CN116843291A - Transaction data verification method, device, equipment and storage medium - Google Patents
Transaction data verification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116843291A CN116843291A CN202310788458.7A CN202310788458A CN116843291A CN 116843291 A CN116843291 A CN 116843291A CN 202310788458 A CN202310788458 A CN 202310788458A CN 116843291 A CN116843291 A CN 116843291A
- Authority
- CN
- China
- Prior art keywords
- transaction data
- scene
- service
- transaction
- type
- 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 32
- 238000013524 data verification Methods 0.000 title claims abstract description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000010276 construction Methods 0.000 claims description 44
- 238000004590 computer program Methods 0.000 claims description 23
- 239000013604 expression vector Substances 0.000 claims description 20
- 238000013145 classification model Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 230000000977 initiatory effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 15
- 238000002372 labelling Methods 0.000 description 5
- 238000012098 association analyses Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application discloses a transaction data verification method, a device, equipment and a storage medium, wherein the method comprises the following steps: intercepting transaction data in a service system, and performing type analysis on the transaction data to generate a corresponding service type; according to the business type of the transaction data identified by the same user id, acquiring corresponding transaction elements and generating a target business scene; extracting characteristics of transaction data identified by the same user id to generate scene characteristic parameters; matching corresponding predicted service scenes according to scene characteristic parameters; judging whether the transaction data is abnormal or not according to the association degree value of the target service scene and the predicted service scene; if yes, the abnormal reminding information is sent to the business system to inform corresponding business personnel to modify the configuration parameters of the transaction data so as to analyze and judge the transaction data with different configuration parameters, and the error rate of the transaction data is reduced and the working efficiency of transaction data processing is improved by modifying the abnormal transaction data.
Description
Technical Field
The present application relates to the field of transaction data processing technologies, and in particular, to a transaction data verification method, device, equipment, and storage medium.
Background
In the prior art, transaction data processing identifies a service scene where a user is located by acquiring transaction data of the user for analysis, and in an informatization age, the user has various service scenes such as order payment, order settlement, refund, third party service reconciliation and the like, wherein the payment comprises the service scenes such as transfer, red package or consumption coupon deduction, borrowing and the like.
In the process of acquiring the user transaction data, the transaction data generated under different business scenes of different business systems have different configuration parameters because the transaction data of the user are generated in the business systems at different sites. Therefore, when the transaction data with different configuration parameters are aggregated and analyzed, the problem of error identification of the transaction data is easy to generate, so that abnormal data is generated, the transaction data is inaccurate to process, and the working efficiency of the transaction data processing is reduced; in addition, the existing transaction data processing method only processes and identifies the acquired transaction data in a limited service scene range, and cannot restore an accurate service scene, so that an abnormal service scene is generated, and further the accuracy of transaction data processing is reduced.
Disclosure of Invention
The application provides a transaction data verification method, which is used for analyzing and judging abnormality of transaction data with different configuration parameters, and reducing error rate of the transaction data and improving working efficiency of transaction data processing by modifying the abnormal transaction data.
The application provides a transaction data verification method, which comprises the following steps: intercepting first transaction data in a first service system, and performing type analysis on the first transaction data to generate a corresponding service type; the first transaction data carries a user id identifier for the first transaction data; the first transaction data is generated by a user initiating a service request to a service system;
acquiring corresponding transaction elements according to the service type of the second transaction data identified by the same user id, and generating a target service scene; extracting features of second transaction data identified by the same user id to generate scene feature parameters; matching corresponding predicted service scenes according to the scene characteristic parameters; the predicted business scenario is stored in a scenario database;
judging whether the second transaction data is abnormal or not according to the association degree value of the target service scene and the predicted service scene; if yes, the abnormal reminding information is sent to the first service system to inform corresponding service personnel to modify the configuration parameters of the second transaction data.
