CN117522416A - Transaction account identification method and device - Google Patents
Transaction account identification method and device Download PDFInfo
- Publication number
- CN117522416A CN117522416A CN202311834063.2A CN202311834063A CN117522416A CN 117522416 A CN117522416 A CN 117522416A CN 202311834063 A CN202311834063 A CN 202311834063A CN 117522416 A CN117522416 A CN 117522416A
- Authority
- CN
- China
- Prior art keywords
- transaction
- sequence
- account
- dimensional
- pooling
- 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 53
- 238000011176 pooling Methods 0.000 claims abstract description 90
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 42
- 239000000203 mixture Substances 0.000 claims abstract description 16
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000006399 behavior Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 4
- 239000003999 initiator Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Computer Security & Cryptography (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The disclosure provides a transaction account identification method and device, and relates to the field of data processing, wherein the method comprises the following steps: acquiring transaction flow within a preset time range, wherein the transaction flow comprises a transaction account number, transaction time and transaction amount; generating a one-dimensional time sequence of the transaction accounts according to transaction running water of the transaction accounts in a preset time range for each transaction account; converting the one-dimensional time sequence of the transaction account into a two-dimensional tensor based on a plurality of periods; carrying out pooling treatment on the two-dimensional tensors of a plurality of periods, and determining a pooling sequence of the transaction account; updating the pooling sequence through a Gaussian mixture model; and determining probability values of the transaction account belonging to different account types according to the updated pooling sequence, and determining the account types of the transaction account according to the probability values. By the method, the one-dimensional time sequence of the transaction account is converted into a plurality of two-dimensional tensors, so that the change condition of the transaction account in the period and the period can be clarified, and the account type of the transaction account can be well determined.
Description
Technical Field
The disclosure relates to the field of data processing, and in particular relates to a method and a device for identifying a transaction account.
Background
With the continuous development of internet technology, the transaction behavior in the financial field is increasingly dependent on the internet, and electronic banking has become one of main competitive means of banking channels and marketing, and network electronic banking provides convenience for us and also provides a new channel for illegal transaction behavior. At present, illegal transaction means gradually develop to the specialized direction, so that the analysis difficulty of illegal transaction behaviors is increased.
According to the transaction time of the transaction behavior, time series data corresponding to the transaction behavior can be obtained, and analysis of illegal transaction behavior based on the time series is of great significance. The time series is usually a superposition of multiple processes and has a multi-period property, and for a certain period process, the time sequence variation in a period is not only related to adjacent time points in the period, but also related to adjacent periods, and two time sequence variations in the period and between periods are presented, but is limited by a one-dimensional structure inherent to the time series, and the time series is difficult to simultaneously present two different time sequence variations in the period and between periods.
Disclosure of Invention
The disclosure provides a method and a device for identifying a transaction account, which are used for at least solving the technical problems in the prior art.
According to a first aspect of the present disclosure, there is provided a method for identifying a transaction account, the method comprising: obtaining transaction running water within a preset time range, wherein the transaction running water comprises a transaction account number, transaction time and transaction amount; for each transaction account, generating a one-dimensional time sequence of the transaction account according to transaction running water of the transaction account in a preset time range; converting the one-dimensional time sequence of the transaction account number into a two-dimensional tensor based on a plurality of periods; pooling the two-dimensional tensors of the plurality of periods to determine a pooling sequence of the transaction account; updating the pooling sequence through a Gaussian mixture model; and determining probability values of the transaction account belonging to different account types according to the updated pooling sequence, and determining the account types of the transaction account according to the probability values.
In an embodiment, the converting the one-dimensional time series of the transaction account number into a two-dimensional tensor based on a plurality of periods includes: processing the one-dimensional time sequence through fast Fourier transform to determine a frequency sequence and a period sequence corresponding to the one-dimensional time sequence; based on the frequency sequence and the period sequence, the one-dimensional time sequence is converted into a plurality of two-dimensional tensors based on periods.
In an embodiment, the pooling the two-dimensional tensors of the plurality of periods, determining the pooling sequence of the transaction account includes: determining a pooling sequence of the transaction account number according to the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein said->Representing the pooling sequence, k being the number of the two-dimensional tensors, +.>Indicating the i-th period,/, is>Represents the j-th period,/, of>Two-dimensional tensor representing the i-th period, < ->Representing the mean pooling of the two-dimensional tensors.
