CN117314639A - Processing method and device of fund account, storage medium and electronic equipment - Google Patents
Processing method and device of fund account, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN117314639A CN117314639A CN202311282759.9A CN202311282759A CN117314639A CN 117314639 A CN117314639 A CN 117314639A CN 202311282759 A CN202311282759 A CN 202311282759A CN 117314639 A CN117314639 A CN 117314639A
- Authority
- CN
- China
- Prior art keywords
- map
- funds
- fund
- account
- accounts
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 53
- 239000013598 vector Substances 0.000 claims description 117
- 238000004422 calculation algorithm Methods 0.000 claims description 116
- 238000012545 processing Methods 0.000 claims description 61
- 238000001228 spectrum Methods 0.000 claims description 50
- 230000006870 function Effects 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 30
- 238000010276 construction Methods 0.000 claims description 16
- 238000005065 mining Methods 0.000 abstract description 13
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012954 risk control Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a processing method and device of a fund account, a storage medium and electronic equipment. Relates to the artificial intelligence field, the financial science field and the other related technical fields, and the method comprises the following steps: acquiring a plurality of first funds accounts, and determining a plurality of first funds account groups and a first map corresponding to each first funds account group according to funds exchange among the plurality of first funds accounts, wherein the first funds account groups are composed of the plurality of first funds accounts; acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk; and judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map, and obtaining a judging result. According to the method and the device, the problem that in the related art, the group account with transaction risk is mined through simple logic rules, so that the accuracy rate of mining the group account is low is solved.
Description
Technical Field
The present application relates to the field of artificial intelligence, financial science and technology, and other related technical fields, and in particular, to a method and apparatus for processing a fund account, a storage medium, and an electronic device.
Background
In the field of financial risk control, there is often a situation that a group account with transaction risk is found in time and core members of the group account are found to control in the process of risk control, so as to cover risk exposure and reduce risk level.
Most of the existing group account mining is a supervised group account, namely, a negative sample is used for carrying out label marking treatment according to media such as certificates, equipment, mobile phone numbers and the like; or an unsupervised community discovery algorithm, and takes certificates, equipment and the like as the same as the basis of the continuous edge during composition. When the fund group account is mined, whether the fund relationship exists between two accounts or not is often used, or a simple rule such as 'amount greater than 100 yuan' is used as a screening condition to carry out the borderline composition of the fund relationship after the hot spot is eliminated.
Aiming at the problem that the mining of the group accounts with transaction risks is carried out through simple logic rules in the related art, so that the mining accuracy of the group accounts is lower, no effective solution is proposed at present.
Disclosure of Invention
The main purpose of the application is to provide a processing method and device of fund accounts, a storage medium and electronic equipment, so as to solve the problem that in the related art, the accuracy rate of mining the group accounts is lower due to the fact that the mining of the group accounts with transaction risks is performed through simple logic rules.
To achieve the above object, according to one aspect of the present application, there is provided a method of processing a fund account. The method comprises the following steps: acquiring a plurality of first funds accounts, and determining a plurality of first funds account groups and a first map corresponding to each first funds account group according to funds traffic among the plurality of first funds accounts, wherein the first funds account groups are composed of a plurality of first funds accounts; acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk; judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map to obtain a judging result, wherein the judging result represents whether the first fund account groups are fund account groups with transaction risks.
Further, determining a plurality of first funds account groups and a first map corresponding to each first funds account group according to funds transactions between the plurality of first funds accounts includes: performing map construction according to the funds of the plurality of first funds accounts to obtain an initial map; and determining the first funds account groups and the first atlas corresponding to each first funds account group according to the initial atlas and the community finding algorithm.
Further, before determining whether the plurality of first funds account groups have transaction risk according to the similarity between the first map and the second map, the method further includes: processing the first map through a map embedding algorithm to obtain a first embedded vector set corresponding to the first map; processing the second map through the map embedding algorithm to obtain a second embedded vector set corresponding to the second map; and calculating according to the first embedded vector set and the second embedded vector set to obtain the similarity between the first map and the second map.
Further, processing the first map through a map embedding algorithm, and obtaining a first embedded vector set corresponding to the first map includes: traversing the first map through the map embedding algorithm to obtain a plurality of first sub-maps; encoding the plurality of first sub-spectrums by the graph embedding algorithm to obtain a first embedded vector corresponding to each first sub-spectrum; and determining the first embedded vector set according to the first embedded vector corresponding to each first sub-graph.