As a preferred scheme, the application generates a theoretically feasible target service scene by carrying out type analysis on transaction data, and generates a practically feasible predicted service scene by extracting and matching characteristics of the transaction data; and judging whether the transaction data is abnormal or not by carrying out association analysis on two business scenes generated by theoretical and actual analysis of the same transaction data. In addition, the transaction data of the same user id are identified, so that construction and anomaly analysis are realized aiming at the business scene of the same user, the accuracy of scene construction can be improved, and abnormal users can be quickly locked according to the abnormal transaction data; after the abnormal data is judged, the error rate of transaction data analysis of different configuration parameters is reduced by modifying the configuration parameters of the transaction data, so that the accuracy of the transaction data can be improved, and the working efficiency of transaction data processing can be improved.
Further, first transaction data in a first service system are intercepted, type analysis is carried out on the first transaction data, and a corresponding service type is generated, specifically:
when a service request event in a first service system is received in a preset time period, acquiring a user id and corresponding first transaction data in the service request event, and identifying the user id in the corresponding first transaction data; classifying the second transaction data identified by the same user id, and generating a service type set for the second transaction data identified by each user id.
As a preferred scheme, the method and the device for identifying the transaction data of the same user id can be used for constructing and exception analyzing the business scene of the same user, so that the accuracy of scene construction can be improved, and abnormal users can be locked quickly according to the abnormal transaction data.
Further, according to the service type of the second transaction data identified by the same user id, a corresponding transaction element is obtained, and a target service scene is generated, specifically:
according to a service type set of second transaction data identified by the same user id, determining a transaction element corresponding to each service type in the second transaction data by searching a mapping relation between the service type of the transaction data and the transaction element; the transaction element includes: one or more of transaction time, transaction period, transaction channel, transaction mode, and transaction target;
inputting the service type and the corresponding transaction elements into a scene construction model; and generating at least one target business scene meeting the conditions according to each combination of the business type and the corresponding transaction elements.
Further, according to each combination of the service type and the corresponding transaction element, at least one target service scene meeting the conditions is generated, specifically:
determining model parameters of a scene construction model according to the service type and the corresponding transaction elements; clustering and fitting the model parameters according to historical transaction data and preset transaction rules to generate combination information of each model parameter combination; generating scene configuration data of each target service scene according to the combination information; and determining configuration service parameters of each target service scene according to the scene configuration data, and constructing a corresponding target service scene.
Further, feature extraction is performed on second transaction data identified by the same user id, scene feature parameters are generated, and corresponding predicted service scenes are matched according to the scene feature parameters, specifically:
extracting a feature expression vector of second transaction data identified by the same user id, calling a classification model to classify and identify the feature expression vector, generating a scene type label of the second transaction data, and taking the scene feature parameter and a service parameter value in the second transaction data as scene feature parameters; the classification model is trained by a multi-label classifier on the characteristic expression vector of the historical transaction data and the corresponding scene type label;
and calculating the similarity value between the scene characteristic parameter and each scene characteristic in the predicted service scene in the scene database, and screening the predicted service scene of which the similarity value meets the preset range.
As a preferred scheme, the application generates a theoretically feasible target service scene by carrying out type analysis on transaction data and combination simulation on transaction elements; and generating a practically feasible predicted service scene with the most similar data characteristics through transaction data characteristic extraction and matching; by comparing two business scenes generated by theoretical and actual analysis of the same transaction data, abnormal judgment of the transaction data can be realized, and by modifying abnormal transaction data, the error rate of the transaction data is reduced, and the working efficiency of transaction data processing is improved.
Further, according to the association degree value of the target service scene and the predicted service scene, judging whether the second transaction data is abnormal, specifically:
calculating the association degree value of each target service scene and each predicted service scene by using the service scene association degree value calculation model through a joint probability density function in sequence; when the association degree value is larger than a first threshold value, stopping calculating the association degree value, and generating a second transaction data normal result; and when all the association degree values are not greater than the first threshold value, generating a second transaction data abnormal result.
As a preferred scheme, the application analyzes the association degree of two business scenes generated by theoretical and practical analysis of the same transaction data through the joint probability density function, so as to judge whether the transaction data is abnormal, improve the accuracy of judging the abnormal transaction data and improve the working efficiency of transaction data processing.