In an embodiment, the updating the pooled sequence by the gaussian mixture model includes: updating the pooled sequence according to the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein,representing an updated pooling sequence, Q representing the total number of account types of the transaction account, and +.>Gaussian distribution representing the q-th account type, < ->Coefficients representing the q-th gaussian distribution, +.>For a pooled sequence of transaction accounts, +.>Is a learnable parameter.
In one embodiment, after obtaining the running water of the transaction within the preset time range, the method further comprises: preprocessing the transaction flow.
According to a second aspect of the present disclosure, there is provided an identification device of a transaction account, the device comprising: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring transaction running water within a preset time range, and the transaction running water comprises a transaction account number, transaction time and transaction amount; the generation module is used for generating a one-dimensional time sequence of the transaction account numbers according to the transaction flow of the transaction account numbers in a preset time range aiming at each transaction account number; the conversion module is used for converting the one-dimensional time sequence of the transaction account into a two-dimensional tensor based on a plurality of periods; the first processing module is used for carrying out pooling processing on the two-dimensional tensors of the plurality of periods and determining a pooling sequence of the transaction account; the updating module is used for updating the pooling sequence through a Gaussian mixture model; and the determining module is used for determining probability values of the transaction account belonging to different account types according to the updated pooling sequence, and determining the account types of the transaction account according to the probability values.
In one embodiment, the conversion module comprises: the processing submodule is used for processing the one-dimensional time sequence through fast Fourier transform and determining a frequency sequence and a period sequence corresponding to the one-dimensional time sequence; and the conversion submodule is used for converting the one-dimensional time sequence into a plurality of two-dimensional tensors based on the period based on the frequency sequence and the period sequence.
In an embodiment, the first processing module is specifically configured to determine the pooling sequence of the transaction account according to the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein said->Representing the pooling sequence, k being the number of the two-dimensional tensors, +.>Indicating the i-th period,/, is>Represents the j-th period,/, of>Two-dimensional tensor representing the i-th period, < ->Representing the mean pooling of the two-dimensional tensors.
In an embodiment, the updating module is specifically configured to update the pooled sequence according to the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing an updated pooling sequence, Q representing the total number of account types of the transaction account, and +.>Gaussian distribution representing the q-th account type, < ->Coefficients representing the q-th gaussian distribution, +.>For a pooled sequence of transaction accounts, +.>Is a learnable parameter.
In an embodiment, the device further comprises: and the second processing module is used for preprocessing the transaction flowing water after the transaction flowing water within the preset time range is acquired.
The method and the device for identifying the transaction account number acquire transaction flow within a preset time range, wherein the transaction flow comprises the transaction account number, transaction time and transaction amount; generating a one-dimensional time sequence of the transaction accounts according to transaction running water of the transaction accounts in a preset time range for each transaction account; converting the one-dimensional time sequence of the transaction account into a two-dimensional tensor based on a plurality of periods; carrying out pooling treatment on the two-dimensional tensors of a plurality of periods, and determining a pooling sequence of the transaction account; updating the pooling sequence through the Gaussian mixture model, determining probability values of the transaction account belonging to different account types according to the updated pooling sequence, and determining the account types of the transaction account according to the probability values. By the method, the one-dimensional time sequence of the transaction account is converted into a plurality of two-dimensional tensors, so that the change condition of the transaction account in the period and the period can be clarified, and the account type of the transaction account can be well determined.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Fig. 1 shows a schematic implementation flow diagram of a method for identifying a transaction account according to an embodiment of the disclosure;
fig. 2 illustrates a second implementation flow diagram of a method for identifying a transaction account according to an embodiment of the disclosure;
fig. 3 is a schematic block diagram of an identification device of a transaction account according to an embodiment of the disclosure;
fig. 4 shows a schematic diagram of a composition structure of an electronic device according to an embodiment of the disclosure.
Detailed Description
In order to make the objects, features and advantages of the present disclosure more comprehensible, the technical solutions in the embodiments of the present disclosure will be clearly described in conjunction with the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person skilled in the art would obtain without making any inventive effort are within the scope of protection of this disclosure.