Further, performing a graph construction according to the funds transaction among the plurality of first funds accounts, and obtaining an initial graph includes: determining nodes of the map according to the plurality of first fund accounts; acquiring fund transaction information among the plurality of first fund accounts, and determining edges of the map according to the fund transaction information; and constructing the spectrum according to the nodes of the spectrum and the edges of the spectrum to obtain the initial spectrum.
Further, performing calculation according to the first embedded vector set and the second embedded vector set, to obtain a similarity between the first map and the second map includes: calculating Euclidean distance between a first embedded vector in the first embedded vector set and a second embedded vector in the second embedded vector set to obtain a target Euclidean distance; and determining the target Euclidean distance as the similarity between the first map and the second map.
Further, according to the similarity between the first map and the second map, determining whether the plurality of first funds account groups have transaction risk, and obtaining the determination result includes: judging whether the similarity between the first map and the second map is smaller than a preset threshold value or not; if the similarity is smaller than the preset threshold, determining that the first fund account group is a fund account group with transaction risk; and if the similarity is greater than or equal to the preset threshold, determining that the first fund account group is not the fund account group with transaction risk.
Further, before the first map is processed through a map embedding algorithm to obtain a first embedded vector set corresponding to the first map, the method further includes: acquiring a plurality of third maps constructed based on funds transactions between the plurality of second funds accounts; traversing the plurality of third patterns through an initial pattern embedding algorithm to obtain a plurality of third sub-patterns corresponding to each third pattern; and carrying out iterative training on the initial graph embedding algorithm according to the plurality of third sub-graphs and an objective function to obtain the graph embedding algorithm, wherein the objective function is used for calculating the probability of the third sub-graphs in the third graphs.
Further, performing iterative training on the initial graph embedding algorithm according to the plurality of third sub-graphs and the objective function, and obtaining the graph embedding algorithm includes: constructing a plurality of fourth sub-maps corresponding to each third map according to the third maps, wherein the probability of the fourth sub-map appearing in the third map is 0; and carrying out iterative training on the initial graph embedding algorithm according to the fourth sub-graphs, the third sub-graphs and the objective function to obtain the graph embedding algorithm.
To achieve the above object, according to another aspect of the present application, there is provided a processing apparatus for a funds account. The device comprises: the first acquisition unit is used for acquiring a plurality of first fund accounts, and determining a plurality of first fund account groups and a first map corresponding to each first fund account group according to fund transactions among the plurality of first fund accounts, wherein the first fund account groups consist of a plurality of first fund accounts; the second acquisition unit is used for acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk; and the judging unit is used for judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map to obtain a judging result, wherein the judging result represents whether the first fund account groups are fund account groups with transaction risks.
Further, the first acquisition unit includes: the first construction subunit is used for constructing a map according to the funds of the plurality of first funds accounts; and the first determining subunit is used for determining the first funds account groups and the first atlas corresponding to each first funds account group according to the initial atlas and the community finding algorithm.
Further, the apparatus further comprises: the first processing unit is used for judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first atlas and the second atlas, and processing the first atlas through an image embedding algorithm before a judgment result is obtained to obtain a first embedding vector set corresponding to the first atlas; the second processing unit is used for processing the second map through the map embedding algorithm to obtain a second embedded vector set corresponding to the second map; and the calculation unit is used for calculating according to the first embedded vector set and the second embedded vector set to obtain the similarity between the first map and the second map.
Further, the first processing unit includes: the traversing subunit is used for traversing the first atlas through the graph embedding algorithm to obtain a plurality of first sub atlas; the coding subunit is used for coding the plurality of first sub-spectrums through the graph embedding algorithm to obtain a first embedded vector corresponding to each first sub-spectrum; and the second determining subunit is used for determining the first embedded vector set according to the first embedded vector corresponding to each first sub-spectrum.
Further, the constructing subunit includes: the determining module is used for determining nodes of the map according to the plurality of first fund accounts; the acquisition module is used for acquiring the fund business information among the plurality of first fund accounts and determining the edges of the map according to the fund business information; and the construction module is used for constructing the map according to the nodes of the map and the edges of the map to obtain the initial map.
Further, the calculation unit includes: a calculating subunit, configured to calculate a euclidean distance between a first embedded vector in the first embedded vector set and a second embedded vector in the second embedded vector set, to obtain a target euclidean distance; and a third determining subunit configured to determine the target euclidean distance as a similarity between the first map and the second map.
Further, the judging unit includes: the judging subunit is used for judging whether the similarity between the first map and the second map is smaller than a preset threshold value or not; a fourth determining subunit, configured to determine that the first fund account group is a fund account group with transaction risk if the similarity is smaller than the preset threshold; and a fifth determining subunit, configured to determine that the first fund account group is not a fund account group with transaction risk if the similarity is greater than or equal to the preset threshold.
Further, the apparatus further comprises: the third acquisition unit is used for acquiring a plurality of third maps constructed based on the fund transaction among a plurality of second fund accounts before the first maps are processed through a map embedding algorithm to obtain a first embedded vector set corresponding to the first maps; the traversing unit is used for traversing the plurality of third patterns through an initial pattern embedding algorithm to obtain a plurality of third sub-patterns corresponding to each third pattern; and the training unit is used for carrying out iterative training on the initial graph embedding algorithm according to the plurality of third sub-graphs and an objective function to obtain the graph embedding algorithm, wherein the objective function is used for calculating the probability of the third sub-graphs in the third graphs.
Further, the training unit includes: a second construction subunit, configured to construct a plurality of fourth sub-maps corresponding to each third map according to the plurality of third maps, where a probability that the fourth sub-map appears in the third map is 0; and the training subunit is used for carrying out iterative training on the initial graph embedding algorithm according to the plurality of fourth sub-graphs, the plurality of third sub-graphs and the objective function to obtain the graph embedding algorithm.
To achieve the above object, according to an aspect of the present application, there is provided a computer-readable storage medium storing a program, wherein the program, when run, controls a device in which the storage medium is located to execute the method for processing a fund account of any one of the above.
To achieve the above object, according to another aspect of the present application, there is also provided an electronic device, including one or more processors and a memory for storing a processing method for the one or more processors to implement the fund account described in any one of the above.
Through the application, the following steps are adopted: acquiring a plurality of first funds accounts, and determining a plurality of first funds account groups and a first map corresponding to each first funds account group according to funds exchange among the plurality of first funds accounts, wherein the first funds account groups are composed of the plurality of first funds accounts; acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk; judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first atlas and the second atlas to obtain a judging result, wherein the judging result represents whether the first fund account groups are the fund account groups with the transaction risks, and the problem that the accuracy rate of excavating the group accounts is lower due to the fact that the group accounts with the transaction risks are excavated through simple logic rules in the related technology is solved. In the scheme, the association relation between the first funds accounts is accurately described through the patterns, the first funds account groups possibly having transaction risks and the first patterns corresponding to each first funds account group are obtained through the patterns, and then whether the first funds account groups have transaction risks or not is accurately judged through the second patterns corresponding to the second funds account groups with determined transaction risks, so that the effect of improving the accuracy of mining the group accounts is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of a method of processing a funds account provided in accordance with embodiments of the application;
FIG. 2 is a flow chart of an alternative method of processing a funds account provided in accordance with embodiments of the application;
FIG. 3 is a schematic diagram of a processing device for a funds account provided in accordance with embodiments of the application;
fig. 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of description, the following will describe some terms or terms related to the embodiments of the present application:
graph embedding: graph Embedding (also called Network Embedding) is a process of mapping Graph data (usually a high-dimensional dense matrix) into low-micro dense vectors, and can well solve the problem that the Graph data is difficult to input into a machine learning algorithm efficiently.
It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.
The invention will now be described in connection with preferred embodiments, and FIG. 1 is a flow chart of a method for processing a funds account provided in accordance with embodiments of the application, as shown in FIG. 1, the method comprising the steps of:
step S101, a plurality of first fund accounts are obtained, and a plurality of first fund account groups and a first map corresponding to each first fund account group are determined according to fund transactions among the plurality of first fund accounts, wherein the first fund account groups are composed of the plurality of first fund accounts.
Optionally, determining a range in which risk group account mining is required, then acquiring the first funds accounts and the funds exchange information between the funds accounts according to the range, and determining a first map corresponding to the first funds accounts and each first funds account group by using the funds exchange information, wherein the first funds account group is a funds account group possibly having transaction risk.
Step S102, a second map corresponding to a second fund account group is acquired, wherein the second fund account group is a fund account group with transaction risk.
Optionally, a second profile corresponding to the second group of funds accounts that has been determined to have a risk of transaction is obtained and a similarity between the first profile and the second profile is calculated.
Step S103, judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map to obtain a judging result, wherein the judging result represents whether the first fund account groups are the fund account groups having the transaction risks.
Optionally, the transaction risk of the first fund account group is judged according to the similarity between the first map and the second map, and whether the first fund account group is the fund account group with the transaction risk is determined.
In summary, the association relationship between the first funds accounts is accurately described through the atlas, the first funds account group which may have transaction risk and the first atlas corresponding to each first funds account group are obtained through the atlas, and then whether the first funds account group has transaction risk or not is accurately judged through the second atlas corresponding to the second funds account group which has determined transaction risk, so that the effect of improving the accuracy of the excavation of the group accounts is achieved.
Optionally, in the method for processing a funds account provided in the embodiment of the present application, determining, according to funds between the plurality of first funds accounts, a plurality of first funds account groups and a first map corresponding to each first funds account group includes: performing map construction according to the funds of the plurality of first funds accounts to obtain an initial map; and determining a plurality of first fund account groups and first maps corresponding to each first fund account group according to the initial maps and the community finding algorithm.
Performing map construction according to funds exchange among a plurality of first funds accounts, wherein obtaining an initial map comprises: determining nodes of the map according to the plurality of first fund accounts; acquiring fund transaction information among a plurality of first fund accounts, and determining edges of the map according to the fund transaction information; and constructing the map according to the nodes of the map and the sides of the map to obtain an initial map.
Optionally, the following steps are adopted to construct a first map corresponding to the first fund account group: and taking the plurality of first fund accounts as nodes, namely determining the nodes of the map according to the plurality of first fund accounts, then acquiring fund business information among the first fund accounts, constructing edges among the map nodes according to the fund business information, namely determining the edges of the map according to the fund business information, and then obtaining initial maps corresponding to the groups of the plurality of first fund accounts according to the nodes of the map and the edges of the map.
After the initial map is obtained, community mining is carried out on the map through a community finding algorithm, and a plurality of first fund account groups and first maps corresponding to the first fund account groups are obtained. It should be noted that the community discovery algorithm may be a louvain algorithm, and controls the size of the primary fund account group according to the actual service requirement, and generally controls the number of fund accounts in the primary fund account group to be less than 100.
The association relation between the fund accounts can be expressed more accurately through the fund current and current information, and the accuracy of constructing the first map is improved.
Optionally, in the method for processing a funds account provided in the embodiment of the present application, before determining whether the plurality of first funds account groups have transaction risk according to the similarity between the first map and the second map, the method further includes: processing the first map through a map embedding algorithm to obtain a first embedded vector set corresponding to the first map; processing the second map through a map embedding algorithm to obtain a second embedded vector set corresponding to the second map; and calculating according to the first embedded vector set and the second embedded vector set to obtain the similarity between the first map and the second map.
Processing the first map through a map embedding algorithm, wherein obtaining a first embedded vector set corresponding to the first map comprises the following steps: traversing the first atlas through an image embedding algorithm to obtain a plurality of first sub atlases; encoding a plurality of first sub-spectrums by a graph embedding algorithm to obtain a first embedding vector corresponding to each first sub-spectrum; and determining a first embedded vector set according to the first embedded vector corresponding to each first sub-graph.
Optionally, before determining whether the plurality of first funds account groups have transaction risk according to the similarity between the first map and the second map, the similarity between the first map and the second map is calculated by adopting the following steps: traversing nodes and edges in the first spectrogram through a graph embedding algorithm to obtain a plurality of first sub-spectrograms, and then encoding the plurality of first sub-spectrograms through the graph embedding algorithm to obtain a first embedded vector set. Traversing nodes and edges in the second spectrogram through a graph embedding algorithm to obtain a plurality of second sub-spectrograms, and then encoding the plurality of second sub-spectrograms through the graph embedding algorithm to obtain a second embedded vector set. It should be noted that the Graph embedding algorithm may be Graph2Vec algorithm.