Correspondingly, the application also provides a transaction data verification device, which comprises: the system comprises an interception module, a scene construction module and an abnormality judgment module;
the interception module is used for intercepting first transaction data in a first service system, and performing type analysis on the first transaction data to generate a corresponding service type; the first transaction data carries a user id identifier for the first transaction data; the first transaction data is generated by a user initiating a service request to a service system;
the scene construction module is used for acquiring corresponding transaction elements according to the service type of the second transaction data identified by the same user id and generating a target service scene; extracting features of second transaction data identified by the same user id to generate scene feature parameters; matching corresponding predicted service scenes according to the scene characteristic parameters; the predicted business scenario is stored in a scenario database;
the abnormality judging module is used for judging whether the second transaction data is abnormal or not according to the association degree value of the target service scene and the predicted service scene; if yes, the abnormal reminding information is sent to the first service system to inform corresponding service personnel to modify the configuration parameters of the second transaction data.
Further, the scene construction module includes: the target business scene construction unit and the predicted business scene construction unit;
the target business scene construction unit is used for determining a transaction element corresponding to each business type in the second transaction data by searching the mapping relation between the business type of the transaction data and the transaction element according to the business type set of the second transaction data identified by the same user id; the transaction element includes: one or more of transaction time, transaction period, transaction channel, transaction mode, and transaction target;
inputting the service type and the corresponding transaction elements into a scene construction model; generating at least one target business scene meeting the conditions according to each combination of the business type and the corresponding transaction elements;
the predicted business scene construction unit is used for extracting a feature expression vector of second transaction data identified by the same user id, calling a classification model to classify and identify the feature expression vector, generating scene type labels of the second transaction data, and taking the scene feature parameters and business parameter values in the second transaction data as scene feature parameters; the classification model is trained by a multi-label classifier on the characteristic expression vector of the historical transaction data and the corresponding scene type label;
and calculating the similarity value between the scene characteristic parameter and each scene characteristic in the predicted service scene in the scene database, and screening the predicted service scene of which the similarity value meets the preset range.
As a preferred scheme, the application intercepts transaction data in a service system through an interception module, performs type analysis on the transaction data, generates a theoretically feasible target service scene for the transaction data through a scene construction module, and generates a practically feasible predicted service scene through extraction and matching of characteristics of the transaction data; and carrying out association analysis on two business scenes generated by theoretical and practical analysis of the same transaction data through an abnormality judgment module, so as to judge whether the transaction data is abnormal. In addition, the transaction data of the same user id are identified, so that construction and anomaly analysis are realized aiming at the business scene of the same user, the accuracy of scene construction can be improved, and abnormal users can be quickly locked according to the abnormal transaction data; after the abnormal data is judged, the error rate of transaction data analysis of different configuration parameters is reduced by modifying the configuration parameters of the transaction data, so that the accuracy of the transaction data can be improved, and the working efficiency of transaction data processing can be improved.
Correspondingly, the embodiment of the application also provides computer equipment, which comprises a processor and a memory, wherein the memory is used for storing a computer program, and the computer program realizes the transaction data verification method when being executed by the processor.
Accordingly, the present application also provides a computer-readable storage medium including a stored computer program; wherein, the computer program controls the equipment of the computer readable storage medium to execute a transaction data verification method according to the application when running.
Drawings
FIG. 1 is a flow chart of an embodiment of a transaction data verification method provided by the present application;
fig. 2 is a schematic structural diagram of an embodiment of a transaction data verification device provided by 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.
Example 1
Referring to fig. 1, a transaction data verification method provided in an embodiment of the present application includes steps S101 to S103:
step S101: intercepting first transaction data in a first service system, and performing type analysis on the first transaction data to generate a corresponding service type; the first transaction data carries a user id identifier for the first transaction data; the first transaction data is generated by a user initiating a service request to a service system;
further, first transaction data in a first service system are intercepted, type analysis is carried out on the first transaction data, and a corresponding service type is generated, specifically:
when a service request event in a first service system is received in a preset time period, acquiring a user id and corresponding first transaction data in the service request event, and identifying the user id in the corresponding first transaction data; classifying the second transaction data identified by the same user id, and generating a service type set for the second transaction data identified by each user id.
In this embodiment, in a preset time period, after different users use different user ids to initiate service requests, corresponding transaction data is generated in a service system; the transaction data comprises transaction time, user id, transaction content, transaction mode and the like; transaction data in a preset time period are intercepted, the transaction data are identified according to user ids, and the transaction data identified by the same user id are classified into one type for exception analysis processing.
In this embodiment, the service type of the transaction data is determined according to the service request corresponding to each transaction data, a service type set is generated for the second transaction data identified by each user id, and the second transaction data identified by the same user id includes at least one service type.
Step S102: acquiring corresponding transaction elements according to the service type of the second transaction data identified by the same user id, and generating a target service scene; extracting features of second transaction data identified by the same user id to generate scene feature parameters; matching corresponding predicted service scenes according to the scene characteristic parameters; the predicted business scenario is stored in a scenario database;
further, according to the service type of the second transaction data identified by the same user id, a corresponding transaction element is obtained, and a target service scene is generated, specifically:
according to a service type set of second transaction data identified by the same user id, determining a transaction element corresponding to each service type in the second transaction data by searching a mapping relation between the service type of the transaction data and the transaction element; the transaction element includes: one or more of transaction time, transaction period, transaction channel, transaction mode, and transaction target;
inputting the service type and the corresponding transaction elements into a scene construction model; and generating at least one target business scene meeting the conditions according to each combination of the business type and the corresponding transaction elements.
Before the corresponding transaction elements are acquired, defining a mapping rule of the business types and the transaction elements in a database; setting a corresponding mapping rule for each service type data;
and a service type set of the second transaction data identified according to the same user id, wherein the service type set comprises at least one service type. And each business type data in the business type set is matched with a corresponding transaction element according to the mapping rule, each business type is matched with at least one transaction element, and a transaction element set of second transaction data with the same user id identification is generated.
Further, according to each combination of the service type and the corresponding transaction element, at least one target service scene meeting the conditions is generated, specifically:
determining model parameters of a scene construction model according to the service type and the corresponding transaction elements; clustering and fitting the model parameters according to historical transaction data and preset transaction rules to generate combination information of each model parameter combination; generating scene configuration data of each target service scene according to the combination information; and determining configuration service parameters of each target service scene according to the scene configuration data, and constructing a corresponding target service scene.
In this embodiment, according to the transaction element set of the second transaction data identified by the same user id, the model parameters of the scene construction model are set, and the scene construction model is used for constructing the transaction scene of the second transaction data identified by the same user id. Sequentially selecting different clustering centers according to historical transaction data and preset transaction rules by using a clustering algorithm to cluster each model parameter combination respectively, calculating the distance from each clustering sample to each clustering center, and updating the clustering centers according to the distances; and (3) continuously and iteratively calculating the distance between the clustering sample and the clustering center until the clustering center is not changed or is lower than a certain threshold value, and performing fitting analysis on the output data to obtain the combination information of each model parameter combination. In the process, according to historical transaction data and preset transaction rules, some model parameter combinations corresponding to the impossible transaction scenes are removed, the model calculation workload is reduced, and the scene construction accuracy is improved.
Further, feature extraction is performed on second transaction data identified by the same user id, scene feature parameters are generated, and corresponding predicted service scenes are matched according to the scene feature parameters, specifically:
extracting a feature expression vector of second transaction data identified by the same user id, calling a classification model to classify and identify the feature expression vector, generating a scene type label of the second transaction data, and taking the scene feature parameter and a service parameter value in the second transaction data as scene feature parameters; the classification model is trained by a multi-label classifier on the characteristic expression vector of the historical transaction data and the corresponding scene type label;
and calculating the similarity value between the scene characteristic parameter and each scene characteristic in the predicted service scene in the scene database, and screening the predicted service scene of which the similarity value meets the preset range.
In this embodiment, training the multi-tag classifier according to the feature expression vector of the historical transaction data and the corresponding scene type label thereof: inputting the historical transaction data into an initial multi-label classifier, outputting a predicted labeling value of each label of a training sample, calculating errors of the predicted labeling value and a real labeling value, and modifying each node parameter of the initial multi-label classifier until the errors of the calculated predicted labeling value and the real labeling value are lower than a preset threshold value, so as to obtain the trained multi-label classifier. The multi-label classifier is used for inputting the feature expression vector into each node, each path of each leaf node is a combination of different features, and each combination is subjected to predictive analysis to determine a scene type, so that at least one scene type conforming to transaction data is generated; and finally, combining the business parameter values in the second transaction data to generate corresponding scene characteristic parameters.
Step S103: judging whether the second transaction data is abnormal or not according to the association degree value of the target service scene and the predicted service scene; if yes, the abnormal reminding information is sent to the first service system to inform corresponding service personnel to modify the configuration parameters of the second transaction data.
Further, according to the association degree value of the target service scene and the predicted service scene, judging whether the second transaction data is abnormal, specifically:
calculating the association degree value of each target service scene and each predicted service scene by using the service scene association degree value calculation model through a joint probability density function in sequence; when the association degree value is larger than a first threshold value, stopping calculating the association degree value, and generating a second transaction data normal result; and when all the association degree values are not greater than the first threshold value, generating a second transaction data abnormal result.
The implementation of the embodiment of the application has the following effects:
the application generates a theoretically feasible target service scene by carrying out type analysis on the transaction data, and generates a practically feasible predicted service scene by extracting and matching characteristics of the transaction data; and judging whether the transaction data is abnormal or not by carrying out association analysis on two business scenes generated by theoretical and actual analysis of the same transaction data. In addition, the transaction data of the same user id are identified, so that construction and anomaly analysis are realized aiming at the business scene of the same user, the accuracy of scene construction can be improved, and abnormal users can be quickly locked according to the abnormal transaction data; after the abnormal data is judged, the error rate of transaction data analysis of different configuration parameters is reduced by modifying the configuration parameters of the transaction data, so that the accuracy of the transaction data can be improved, and the working efficiency of transaction data processing can be improved.
Example two
Referring to fig. 2, a transaction data verification device provided in an embodiment of the present application includes: an interception module 201, a scene construction module 202 and an abnormality judgment module 203;
the interception module 201 is configured to intercept first transaction data in a first service system, and perform type analysis on the first transaction data to generate a corresponding service type; the first transaction data carries a user id identifier for the first transaction data; the first transaction data is generated by a user initiating a service request to a service system;
the scene construction module 202 is configured to obtain corresponding transaction elements according to a service type of second transaction data identified by the same user id, and generate a target service scene; extracting features of second transaction data identified by the same user id to generate scene feature parameters; matching corresponding predicted service scenes according to the scene characteristic parameters; the predicted business scenario is stored in a scenario database;
the abnormality judging module 203 is configured to judge whether the second transaction data is abnormal according to the association value of the target service scenario and the predicted service scenario; if yes, the abnormal reminding information is sent to the first service system to inform corresponding service personnel to modify the configuration parameters of the second transaction data.
The interception module 201 includes: an acquisition unit and a classification unit;
the acquisition unit is used for acquiring a user id and corresponding first transaction data in a service request event in a first service system when the service request event is received in a preset time period, and identifying the user id in the corresponding first transaction data;
the classifying unit is used for classifying the second transaction data identified by the same user id and generating a service type set for the second transaction data identified by each user id.
The scene construction module 202 includes: the target business scene construction unit and the predicted business scene construction unit;
the target business scene construction unit is used for determining a transaction element corresponding to each business type in the second transaction data by searching the mapping relation between the business type of the transaction data and the transaction element according to the business type set of the second transaction data identified by the same user id; the transaction element includes: one or more of transaction time, transaction period, transaction channel, transaction mode, and transaction target;
inputting the service type and the corresponding transaction elements into a scene construction model; generating at least one target business scene meeting the conditions according to each combination of the business type and the corresponding transaction elements;
the predicted business scene construction unit is used for extracting a feature expression vector of second transaction data identified by the same user id, calling a classification model to classify and identify the feature expression vector, generating scene type labels of the second transaction data, and taking the scene feature parameters and business parameter values in the second transaction data as scene feature parameters; the classification model is trained by a multi-label classifier on the characteristic expression vector of the historical transaction data and the corresponding scene type label;
and calculating the similarity value between the scene characteristic parameter and each scene characteristic in the predicted service scene in the scene database, and screening the predicted service scene of which the similarity value meets the preset range.
The abnormality determination module 203 includes: a calculation unit and a judgment unit;
the computing unit is used for computing the relevance value of each target service scene and each predicted service scene by utilizing the service scene relevance value computing model and sequentially through a joint probability density function;
the judging unit is used for stopping the calculation of the association degree value when the association degree value is larger than a first threshold value, and generating a second transaction data normal result; and when all the association degree values are not greater than the first threshold value, generating a second transaction data abnormal result.
The transaction data verification device can implement the transaction data verification method of the method embodiment. The options in the method embodiments described above are also applicable to this embodiment and will not be described in detail here. The rest of the embodiments of the present application may refer to the content of the above method embodiments, and in this embodiment, no further description is given.
In addition, the embodiment of the application also provides a computer device, which comprises a processor and a memory, wherein the memory is used for storing a computer program, and the computer program is executed by the processor to realize the steps in any of the method embodiments.
The implementation of the embodiment of the application has the following effects:
according to the application, transaction data in a service system is intercepted by the interception module, the transaction data is subjected to type analysis, a theoretically feasible target service scene is generated for the transaction data by the scene construction module, and a practically feasible predicted service scene is generated by extracting and matching characteristics of the transaction data; and carrying out association analysis on two business scenes generated by theoretical and practical analysis of the same transaction data through an abnormality judgment module, so as to judge whether the transaction data is abnormal. In addition, the transaction data of the same user id are identified, so that construction and anomaly analysis are realized aiming at the business scene of the same user, the accuracy of scene construction can be improved, and abnormal users can be quickly locked according to the abnormal transaction data; after the abnormal data is judged, the error rate of transaction data analysis of different configuration parameters is reduced by modifying the configuration parameters of the transaction data, so that the accuracy of the transaction data can be improved, and the working efficiency of transaction data processing can be improved.
Example III
Correspondingly, the application further provides a computer readable storage medium, which comprises a stored computer program, wherein the computer program is used for controlling the equipment where the computer readable storage medium is located to execute the transaction data verification method according to any one of the embodiments.
The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present application, for example. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program in the terminal device.
The terminal equipment can be computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The terminal device may include, but is not limited to, a processor, a memory.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the terminal device, and which connects various parts of the entire terminal device using various interfaces and lines.
The memory may be used to store the computer program and/or the module, and the processor may implement various functions of the terminal device by running or executing the computer program and/or the module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the mobile terminal, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Wherein the terminal device integrated modules/units may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as stand alone products. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present application, and are not to be construed as limiting the scope of the application. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art without departing from the spirit and principles of the present application are intended to be included in the scope of the present application.
Claims (10)
1. A transaction data verification method, comprising:
intercepting first transaction data in a first service system, and performing type analysis on the first transaction data to generate a corresponding service type; the first transaction data carries a user id identifier for the first transaction data; the first transaction data is generated by a user initiating a service request to a service system;
acquiring corresponding transaction elements according to the service type of the second transaction data identified by the same user id, and generating a target service scene; extracting features of second transaction data identified by the same user id to generate scene feature parameters; matching corresponding predicted service scenes according to the scene characteristic parameters; the predicted business scenario is stored in a scenario database;
judging whether the second transaction data is abnormal or not according to the association degree value of the target service scene and the predicted service scene; if yes, the abnormal reminding information is sent to the first service system to inform corresponding service personnel to modify the configuration parameters of the second transaction data.
2. The method for verifying transaction data according to claim 1, wherein the intercepting the first transaction data in the first service system and performing type analysis on the first transaction data generate a corresponding service type specifically comprises:
when a service request event in a first service system is received in a preset time period, acquiring a user id and corresponding first transaction data in the service request event, and identifying the user id in the corresponding first transaction data; classifying the second transaction data identified by the same user id, and generating a service type set for the second transaction data identified by each user id.
3. The transaction data verification method according to claim 2, wherein the obtaining the corresponding transaction element according to the service type of the second transaction data identified by the same user id, and generating the target service scenario specifically includes:
according to a service type set of second transaction data identified by the same user id, determining a transaction element corresponding to each service type in the second transaction data by searching a mapping relation between the service type of the transaction data and the transaction element; the transaction element includes: one or more of transaction time, transaction period, transaction channel, transaction mode, and transaction target;
inputting the service type and the corresponding transaction elements into a scene construction model; and generating at least one target business scene meeting the conditions according to each combination of the business type and the corresponding transaction elements.
4. A transaction data verification method according to claim 3, wherein said generating at least one target business scenario meeting the conditions according to each combination of the business type and the corresponding transaction element comprises:
determining model parameters of a scene construction model according to the service type and the corresponding transaction elements; clustering and fitting the model parameters according to historical transaction data and preset transaction rules to generate combination information of each model parameter combination; generating scene configuration data of each target service scene according to the combination information; and determining configuration service parameters of each target service scene according to the scene configuration data, and constructing a corresponding target service scene.
5. The transaction data verification method according to claim 1, wherein the feature extraction is performed on the second transaction data identified by the same user id to generate scene feature parameters, and the matching of the corresponding predicted service scene is performed according to the scene feature parameters, specifically:
extracting a feature expression vector of second transaction data identified by the same user id, calling a classification model to classify and identify the feature expression vector, generating a scene type label of the second transaction data, and taking the scene feature parameter and a service parameter value in the second transaction data as scene feature parameters; the classification model is trained by a multi-label classifier on the characteristic expression vector of the historical transaction data and the corresponding scene type label;
and calculating the similarity value between the scene characteristic parameter and each scene characteristic in the predicted service scene in the scene database, and screening the predicted service scene of which the similarity value meets the preset range.
6. The method for verifying transaction data according to claim 5, wherein the determining whether the second transaction data is abnormal according to the association degree value of the target service scenario and the predicted service scenario is specifically:
calculating the association degree value of each target service scene and each predicted service scene by using the service scene association degree value calculation model through a joint probability density function in sequence; when the association degree value is larger than a first threshold value, stopping calculating the association degree value, and generating a second transaction data normal result; and when all the association degree values are not greater than the first threshold value, generating a second transaction data abnormal result.
7. A transaction data verification device, comprising: the system comprises an interception module, a scene construction module and an abnormality judgment module;
the interception module is used for intercepting first transaction data in a first service system, and performing type analysis on the first transaction data to generate a corresponding service type; the first transaction data carries a user id identifier for the first transaction data; the first transaction data is generated by a user initiating a service request to a service system;
the scene construction module is used for acquiring corresponding transaction elements according to the service type of the second transaction data identified by the same user id and generating a target service scene; extracting features of second transaction data identified by the same user id to generate scene feature parameters; matching corresponding predicted service scenes according to the scene characteristic parameters; the predicted business scenario is stored in a scenario database;
the abnormality judging module is used for judging whether the second transaction data is abnormal or not according to the association degree value of the target service scene and the predicted service scene; if yes, the abnormal reminding information is sent to the first service system to inform corresponding service personnel to modify the configuration parameters of the second transaction data.
8. The transaction data verification device of claim 7, wherein the scenario construction module comprises: the target business scene construction unit and the predicted business scene construction unit;
the target business scene construction unit is used for determining a transaction element corresponding to each business type in the second transaction data by searching the mapping relation between the business type of the transaction data and the transaction element according to the business type set of the second transaction data identified by the same user id; the transaction element includes: one or more of transaction time, transaction period, transaction channel, transaction mode, and transaction target;
inputting the service type and the corresponding transaction elements into a scene construction model; generating at least one target business scene meeting the conditions according to each combination of the business type and the corresponding transaction elements;
the predicted business scene construction unit is used for extracting a feature expression vector of second transaction data identified by the same user id, calling a classification model to classify and identify the feature expression vector, generating scene type labels of the second transaction data, and taking the scene feature parameters and business parameter values in the second transaction data as scene feature parameters; the classification model is trained by a multi-label classifier on the characteristic expression vector of the historical transaction data and the corresponding scene type label;
and calculating the similarity value between the scene characteristic parameter and each scene characteristic in the predicted service scene in the scene database, and screening the predicted service scene of which the similarity value meets the preset range.
9. A transaction data verification device comprising a processor and a memory for storing a computer program which when executed by the processor implements a transaction data verification method as claimed in any one of claims 1 to 6.
10. A computer readable storage medium, wherein the computer readable storage medium comprises a stored computer program; wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform a transaction data verification method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310788458.7A CN116843291A (en) | 2023-06-29 | 2023-06-29 | Transaction data verification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310788458.7A CN116843291A (en) | 2023-06-29 | 2023-06-29 | Transaction data verification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116843291A true CN116843291A (en) | 2023-10-03 |
Family
ID=88171963
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310788458.7A Pending CN116843291A (en) | 2023-06-29 | 2023-06-29 | Transaction data verification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116843291A (en) |
-
2023
- 2023-06-29 CN CN202310788458.7A patent/CN116843291A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107122369B (en) | Service data processing method, device and system | |
| CN107862425B (en) | Wind control data acquisition method, device and system and readable storage medium | |
| CN111814910B (en) | Abnormality detection method, abnormality detection device, electronic device, and storage medium | |
| CN112215288B (en) | Method and device for determining category of target enterprise, storage medium and electronic device | |
| CN113626241B (en) | Abnormality processing method, device, equipment and storage medium for application program | |
| WO2019179030A1 (en) | Product purchasing prediction method, server and storage medium | |
| CN111666346A (en) | Information merging method, transaction query method, device, computer and storage medium | |
| CN113282630B (en) | Data query method and device based on interface switching | |
| US20150170036A1 (en) | Determining document classification probabilistically through classification rule analysis | |
| CN114186626A (en) | Abnormity detection method and device, electronic equipment and computer readable medium | |
| CN113468520A (en) | Data intrusion detection method applied to block chain service and big data server | |
| US11829455B2 (en) | AI governance using tamper proof model metrics | |
| CN112883990A (en) | Data classification method and device, computer storage medium and electronic equipment | |
| CN114186760A (en) | Analysis method and system for stable operation of enterprise and readable storage medium | |
| WO2016188334A1 (en) | Method and device for processing application access data | |
| CN111210321B (en) | Risk early warning method and system based on contract management | |
| US20230169054A1 (en) | End-to-end identification of erroneous data using machine learning and similarity analysis | |
| CN109446054B (en) | Processing method and terminal equipment for override operation request based on big data | |
| CN110070383B (en) | Abnormal user identification method and device based on big data analysis | |
| CN109544348B (en) | Asset security screening method, device and computer readable storage medium | |
| CN113763057A (en) | User identity portrait data processing method and device | |
| CN115146653B (en) | Dialogue scenario construction method, device, equipment and storage medium | |
| CN116485019A (en) | Data processing method and device | |
| CN111277465A (en) | Abnormal data message detection method and device and electronic equipment | |
| CN116843291A (en) | Transaction data verification method, device, equipment and storage medium |
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 |