Fig. 1 shows a schematic implementation flow diagram of a method for identifying a transaction account according to an embodiment of the disclosure, including:
step 101, obtaining a transaction flow within a preset time range, wherein the transaction flow comprises a transaction account number, transaction time and transaction amount.
Firstly, a transaction flow in a preset time range is obtained, transaction behaviors of transaction accounts are recorded by the transaction flow, the transaction flow comprises a transaction account, transaction time, transaction amount and the like, and the transaction account comprises a transaction account of both transaction parties, namely an account of a transaction initiator and an account of a transaction receiver. For example, in a transaction flow, an account A is an account of a transaction initiator, an account B is an account of a transaction receiver, and an account A and an account B are accounts of the transaction when an account A transfers M elements to an account B at a moment T, wherein the account A and the account B are accounts of the transaction account, the moment T is transaction time, and the M elements are transaction amounts. Because the transaction account number has uniqueness, a bank card number can be preferred as the transaction account number in the transaction stream. In addition, the preset time range may be determined according to an actual scene, and for example, a time range of three months, six months, one year, or the like may be selected as the preset time range.
Step 102, generating a one-dimensional time sequence of the transaction accounts according to the transaction running water of the transaction accounts within a preset time range for each transaction account.
According to all transaction running water in a preset time range, all transaction accounts in the preset time range are obtained, and for each transaction account, transaction running water related to the transaction account is determined, wherein the transaction running water related to the transaction account comprises the transaction running water with the transaction account as a transaction initiator, and also comprises the transaction running water with the transaction account as a transaction receiver, namely, the transaction running water related to the account comprises the transaction running water transferred into the transaction account and the transaction running water transferred out of the account. Generating a one-dimensional time sequence of the transaction account according to transaction running water of the transaction account in a preset time range, wherein the one-dimensional time sequence comprises n values, n is transaction time corresponding to all transaction running water in the preset time range, if the transaction account has an amount to be transferred in or out in the corresponding transaction time, the value corresponding to the transaction time in the one-dimensional time sequence of the transaction account is the transaction amount corresponding to the transaction time, if the transaction account has no amount to be transferred in or out in the corresponding transaction time, the value corresponding to the transaction time in the time sequence of the transaction account can be set to be a preset value, and in general, the preset value is 0 for convenient processing.
Each transaction account number can determine a corresponding one-dimensional time sequence according to the transaction flow related to the transaction account number.
It can be understood that in one embodiment, the transaction running water corresponding to the transaction account has a transaction running water transferred to the transaction account and a transaction running water transferred from the transaction account, so that if the transaction running water is transferred to the transaction account, a value corresponding to the transaction time in a one-dimensional time sequence of the transaction account can be determined as a corresponding transaction amount, and if the transaction running water is transferred from the transaction account, a value corresponding to the transaction time in the one-dimensional time sequence of the transaction account can be determined as a negative value of the corresponding transaction amount, so as to distinguish the transaction direction.
Step 103, converting the one-dimensional time sequence of the transaction account number into a two-dimensional tensor based on a plurality of periods.
The one-dimensional time sequence of the transaction account presents multicycle, a plurality of cycles are overlapped and influenced mutually, for each cycle, the change of the time point in the cycle is influenced by the change of the adjacent time point in the same cycle and is related to the change of the adjacent cycle, but the one-dimensional time sequence based on the time account is difficult to simultaneously represent two different time sequence changes in the cycle and in the period, so that the one-dimensional time sequence can be converted into two-dimensional tensors of a plurality of cycles, and the change in the cycle and in the period can be unified.
Step 104, pooling processing is carried out on the two-dimensional tensors of a plurality of periods, and a pooling sequence of the transaction account numbers is determined.
Because transaction running water of transaction accounts in the same period is generally higher in similarity, pooling processing is carried out on the two-dimensional tensors of each period, so that the transaction condition of the transaction accounts can be reflected, and the stability is higher. The pooling core adopted by the pooling process can be determined according to practical situations. And carrying out pooling treatment on the two-dimensional tensors in a period to obtain a pooling sequence of the transaction account, wherein the pooling sequence is a one-dimensional sequence, the data volume of the pooling sequence is reduced compared with that of the one-dimensional time sequence, and the pooling sequence is equivalent to the feature of retaining part of important transaction flowing water in the one-dimensional time sequence.
Step 105, updating the pooled sequence through a Gaussian mixture model.
The sequence features of the transaction accounts of the same type accord with Gaussian distribution, and the sequence features of the transaction accounts of different types accord with different Gaussian distribution, so that the pooling sequence of the transaction accounts can be updated according to the characteristics of data distribution, and the finally determined account types of the transaction accounts can be more accurate.
And 106, determining probability values of the transaction account belonging to different account types according to the updated pooling sequence, and determining the account types of the transaction account according to the probability values.
After the updated pooling sequence is obtained, performing linear transformation on the updated pooling sequence to obtain a target matrix, wherein the adopted linear transformation parameter matrix is a KxQ matrix, K is the dimension of the updated pooling sequence, Q is the account type, and the specific value of Q can be determined according to the account type set in an actual scene. Each value in the obtained target matrix represents the probability value that the transaction account belongs to the corresponding account type, the maximum probability value is determined for the obtained Q probability values, and the account type corresponding to the maximum probability value is determined as the account type corresponding to the transaction account.
According to the identification method of the transaction account numbers, transaction running water within a preset time range is firstly obtained, the transaction running water comprises transaction account numbers, transaction amounts and transaction time, for each transaction account number, a one-dimensional time sequence corresponding to the transaction account number is determined according to the transaction running water corresponding to the transaction account number, the one-dimensional time sequence is converted into two-dimensional tensors of a plurality of periods, after pooling processing is carried out on the two-dimensional tensors of the plurality of periods, a pooling sequence corresponding to the transaction account number is determined, after the pooling sequence of the transaction account number is processed through a Gaussian mixture model, probability values of the transaction account numbers for different account types are determined, and the account number types of the transaction account numbers are finally determined according to the obtained probability values. By the method, the one-dimensional time sequence of the transaction account is converted into a plurality of two-dimensional tensors, the change condition of the transaction account in the period and the period can be clarified, pooling processing and Gaussian mixture model processing are carried out based on the two-dimensional tensors, and the account type of the transaction account can be well determined.
In one embodiment, as shown in fig. 2, converting the one-dimensional time series of transaction accounts into a two-dimensional tensor based on a plurality of periods includes:
step 201, processing the one-dimensional time sequence through fast Fourier transform, and determining a frequency sequence and a period sequence corresponding to the one-dimensional time sequence;
step 202, converting the one-dimensional time series into a plurality of two-dimensional tensors based on the period based on the frequency series and the period series.
After a one-dimensional time sequence of the transaction account is obtained, the one-dimensional time sequence is processed through fast Fourier transform, the time sequence in the frequency domain is analyzed, and the period of the one-dimensional time sequence is discovered. Specifically, by the fast fourier transform formula) Wherein->Representing a one-dimensional time series of transaction accounts,representing the processing of the one-dimensional time sequence by means of a fast fourier transformation,/>Representing peaking of each waveform obtained from the fast fourier transform,/for each waveform>) The average value is obtained after the peak value of each waveform is obtained, and the frequency sequence F = { } corresponding to the one-dimensional time sequence is obtained>，/>…/>}, wherein->Representing the first frequency, +.>Representing the second frequency, +.>Representing the kth frequency.
Then according to the frequency and periodRelationship t=Frequency sequence determination periodic sequence P = { }>，/>…/>}, wherein->Representing the first period, +.>Representing the second period, +.>Representing the kth period.
Based on the obtained frequency sequence and period sequence, according to a dimension conversion formula:converting a one-dimensional time series of transaction accounts into a plurality of two-dimensional tensors, wherein，/>Representing the period +.>Dominant two-dimensional tensors. For each of the plurality of two-dimensional tensors, each column of the two-dimensional tensor represents a different frequency, and each row represents the same period.
In one embodiment, the pooling process is performed on two-dimensional tensors of a plurality of periods, and the pooling sequence of the transaction account number is determined, including: determining a pooling sequence of the transaction account number according to the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein,representing a pooling sequence, k being the number of two-dimensional tensors,/->Indicating the i-th period,/, is>Represents the j-th period,/, of>Two-dimensional tensor representing the i-th period, < ->Representing the mean pooling of the two-dimensional tensors.
Because transaction running water of transaction accounts in the same period is generally higher in similarity, pooling processing is carried out on the two-dimensional tensors of each period, so that the transaction condition of the transaction accounts can be reflected, and the stability is higher. The pooling core adopted by the pooling process can be determined according to practical situations. The pooling processing method adopted in the embodiment of the application is mean pooling processing, and the pooling processing is performed on the two-dimensional tensors of a plurality of periods, wherein the specific formula is as follows:wherein->Representing a pooling sequence, k being the number of two-dimensional tensors,/->Indicating the i-th period,/, is>Represents the j-th period,/, of>Two-dimensional tensor representing the ith period，/>Representing the mean pooling of the two-dimensional tensors. The pooling sequence is a one-dimensional sequence, the data volume of the pooling sequence is reduced compared with the data volume of the one-dimensional time sequence, and the pooling sequence is equivalent to the feature of retaining part of important transaction flow in the one-dimensional time sequence. It will be appreciated that other types of pooling methods may be selected depending on the circumstances.
In one embodiment, updating the pooled sequence by a gaussian mixture model comprises: updating the pooled sequence according to the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing an updated pooling sequence, Q representing the total number of account types of the transaction account, and +.>Gaussian distribution representing the q-th account type, < ->Coefficients representing the q-th gaussian distribution, +.>For a pooled sequence of transaction accounts, +.>Is a learnable parameter.
The sequence features of the transaction accounts of the same type conform to Gaussian distribution, and the sequence features of the transaction accounts of different types conform to different Gaussian distribution. Therefore, the pooling sequence of the transaction account can be updated according to the Gaussian distribution condition of the data, and a specific Gaussian mixture model formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>The updated pooling sequence is represented, Q represents the total number of account types of the transaction account, and the specific value of the account can be determined according to an actual scene, for example, when the nodes are divided into two types of normal nodes and abnormal nodes, the value of Q is 2; when the transaction account numbers are classified in more detail in the actual application scene, the corresponding Q values are the types of the transaction account numbers. />Gaussian distribution representing the q-th account type, < ->A coefficient representing the q-th Gaussian distribution, and +.>=1；/>For a pooled sequence of transaction accounts,is a learnable parameter. The pooling sequence is updated through the Gaussian mixture model, so that the account type of the finally determined transaction account can be more accurate.
In one embodiment, after obtaining the transaction flowing water within the preset time range, the method further includes: preprocessing transaction flowing water.
Because the transaction flow may include some transaction flows with transaction failures, after the transaction flow within the preset time range is acquired, in order to analyze the transaction account more accurately, the transaction flow needs to be cleaned first to remove the transaction flow with transaction failures.
Fig. 3 is a schematic block diagram of an identification device of a transaction account according to an embodiment of the disclosure.
Referring to fig. 3, according to a second aspect of an embodiment of the present disclosure, there is provided an identification apparatus for a transaction account, the apparatus including: the obtaining module 301 is configured to obtain a transaction arrangement within a preset time range, where the transaction arrangement includes a transaction account number, a transaction time, and a transaction amount; the generating module 302 is configured to generate, for each transaction account, a one-dimensional time sequence of the transaction accounts according to the transaction running water of the transaction account within a preset time range; a conversion module 303, configured to convert a one-dimensional time sequence of transaction accounts into a two-dimensional tensor based on a plurality of periods; the first processing module 304 is configured to perform pooling processing on the two-dimensional tensors in multiple periods, and determine a pooling sequence of the transaction account; an updating module 305, configured to update the pooled sequence through a gaussian mixture model; the determining module 306 is configured to determine probability values of the transaction account belonging to different account types according to the updated pooling sequence, and determine account types of the transaction account according to the probability values.
In one embodiment, the conversion module 303 comprises: a processing sub-module 3031, configured to process the one-dimensional time sequence by using a fast fourier transform, and determine a frequency sequence and a period sequence corresponding to the one-dimensional time sequence; a conversion submodule 3032 for converting the one-dimensional time series into a plurality of two-dimensional tensors based on the period based on the frequency series and the period series.
In an embodiment, the first processing module 304 is specifically configured to determine the pooling sequence of the transaction account according to the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a pooling sequence, k being the number of two-dimensional tensors,/->Indicating the i-th period,/, is>Represents the j-th period,/, of>Two-dimensional tensor representing the i-th period, < ->Representing pairs of two dimensionsTensors are averaged and pooled.
In one embodiment, the updating module 305 is specifically configured to update the pooled sequence according to the following formula:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing an updated pooling sequence, Q representing the total number of account types of the transaction account, and +.>Gaussian distribution representing the q-th account type, < ->Coefficients representing the q-th gaussian distribution, +.>For a pooled sequence of transaction accounts, +.>Is a learnable parameter.
In an embodiment, the apparatus further comprises: the second processing module 307 is configured to pre-process the transaction flowing water after obtaining the transaction flowing water within the preset time range.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.
Fig. 4 illustrates a schematic block diagram of an example electronic device 400 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 4, the apparatus 400 includes a computing unit 401 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 402 or a computer program loaded from a storage unit 408 into a Random Access Memory (RAM) 403. In RAM 403, various programs and data required for the operation of device 400 may also be stored. The computing unit 401, ROM 402, and RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
Various components in device 400 are connected to I/O interface 405, including: an input unit 406 such as a keyboard, a mouse, etc.; an output unit 407 such as various types of displays, speakers, and the like; a storage unit 408, such as a magnetic disk, optical disk, etc.; and a communication unit 409 such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 401 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as a transaction account identification method. For example, in some embodiments, a method of identifying a transaction account number may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 400 via the ROM 402 and/or the communication unit 409. When the computer program is loaded into RAM 403 and executed by computing unit 401, one or more steps of one of the transaction account identification methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform a transaction account identification method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The foregoing is merely specific embodiments of the disclosure, but the protection scope of the disclosure is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the disclosure, and it is intended to cover the scope of the disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (10)
1. A method for identifying a transaction account, the method comprising:
obtaining transaction running water within a preset time range, wherein the transaction running water comprises a transaction account number, transaction time and transaction amount;
for each transaction account, generating a one-dimensional time sequence of the transaction account according to transaction running water of the transaction account in a preset time range;
converting the one-dimensional time sequence of the transaction account number into a two-dimensional tensor based on a plurality of periods;
pooling the two-dimensional tensors of the plurality of periods to determine a pooling sequence of the transaction account;
updating the pooling sequence through a Gaussian mixture model;
and determining probability values of the transaction account belonging to different account types according to the updated pooling sequence, and determining the account types of the transaction account according to the probability values.
2. The method of claim 1, wherein the converting the one-dimensional time series of transaction accounts into a two-dimensional tensor based on a plurality of cycles comprises:
processing the one-dimensional time sequence through fast Fourier transform to determine a frequency sequence and a period sequence corresponding to the one-dimensional time sequence;
based on the frequency sequence and the period sequence, the one-dimensional time sequence is converted into a plurality of two-dimensional tensors based on periods.
3. The method of claim 1, wherein the pooling the two-dimensional tensors for the plurality of cycles to determine the pooling sequence of the transaction account number comprises:
determining a pooling sequence of the transaction account number according to the following formula:
；
wherein the saidRepresenting the pooling sequence, k being the number of the two-dimensional tensors, +.>Representation ofI th period, +.>Represents the j-th period,/, of>Two-dimensional tensor representing the i-th period, < ->Representing the mean pooling of the two-dimensional tensors.
4. The method of claim 1, wherein the updating the pooled sequence by a gaussian mixture model comprises:
updating the pooled sequence according to the following formula:
；
wherein,represents an updated pooling sequence, Q represents the total number of account types of the transaction account,gaussian distribution representing the q-th account type, < ->Coefficients representing the q-th gaussian distribution, +.>For a pooled sequence of transaction accounts, +.>Is a learnable parameter.
5. The method of claim 1, wherein after acquiring the flowing water of the transaction within the preset time frame, the method further comprises:
preprocessing the transaction flow.
6. An apparatus for identifying a transaction account, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring transaction running water within a preset time range, and the transaction running water comprises a transaction account number, transaction time and transaction amount;
the generation module is used for generating a one-dimensional time sequence of the transaction account numbers according to the transaction flow of the transaction account numbers in a preset time range aiming at each transaction account number;
the conversion module is used for converting the one-dimensional time sequence of the transaction account into a two-dimensional tensor based on a plurality of periods;
the first processing module is used for carrying out pooling processing on the two-dimensional tensors of the plurality of periods and determining a pooling sequence of the transaction account;
the updating module is used for updating the pooling sequence through a Gaussian mixture model;
and the determining module is used for determining probability values of the transaction account belonging to different account types according to the updated pooling sequence, and determining the account types of the transaction account according to the probability values.
7. The apparatus of claim 6, wherein the conversion module comprises:
the processing submodule is used for processing the one-dimensional time sequence through fast Fourier transform and determining a frequency sequence and a period sequence corresponding to the one-dimensional time sequence;
and the conversion submodule is used for converting the one-dimensional time sequence into a plurality of two-dimensional tensors based on the period based on the frequency sequence and the period sequence.
8. The apparatus according to claim 6, wherein the first processing module is configured to determine the pooling sequence of the transaction account number according to the following formula:
；
wherein the saidRepresenting the pooling sequence, k being the number of the two-dimensional tensors, +.>Indicating the i-th period,/, is>Represents the j-th period,/, of>Two-dimensional tensor representing the i-th period, < ->Representing the mean pooling of the two-dimensional tensors.
9. The apparatus according to claim 6, wherein the updating module is configured to update the pooled sequence according to the following formula:
；
wherein,represents an updated pooling sequence, Q represents the total number of account types of the transaction account,gaussian distribution representing the q-th account type, < ->Coefficients representing the q-th gaussian distribution, +.>For a pooled sequence of transaction accounts, +.>Is a learnable parameter.
10. The apparatus of claim 6, wherein the apparatus further comprises:
and the second processing module is used for preprocessing the transaction flowing water after the transaction flowing water within the preset time range is acquired.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311834063.2A CN117522416A (en) | 2023-12-28 | 2023-12-28 | Transaction account identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311834063.2A CN117522416A (en) | 2023-12-28 | 2023-12-28 | Transaction account identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117522416A true CN117522416A (en) | 2024-02-06 |
Family
ID=89756969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311834063.2A Pending CN117522416A (en) | 2023-12-28 | 2023-12-28 | Transaction account identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117522416A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165950A (en) * | 2018-08-10 | 2019-01-08 | 哈尔滨工业大学（威海） | A kind of abnormal transaction identification method based on financial time series feature, equipment and readable storage medium storing program for executing |
| US20190327259A1 (en) * | 2018-04-24 | 2019-10-24 | Jungle Disk, L.L.C. | Vulnerability profiling based on time series analysis of data streams |
| CN112487406A (en) * | 2020-12-02 | 2021-03-12 | 中国电子科技集团公司第三十研究所 | Network behavior analysis method based on machine learning |
| CN115358838A (en) * | 2022-08-22 | 2022-11-18 | 晋商消费金融股份有限公司 | Credit time series data modeling method and device based on convolutional neural network |
| CN115564466A (en) * | 2022-08-15 | 2023-01-03 | 四川大学 | Double-layer day-ahead electricity price prediction method based on calibration window integration and coupled market characteristics |
| CN116050595A (en) * | 2022-12-29 | 2023-05-02 | 烟台新旧动能转换研究院暨烟台科技成果转移转化示范基地 | Attention mechanism and decomposition mechanism coupled runoff amount prediction method |
| US20230143484A1 (en) * | 2021-05-24 | 2023-05-11 | Visa International Service Association | System, Method, and Computer Program Product for Analyzing Multivariate Time Series Using a Convolutional Fourier Network |
| CN116579447A (en) * | 2022-12-15 | 2023-08-11 | 重庆邮电大学 | Time sequence prediction method based on decomposition mechanism and attention mechanism |
| CN117056695A (en) * | 2023-07-25 | 2023-11-14 | 北京百度网讯科技有限公司 | Transaction data prediction method, training method, device and equipment of prediction model |
-
2023
- 2023-12-28 CN CN202311834063.2A patent/CN117522416A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190327259A1 (en) * | 2018-04-24 | 2019-10-24 | Jungle Disk, L.L.C. | Vulnerability profiling based on time series analysis of data streams |
| CN109165950A (en) * | 2018-08-10 | 2019-01-08 | 哈尔滨工业大学（威海） | A kind of abnormal transaction identification method based on financial time series feature, equipment and readable storage medium storing program for executing |
| CN112487406A (en) * | 2020-12-02 | 2021-03-12 | 中国电子科技集团公司第三十研究所 | Network behavior analysis method based on machine learning |
| US20230143484A1 (en) * | 2021-05-24 | 2023-05-11 | Visa International Service Association | System, Method, and Computer Program Product for Analyzing Multivariate Time Series Using a Convolutional Fourier Network |
| CN115564466A (en) * | 2022-08-15 | 2023-01-03 | 四川大学 | Double-layer day-ahead electricity price prediction method based on calibration window integration and coupled market characteristics |
| CN115358838A (en) * | 2022-08-22 | 2022-11-18 | 晋商消费金融股份有限公司 | Credit time series data modeling method and device based on convolutional neural network |
| CN116579447A (en) * | 2022-12-15 | 2023-08-11 | 重庆邮电大学 | Time sequence prediction method based on decomposition mechanism and attention mechanism |
| CN116050595A (en) * | 2022-12-29 | 2023-05-02 | 烟台新旧动能转换研究院暨烟台科技成果转移转化示范基地 | Attention mechanism and decomposition mechanism coupled runoff amount prediction method |
| CN117056695A (en) * | 2023-07-25 | 2023-11-14 | 北京百度网讯科技有限公司 | Transaction data prediction method, training method, device and equipment of prediction model |
Non-Patent Citations (4)
| Title |
|---|
| 吕云翔 等: "《机器学习原理及应用》", 31 August 2021, 北京机械工业出版社, pages: 68 * |
| 王贝伦: "《机器学习》", 30 November 2021, 南京东南大学出版社, pages: 261 * |
| 羽星_S: "TimesNet：用于一般时间序列分析的时间二维变化模型", pages 1 - 9, Retrieved from the Internet <URL:https://blog.csdn.net/qq_20144897/article/details/130656319> * |
| 郭军 等: "《人工智能导论》", 31 October 2021, 北京邮电大学出版社, pages: 9 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113360580B (en) | Abnormal event detection method, device, equipment and medium based on knowledge graph | |
| CN111814910B (en) | Abnormality detection method, abnormality detection device, electronic device, and storage medium | |
| CN113627361B (en) | Training method and device for face recognition model and computer program product | |
| CN117593115A (en) | Feature value determining method, device, equipment and medium of credit risk assessment model | |
| CN116383708B (en) | Transaction account identification method and device | |
| CN115982664A (en) | Abnormal account identification method, device, equipment and storage medium | |
| CN114741433B (en) | Community mining method, device, equipment and storage medium | |
| CN117522416A (en) | Transaction account identification method and device | |
| CN112541557B (en) | Training method and device for generating countermeasure network and electronic equipment | |
| CN115641481A (en) | Method and device for training image processing model and image processing | |
| CN113313049A (en) | Method, device, equipment, storage medium and computer program product for determining hyper-parameters | |
| CN113553407B (en) | Event tracing method and device, electronic equipment and storage medium | |
| CN115471717B (en) | Semi-supervised training and classifying method device, equipment, medium and product of model | |
| CN118037472B (en) | Financial data processing method and related device | |
| CN112214387B (en) | Knowledge graph-based user operation behavior prediction method and device | |
| CN115511047B (en) | Quantification method, device, equipment and medium of Softmax model | |
| CN118094444A (en) | Abnormal account detection model training method and device, electronic equipment and storage medium | |
| CN116684063A (en) | Detection method, detection device, detection equipment and storage medium | |
| CN116167519A (en) | Monitoring amount prediction method, device, equipment and medium | |
| CN117272381A (en) | Desensitization method, device, equipment and medium for sensitive data | |
| CN116342253A (en) | Loan risk scoring method, device, equipment and storage medium | |
| CN115600129A (en) | Information identification method and device, electronic equipment and storage medium | |
| CN115810343A (en) | Voice recognition method and device, electronic equipment and storage medium | |
| Pradana et al. | Identifying Thresholds for Similarity-Based Class Cohesion (SCC) Metrics | |
| CN113033658A (en) | Merchant classification method and device, electronic equipment and 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 |