | User risk identification method and device and electronic equipment | |
| CN115760119A (en) | Financial payment supervision system and method based on data processing and feature recognition | |
| CN110490750B (en) | Data identification method, system, electronic equipment and computer storage medium | |
| CN114418175A (en) | Personnel management method and device, electronic equipment and storage medium | |
| CN113762973A (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN113420789B (en) | Method and device for predicting risk account number, storage medium and computer equipment | |
| CN117575595A (en) | Payment risk identification method, device, computer equipment and storage medium | |
| CN110706122A (en) | Method, device and readable medium for improving social security agent efficiency based on big data analysis | |
| CN110738570A (en) | Information type manipulation automatic identification method based on multi-channel heterogeneous data | |
| CN118037301A (en) | Method, device and equipment for supervising public account and readable storage medium | |
| CN113822715B (en) | Data acquisition, training and processing integrated platform analysis method | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| CN115271514A (en) | Communication enterprise monitoring method and device, electronic equipment and storage medium | |
| CN114529402A (en) | Credit management method, device and medium based on big data wind control | |
| Asthana et al. | System and Method on Order Management Using Neural Networks and Risk Modeling | |
| CN113688924B (en) | Abnormal order detection method, device, equipment and medium | |
| US20230048345A1 (en) | Using email history to estimate creditworthiness for applicants having insufficient credit history |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |