CN115375330A - Account state processing method, device, equipment, medium and product - Google Patents
Account state processing method, device, equipment, medium and product Download PDFInfo
- Publication number
- CN115375330A CN115375330A CN202211031876.3A CN202211031876A CN115375330A CN 115375330 A CN115375330 A CN 115375330A CN 202211031876 A CN202211031876 A CN 202211031876A CN 115375330 A CN115375330 A CN 115375330A
- Authority
- CN
- China
- Prior art keywords
- account
- type
- list data
- data
- model
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000004590 computer program Methods 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims description 33
- 238000012550 audit Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 8
- 238000012216 screening Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 208000001613 Gambling Diseases 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- 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
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to an account state processing method, an account state processing device, a computer device, a storage medium and a computer program product. The method comprises the following steps: the method comprises the steps of firstly obtaining account list data and at least two account type recognition models obtained through pre-training, then respectively carrying out recognition processing on the account list data through the account type recognition models to obtain an initial risk type of each account, then calculating a target risk type of each account according to the initial risk type of each account obtained through each account type recognition model, and finally modifying the state of each account according to the target risk type. According to the method, the suspicious account processing efficiency can be improved by carrying out recognition processing on the account list data through at least two account type recognition models obtained through pre-training.
Description
Technical Field
The present application relates to the field of big data analysis and mining technologies, and in particular, to an account status processing method and apparatus, a computer device, a storage medium, and a computer program product.
Background
With the high emphasis of the country on fighting against telecommunication phishing and cross-border gambling, the banks take the deep advancement of telecommunication phishing governance as an important task item of 'doing things for the masses'.
However, as the number of case-involved accounts is more and more, the treatment of suspicious accounts enters an urgent and difficult stage, the existing solution is to treat the suspicious accounts one by using manpower, the solution can not identify the case-involved accounts from the suspicious accounts in a targeted manner, the efficiency is very low, and a large amount of manpower and material resources are wasted.
Disclosure of Invention
In view of the above, it is necessary to provide an account status processing method, an account status processing apparatus, a computer device, a computer readable storage medium, and a computer program product, which can improve suspicious account processing efficiency.
In a first aspect, the present application provides an account status processing method, including:
acquiring account list data;
acquiring at least two account type recognition models obtained by pre-training;
respectively identifying the account list data through the account type identification model to obtain the initial risk type of each account;
calculating a target risk type of each account according to the initial risk type of each account obtained by each account type identification model;
and modifying the state of each account according to the target risk type.
In one embodiment, the modifying the account status according to the target risk type includes:
outputting the account list data, the initial risk type and the target risk type to an auditing terminal;
receiving an auditing result fed back by the auditing terminal, wherein the auditing result is obtained by auditing based on the account list data, the initial risk type and the target risk type;
and modifying the state of each account based on the auditing result.
In one embodiment, after modifying the account status based on the audit result, the modifying includes:
obtaining a model evaluation index based on the auditing result and the target risk type;
and sending the model evaluation index to a model training platform, wherein the model evaluation index is used for instructing the model training platform to screen the account list data according to the model evaluation index to obtain new model training data, and updating each account type identification model based on the new model training data.
In one embodiment, the obtaining account inventory data includes:
synchronizing account history inventory data from a data platform;
polling the data platform according to a preset time period to obtain newly added list data of each account;
and determining the account list data according to the historical list data and the newly added list data.
In one embodiment, before the obtaining of the at least two pre-trained account type recognition models, the method further includes:
extracting account basic information and account transaction information from the account inventory data;
and calculating account characteristics according to the account basic information and the account transaction information.
In one embodiment, the identifying the account list data by the account type identification model respectively to obtain the initial risk type of each account includes:
respectively acquiring account characteristics corresponding to the account type identification models;
and respectively inputting the acquired account characteristics into the corresponding account type identification models to obtain the initial risk types of the accounts.
In one embodiment, the calculating the target risk type of each account according to the initial risk type of each account obtained by each account type identification model includes:
when all initial risk types corresponding to the account are target types, determining that the target risk types of the account are first types;
when one of the initial risk types corresponding to the account is a target type, determining that the target risk type of the account is a second type, wherein the risk of the first type is higher than that of the second type.
In a second aspect, the present application further provides an account status processing apparatus, including:
the first acquisition module is used for acquiring account list data;
the second acquisition module is used for acquiring at least two account type recognition models obtained by pre-training;
the identification processing module is used for respectively identifying and processing the account list data through the account type identification model to obtain the initial risk type of each account;
the calculation module is used for calculating and obtaining a target risk type of each account according to the initial risk type of each account obtained by each account type identification model;
and the modifying module is used for modifying the state of each account according to the target risk type.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method in any of the embodiments described above when executing the computer program.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method in any of the above-mentioned embodiments.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, carries out the steps of the method in any of the embodiments described above.
According to the account state processing method, the account state processing device, the computer equipment, the storage medium and the computer program product, firstly, account list data are obtained, at least two account type recognition models obtained through pre-training are obtained, then, the account list data are respectively recognized and processed through the account type recognition models, initial risk types of all accounts are obtained, then, target risk types of all accounts are obtained through calculation according to the initial risk types of all accounts obtained through the account type recognition models, and finally, the account states are modified according to the target risk types. According to the method, the suspicious account processing efficiency can be improved by carrying out recognition processing on the account list data through at least two account type recognition models obtained through pre-training.
Drawings
FIG. 1 is a flow diagram illustrating a method for account status processing according to one embodiment;
FIG. 2 is a schematic diagram of account features in one embodiment;
FIG. 3 is a schematic diagram of a method of account status processing in one embodiment;
FIG. 4 is a block diagram showing the construction of an account status processing apparatus according to an embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an embodiment, as shown in fig. 1, an account status processing method is provided, and this embodiment is illustrated by applying the method to a terminal, and it is to be understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and is implemented by interaction between the terminal and the server. In this embodiment, the method includes the steps of:
s101, acquiring account list data.
The account inventory data includes account basic information and account transaction information for the individual account, for example, the account inventory data is shown in table 1:
TABLE 1
| Meaning of Chinese | Data volume |
| Account history detail master table | Approximately 1800 thousands of data in three months |
| Account register | The last year of data, about 3.6 hundred million pieces of data. |
| WAP mobile phone bank auxiliary meter | Total volume of the last month |
| Personal client holds product statistics (head office) | Total volume of the last month |
| Basic information of individual customer | Total volume of the last month |
| Personal mobile banking aggregation | Total volume of the last month |
| Credit card aggregation | Total volume of the last month |
The server acquires account list data of all clients stored in a head office data lake from the head office data lake, transmits the account list data to a branch big data service cloud through a characteristic docking head office interface, and then identifies and screens risk accounts according to the account list data in the branch big data service cloud, wherein the head office data lake uniformly stores all data of the whole bank, and the branch big data service cloud is used for acquiring and storing required data from the head office data lake and processing the acquired data.
S102, obtaining at least two account type recognition models obtained through pre-training.
The account type identification model is a model for identifying and screening accounts corresponding to account list data according to account list data acquired from the head office data lake. Before screening accounts, the server obtains an account type identification model by training historical risk account list data, wherein the historical risk account list data is account list data corresponding to risk accounts determined manually or by using a screening model before the account list data is obtained at this time. The setting of at least two account type identification models can enable screening results of the accounts to be more accurate.
S103, the account list data are respectively identified through the account type identification model, and the initial risk types of the accounts are obtained.
The server processes the account list data by using the account category identification model, so as to identify accounts which may be at risk, and determines an initial risk type corresponding to each account which may be at risk, for example, if the account category identification model is a frequent transaction model and a multiple-in and multiple-out model, the initial risk type includes that the account has no risk, the account satisfies the frequent transaction model, the account satisfies the multiple-in and multiple-out model, and the account satisfies one or more of the two identification models.
Wherein the frequent transaction model comprises: (1) debit average amount on day > = parameter value 1; average amount of lender on the same day > = parameter value 2; (2) a-times of same-name account fast-forwarding and fast-releasing occur in the same day: the time difference between the posting and the posting is more than or equal to b minutes and less than or equal to c minutes; (3) the average amount of the borrower in the same day/the average amount of the lender in the same day is more than or equal to the parameter value 3 and less than or equal to the parameter value 4; (4) the amount of the debt of the card client on the day of my bank is lower than the parameter value d yuan.
The multiple-in and multiple-out model comprises: (1) the account transaction amount in the current day is less than or equal to the parameter 5, and the transaction note is one of three values of 'transfer', 'purchase' and 'third party payment'; (2) the account in the current day is transferred to the amount which is more than or equal to the parameter 6 through one channel of 'bank clearing', 'third party payment' and 'other banks'; (3) the account has a transaction with the parameter 7 or more in the current day; (4) in the day, the transfer amount = the transfer amount; (5) in the current day, the transaction sequence of the account needs to occur in the first four steps, namely the first step, the second step, the third step and the fourth step are triggered respectively.
In other embodiments, the frequent transaction model and the multiple-in and multiple-out model may be other, again without specific limitation.
And S104, calculating the target risk type of each account according to the initial risk type of each account obtained by each account type identification model.
Because the initial risk type identified by the account type identification model may also include an account without risk, after the initial risk type is determined, the server further needs to send the account corresponding to the initial risk type and the account list data corresponding to the account to the auditing terminal, and the auditing terminal performs further auditing confirmation to finally obtain the account corresponding to the target risk type, where the account corresponding to the target risk type does not include the account without risk.
And S105, modifying the state of each account according to the target risk type.
After the account corresponding to the target risk type is determined, the state of the account can be modified according to the target risk type to which the account belongs, for example, the target risk type includes that the account meets a frequent transaction model, the account meets a more-in-and-less-out model and the account meets one or more of two recognition models at the same time, when the account meets the frequent transaction model or the account meets the more-in-and-less-out model, the account is degraded, and when the account meets the two recognition models at the same time, the account is subjected to stop payment management and control.
In the account state processing method, account list data are obtained and at least two account type recognition models obtained through pre-training are obtained, then the account list data are recognized through the account type recognition models respectively to obtain the initial risk types of the accounts, then the target risk types of the accounts are obtained through calculation according to the initial risk types of the accounts obtained through the account type recognition models, and finally the account states are modified according to the target risk types. According to the method, the suspicious account processing efficiency can be improved by carrying out recognition processing on the account list data through at least two account type recognition models obtained through pre-training.
In some embodiments, modifying the status of each account according to the target risk type includes: outputting the account list data, the initial risk type and the target risk type to an auditing terminal; receiving an auditing result fed back by an auditing terminal, wherein the auditing result is obtained by auditing based on account list data, an initial risk type and a target risk type; and modifying the state of each account based on the auditing result.
In the step, the server outputs the account list data, the initial risk type and the target risk type to an auditing terminal, then receives an account corresponding to the target risk type finally determined by an evaluator at the auditing terminal, performs state adjustment processing on the account corresponding to the target risk type, performs degradation processing on the account when the account meets a frequent transaction model or the account meets an in-out model, and performs control of stop-go and stop-pay on the account when the account meets two recognition models.
According to the method provided by the step, the risk account is further confirmed by the evaluator, so that the accuracy of risk account identification can be improved; the corresponding state adjustment processing is carried out on the account which is finally determined to be at risk, so that the conditions of telecommunication fraud and network gambling can be effectively controlled.
In some embodiments, after modifying the status of each account based on the audit result, the method includes: obtaining a model evaluation index based on the auditing result and the target risk type; and sending the model evaluation index to a model training platform, wherein the model evaluation index is used for instructing the model training platform to screen account statement data according to the model evaluation index to obtain new model training data, and updating each account type recognition model based on the new model training data.
In the step, the server gives an evaluation index 1 to account list data of an account corresponding to a target risk type which is finally checked and confirmed, gives an evaluation index 0 to account list data of an account which is not at risk in the account corresponding to an initial risk type which is finally checked and confirmed, and then sends the obtained evaluation index to the model training platform, when the evaluation index is 0, the account type recognition model is not trained, and when the evaluation index is 1, the model training platform trains the account type recognition model according to the account list data of the account corresponding to the target risk type to obtain a new account type recognition model.
According to the method provided by the step, the account type recognition model is trained and updated based on the auditing result and the target risk model, so that the model accuracy can be effectively improved.
In some embodiments, obtaining account manifest data comprises: synchronizing account history inventory data from the data platform; polling a data platform according to a preset time period to obtain newly added list data of each account; and determining account list data according to the historical list data and the newly added list data.
In this step, the server may first obtain historical list data of all accounts from the big data lake of the head office, and then periodically poll the big data lake of the head office to obtain list data of new accounts, for example, the server obtains list data of new accounts of the current day from the big data lake every other day. The historical inventory data and all newly added inventory data together are account inventory data.
The method provided by the step can acquire the historical inventory data and the newly added inventory data, so that the acquired data is more comprehensive, and the model accuracy can be more effectively improved.
In some embodiments, before obtaining the at least two account type recognition models trained in advance, the method further includes: extracting account basic information and account transaction information from the account inventory data; and calculating the account characteristics according to the account basic information and the account transaction information.
In this step, the basic information of the account includes information such as the sex, age, number establishment date of the customer, and identity information verification result of the customer, and the account transaction information includes information such as a transaction opponent, transaction information, and a service provision condition, and in other embodiments, the basic information of the account and the account transaction information may be other information, which is not specifically limited herein, and then account characteristics are determined according to the basic information of the account and the account transaction information, wherein the account characteristics are characteristics corresponding to the basic information of the account and the account transaction information, and are used for determining an initial risk type of each account according to an account type identification model, and a schematic diagram of the account characteristics is shown in fig. 2.
The method provided by the step determines the account characteristics through the account basic information and the account transaction information of the account list data, and can improve the efficiency of determining the initial risk types of the accounts according to the account type identification model.
In some embodiments, the identifying the account list data by the account type identification model to obtain the initial risk type of each account includes: respectively acquiring account characteristics corresponding to the account type identification models; and respectively inputting the acquired account characteristics into the corresponding account type identification models to obtain the initial risk types of the accounts.
In this step, the server inputs data corresponding to the account characteristics into an account type identification model, and the account type identification model determines the initial risk type of each account according to the account characteristics, wherein the account type identification model is a frequent transaction model and an excess-in and excess-out model.
The method provided by the step can determine the initial risk type more accurately.
In some embodiments, calculating the target risk type of each account according to the initial risk type of each account obtained by each account type identification model includes: when all initial risk types corresponding to the account are target types, determining that the target risk type of the account is a first type; when one of the initial risk types corresponding to the account is the target type, determining that the target risk type of the account is the second type, wherein the risk of the first type is higher than that of the second type.
In this step, the target type refers to a risk type corresponding to an account satisfying the account type identification model, if the account corresponding to the initial risk type satisfies both the frequent transaction model and the multiple-in and multiple-out model, the target risk type of the account is determined to be a first type, and if the account corresponding to the initial risk type satisfies the frequent transaction model or the multiple-in and multiple-out model, the target risk type of the account is determined to be a second type.
In the step, corresponding processing can be performed on different risk accounts by judging which risk type the account belongs to, and the processing on the risk accounts is more accurate and efficient.
In one embodiment, as shown in FIG. 3, a schematic diagram of an account status processing method is provided. The server firstly obtains account list data from big data lake of head office, then determines account characteristics according to account basic information and account transaction information in the account list data, screens the account list data according to the account characteristics and a preset account type identification model to obtain initial risk types of each account, then calculates target risk types of each account according to the initial risk types of each account obtained by each account type identification model, finally modifies the states of each account according to the target risk types, and identifies and updates the account type identification model according to the target risk types.
It should be understood that, although the steps in the flowcharts related to the embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides an account status processing apparatus for implementing the above-mentioned account status processing method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the account status processing device provided below can be referred to the limitations of the above account status processing method, and details are not described here.
In one embodiment, as shown in fig. 4, there is provided an account status processing apparatus 400 including: a first obtaining module 401, a second obtaining module 402, a recognition processing module 403, a calculating module 404, and a modifying module 405, wherein:
the first obtaining module 401 is configured to obtain account inventory data.
A second obtaining module 402, configured to obtain at least two account type recognition models obtained through pre-training.
And the identification processing module 403 is configured to perform identification processing on the account list data through the account type identification model, so as to obtain an initial risk type of each account.
And a calculating module 404, configured to calculate a target risk type of each account according to the initial risk type of each account obtained by each account type identification model.
And a modification module 405, configured to modify the account statuses according to the target risk types.
In one embodiment, the modification module 405 is further configured to: outputting the account list data, the initial risk type and the target risk type to an auditing terminal; receiving an auditing result fed back by an auditing terminal, wherein the auditing result is obtained by auditing based on account list data, an initial risk type and a target risk type; and modifying the state of each account based on the auditing result.
In one embodiment, after modifying the account status based on the audit result, the account status processing apparatus 400 is specifically configured to: obtaining a model evaluation index based on the auditing result and the target risk type; and sending the model evaluation index to a model training platform, wherein the model evaluation index is used for instructing the model training platform to screen account statement data according to the model evaluation index to obtain new model training data, and updating each account type recognition model based on the new model training data.
In one embodiment, the first obtaining module 401 is further configured to: synchronizing account history inventory data from a data platform; polling a data platform according to a preset time period to obtain newly added list data of each account; and determining account list data according to the history list data and the newly added list data.
In one embodiment, before obtaining the at least two pre-trained account type recognition models, the account status processing apparatus 400 is further configured to: extracting account basic information and account transaction information from the account inventory data; and calculating the account characteristics according to the account basic information and the account transaction information.
In one embodiment, the recognition processing module 403 is further configured to: respectively acquiring account characteristics corresponding to the account type identification models; and respectively inputting the acquired account characteristics into the corresponding account type identification models to obtain the initial risk types of the accounts.
In one embodiment, the calculation module 404 is further configured to determine that the target risk type of the account is a first type when each of the initial risk types corresponding to the account is a target type; when one of the initial risk types corresponding to the account is the target type, determining that the target risk type of the account is the second type, wherein the risk of the first type is higher than that of the second type.
The respective modules in the above-mentioned account status processing device may be implemented wholly or partially by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store account listing data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an account status handling method.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring account list data; acquiring at least two account type recognition models obtained by pre-training; respectively identifying and processing account list data through an account type identification model to obtain an initial risk type of each account; calculating a target risk type of each account according to the initial risk type of each account obtained by each account type identification model; and modifying the state of each account according to the target risk type.
In one embodiment, modifying the status of each account according to the target risk type, as performed by the processor executing the computer program, comprises: outputting the account list data, the initial risk type and the target risk type to an auditing terminal; receiving an auditing result fed back by an auditing terminal, wherein the auditing result is obtained by auditing based on account list data, an initial risk type and a target risk type; and modifying the state of each account based on the auditing result.
In one embodiment, the modifying the status of each account based on the result of the audit, as performed by the processor when executing the computer program, comprises: obtaining a model evaluation index based on the auditing result and the target risk type; and sending the model evaluation indexes to a model training platform, wherein the model evaluation indexes are used for instructing the model training platform to screen account statement data according to the model evaluation indexes to obtain new model training data, and updating each account type recognition model based on the new model training data.
In one embodiment, the obtaining account statement data, as implemented by a processor executing a computer program, comprises: synchronizing account history inventory data from the data platform; polling a data platform according to a preset time period to obtain newly added list data of each account; and determining account list data according to the history list data and the newly added list data.
In one embodiment, the obtaining of the at least two pre-trained account type identification models performed by the processor when executing the computer program further comprises: extracting account basic information and account transaction information from the account inventory data; and calculating the account characteristics according to the account basic information and the account transaction information.
In one embodiment, the identification of the account list data by the account type identification model when the processor executes the computer program to obtain the initial risk type of each account includes: respectively acquiring account characteristics corresponding to the account type identification models; and respectively inputting the acquired account characteristics into the corresponding account type identification models to obtain the initial risk types of the accounts.
In one embodiment, the calculating the target risk type of each account according to the initial risk type of each account obtained by each account type identification model when the processor executes the computer program includes:
when all initial risk types corresponding to the account are target types, determining that the target risk type of the account is a first type; when one of the initial risk types corresponding to the account is the target type, determining that the target risk type of the account is the second type, wherein the risk of the first type is higher than that of the second type.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring account list data; acquiring at least two account type recognition models obtained by pre-training; respectively identifying account list data through an account type identification model to obtain an initial risk type of each account; calculating a target risk type of each account according to the initial risk type of each account obtained by each account type identification model; and modifying the state of each account according to the target risk type.
In one embodiment, modifying the status of each account according to the target risk type, when performed by the processor, includes: outputting the account list data, the initial risk type and the target risk type to an auditing terminal; receiving an auditing result fed back by an auditing terminal, wherein the auditing result is obtained by auditing based on account list data, an initial risk type and a target risk type; and modifying the state of each account based on the auditing result.
In one embodiment, the modifying the status of each account based on the audit result, when performed by the processor, comprises: obtaining a model evaluation index based on the auditing result and the target risk type; and sending the model evaluation index to a model training platform, wherein the model evaluation index is used for instructing the model training platform to screen account statement data according to the model evaluation index to obtain new model training data, and updating each account type recognition model based on the new model training data.
In one embodiment, the computer program, when executed by a processor, implements obtaining account manifest data, comprising: synchronizing account history inventory data from a data platform; polling a data platform according to a preset time period to obtain newly added list data of each account; and determining account list data according to the history list data and the newly added list data.
In one embodiment, the obtaining of the at least two pre-trained account type recognition models, when performed by the processor, further comprises: extracting account basic information and account transaction information from the account inventory data; and calculating the account characteristics according to the account basic information and the account transaction information.
In one embodiment, the identification of account list data by an account type identification model when the computer program is executed by the processor to obtain an initial risk type of each account includes: respectively acquiring account characteristics corresponding to the account type identification models; and respectively inputting the acquired account characteristics into the corresponding account type identification models to obtain the initial risk types of the accounts.
In one embodiment, the calculating of the target risk type for each account from the initial risk type for each account obtained from each account type recognition model when the computer program is executed by the processor includes: when all initial risk types corresponding to the account are target types, determining that the target risk type of the account is a first type; when one of the initial risk types corresponding to the account is the target type, determining that the target risk type of the account is the second type, wherein the risk of the first type is higher than that of the second type.
In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:
acquiring account list data; acquiring at least two account type recognition models obtained by pre-training; respectively identifying and processing account list data through an account type identification model to obtain an initial risk type of each account; calculating a target risk type of each account according to the initial risk type of each account obtained by each account type identification model; and modifying the state of each account according to the target risk type.
In one embodiment, modifying the account status according to the target risk type, as performed by the computer program when executed by the processor, comprises: outputting the account list data, the initial risk type and the target risk type to an auditing terminal; receiving an auditing result fed back by an auditing terminal, wherein the auditing result is obtained by auditing based on account list data, an initial risk type and a target risk type; and modifying the state of each account based on the auditing result.
In one embodiment, the modifying the status of each account based on the audit result, when performed by the processor, comprises: obtaining a model evaluation index based on the auditing result and the target risk type; and sending the model evaluation index to a model training platform, wherein the model evaluation index is used for instructing the model training platform to screen account statement data according to the model evaluation index to obtain new model training data, and updating each account type recognition model based on the new model training data.
In one embodiment, the computer program, when executed by a processor, implements obtaining account manifest data, comprising: synchronizing account history inventory data from a data platform; polling a data platform according to a preset time period to obtain newly added list data of each account; and determining account list data according to the historical list data and the newly added list data.
In one embodiment, the obtaining of the at least two pre-trained account type recognition models, when performed by the processor, further comprises: extracting account basic information and account transaction information from the account inventory data; and calculating the account characteristics according to the account basic information and the account transaction information.
In one embodiment, the identification of account list data by an account type identification model when the computer program is executed by the processor to obtain an initial risk type of each account includes: respectively acquiring account characteristics corresponding to the account type identification models; and respectively inputting the acquired account characteristics into the corresponding account type identification models to obtain the initial risk types of the accounts.
In one embodiment, the calculating of the target risk type for each account from the initial risk type for each account obtained from each account type recognition model when the computer program is executed by the processor includes: when all initial risk types corresponding to the account are target types, determining that the target risk type of the account is a first type; when one of the initial risk types corresponding to the account is the target type, determining that the target risk type of the account is the second type, wherein the risk of the first type is higher than that of the second type.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware that is instructed by a computer program, and the computer program may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (11)
1. An account status processing method, characterized in that the method comprises:
acquiring account list data;
acquiring at least two account type recognition models obtained by pre-training;
respectively identifying the account list data through the account type identification model to obtain the initial risk type of each account;
calculating a target risk type of each account according to the initial risk type of each account obtained by each account type identification model;
and modifying the state of each account according to the target risk type.
2. The method of claim 1, wherein modifying the status of each account according to the target risk type comprises:
outputting the account list data, the initial risk type and the target risk type to an auditing terminal;
receiving an auditing result fed back by the auditing terminal, wherein the auditing result is obtained by auditing based on the account list data, the initial risk type and the target risk type;
and modifying the state of each account based on the auditing result.
3. The method of claim 2, wherein modifying the status of each account based on the audit result comprises:
obtaining a model evaluation index based on the auditing result and the target risk type;
and sending the model evaluation index to a model training platform, wherein the model evaluation index is used for instructing the model training platform to screen the account list data according to the model evaluation index to obtain new model training data, and updating each account type identification model based on the new model training data.
4. The method of claim 1, wherein the obtaining account manifest data comprises:
synchronizing account history inventory data from a data platform;
polling the data platform according to a preset time period to obtain newly added list data of each account;
and determining the account list data according to the historical list data and the newly added list data.
5. The method of claim 1, wherein before the obtaining the at least two pre-trained account type recognition models, further comprising:
extracting account basic information and account transaction information from the account inventory data;
and calculating account characteristics according to the account basic information and the account transaction information.
6. The method according to claim 1, wherein the identifying the account list data by the account type identification model to obtain the initial risk type of each account comprises:
respectively acquiring account characteristics corresponding to the account type identification models;
and respectively inputting the acquired account characteristics into the corresponding account type identification models to obtain the initial risk types of the accounts.
7. The method of claim 1, wherein calculating a target risk type for each account according to the initial risk type of each account obtained by each account type identification model comprises:
when all initial risk types corresponding to the account are target types, determining that the target risk types of the account are first types;
when one of the initial risk types corresponding to the account is a target type, determining that the target risk type of the account is a second type, wherein the risk of the first type is higher than that of the second type.
8. An account status processing apparatus, the apparatus comprising:
the first acquisition module is used for acquiring account list data;
the second acquisition module is used for acquiring at least two account type recognition models obtained by pre-training;
the identification processing module is used for respectively identifying and processing the account list data through the account type identification model to obtain the initial risk type of each account;
the calculation module is used for calculating and obtaining the target risk type of each account according to the initial risk type of each account obtained by each account type identification model;
and the modifying module is used for modifying the state of each account according to the target risk type.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
11. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211031876.3A CN115375330A (en) | 2022-08-26 | 2022-08-26 | Account state processing method, device, equipment, medium and product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211031876.3A CN115375330A (en) | 2022-08-26 | 2022-08-26 | Account state processing method, device, equipment, medium and product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115375330A true CN115375330A (en) | 2022-11-22 |
Family
ID=84066920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211031876.3A Pending CN115375330A (en) | 2022-08-26 | 2022-08-26 | Account state processing method, device, equipment, medium and product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115375330A (en) |
-
2022
- 2022-08-26 CN CN202211031876.3A patent/CN115375330A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110503564B (en) | Security case processing method, system, equipment and storage medium based on big data | |
| CN110097451B (en) | Bank business monitoring method and device | |
| CN109685336A (en) | Collection task distribution method, device, computer equipment and storage medium | |
| CN109377214A (en) | A kind of method of payment, computer readable storage medium and server | |
| WO2022213194A1 (en) | Predicting service-specific attrition events using trained artificial-intelligence processes | |
| CN110796539A (en) | Credit investigation evaluation method and device | |
| WO2022140839A1 (en) | Predicting occurrences of temporally separated events using adaptively trained artificial-intelligence processes | |
| CN109919608B (en) | Identification method, device and server for high-risk transaction main body | |
| CN115630221A (en) | Terminal application interface display data processing method and device and computer equipment | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| WO2022140837A1 (en) | Prediction of future occurrences of events using adaptively trained artificial-intelligence processes | |
| CN113313580A (en) | Suspicious transaction screening method and device, electronic equipment and storage medium | |
| CN117094764A (en) | Bank integral processing method and device | |
| CN112308623A (en) | High-quality client loss prediction method and device based on supervised learning and storage medium | |
| US20220318573A1 (en) | Predicting targeted, agency-specific recovery events using trained artificial intelligence processes | |
| US20220343422A1 (en) | Predicting occurrences of future events using trained artificial-intelligence processes and normalized feature data | |
| CN115375330A (en) | Account state processing method, device, equipment, medium and product | |
| US20220277227A1 (en) | Predicting occurrences of targeted classes of events using trained artificial-intelligence processes | |
| CN114693428A (en) | Data determination method and device, computer readable storage medium and electronic equipment | |
| WO2022204779A1 (en) | Predicting future events of predetermined duration using adaptively trained artificial-intelligence processes | |
| CN112734352A (en) | Document auditing method and device based on data dimensionality | |
| US11361267B1 (en) | System and method for determining loss resulting from data privacy and security breach | |
| CN116883155A (en) | Bank credit limit judging method, device and equipment applied to automobile supply chain | |
| CN115936843A (en) | Credit card management method, device and system | |
| CN116739775A (en) | Investigation method, application admission system, device and computer equipment for application qualification |
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 |