After the first embedded vector set and the second embedded vector set are obtained, the first embedded vector set and the second embedded vector set are calculated, and the similarity between the first map and the second map is obtained.
Through converting the patterns into vector sets, and then calculating the similarity between the first patterns and the second patterns by using the vector sets, the accuracy of calculating the similarity can be effectively improved.
Optionally, in the processing method for a fund account provided in the embodiment of the present application, calculating according to the first embedded vector set and the second embedded vector set, obtaining the similarity between the first map and the second map includes: calculating Euclidean distance between a first embedded vector in a first embedded vector set and a second embedded vector in a second embedded vector set to obtain a target Euclidean distance; the target euclidean distance is determined as a similarity between the first map and the second map.
Optionally, in order to improve accuracy of calculating the similarity between the first and second patterns, a euclidean distance between the first embedded vector in the first set of embedded vectors and the second embedded vector in the second set of embedded vectors is calculated, and then the target euclidean distance is determined as the similarity between the first and second patterns.
Optionally, in the method for processing a funds account provided in the embodiment of the present application, determining whether the plurality of first funds account groups have transaction risk according to the similarity between the first map and the second map, and obtaining the determination result includes: judging whether the similarity between the first map and the second map is smaller than a preset threshold value or not; if the similarity is smaller than a preset threshold value, determining that the first fund account group is a fund account group with transaction risk as a judgment result; if the similarity is greater than or equal to a preset threshold, determining that the first fund account group is not the fund account group with transaction risk.
Optionally, determining whether the first fund account group has transaction risk includes: judging whether the similarity between the first map and the second map is smaller than a preset threshold (for example, 0.2), if the similarity between the first map and the second map is smaller than 0.2, determining that the first fund account group is a fund account group with transaction risk directly if the Euclidean distance between the first map and the second map is close, and if the similarity between the first map and the second map is larger than or equal to 0.2, determining that the first fund account group is not a fund account group with transaction risk.
By the similarity, whether the first fund account group is the fund account group with transaction risk can be accurately and quickly determined.
Optionally, in the method for processing a fund account provided in the embodiment of the present application, before the first map is processed by the map embedding algorithm to obtain a first embedded vector set corresponding to the first map, the method further includes: acquiring a plurality of third maps constructed based on funds transactions between the plurality of second funds accounts; traversing the plurality of third patterns through an initial pattern embedding algorithm to obtain a plurality of third sub patterns corresponding to each third pattern; and carrying out iterative training on the initial graph embedding algorithm according to a plurality of third sub-graphs and an objective function to obtain the graph embedding algorithm, wherein the objective function is used for calculating the probability of the third sub-graphs in the third graphs.
Performing iterative training on the initial graph embedding algorithm according to a plurality of third sub-graphs and objective functions, wherein the obtaining the graph embedding algorithm comprises the following steps: constructing a plurality of fourth sub-spectrums corresponding to each third spectrum according to the plurality of third spectrums, wherein the probability that the fourth sub-spectrum appears in the third spectrum is 0; and carrying out iterative training on the initial graph embedding algorithm according to the fourth sub-graphs, the third sub-graphs and the objective function to obtain the graph embedding algorithm.
Optionally, in order to improve the accuracy of vector expression of the graph by the graph embedding algorithm, the following steps are adopted to obtain the graph embedding algorithm: obtaining a training sample: obtaining a plurality of third patterns constructed based on the fund flow between a plurality of second fund accounts, traversing nodes and edges in the plurality of third patterns through an initial pattern embedding algorithm to obtain a plurality of third sub patterns corresponding to each third pattern, calculating the probability of the third sub pattern appearing in the third pattern through an objective function, performing iterative training on the initial pattern embedding algorithm through the plurality of third sub patterns and the objective function so that the probability of the third sub pattern appearing in the third pattern reaches the maximum, and determining the initial pattern embedding algorithm when the probability of the third sub pattern appearing in the third pattern reaches the maximum as the pattern embedding algorithm.
It should be noted that, in order to further improve the accuracy of vector expression of the third spectrum by the graph embedding algorithm, a negative sample may be further constructed according to the third spectrum, that is, a plurality of fourth sub-spectrums corresponding to each third spectrum may be constructed based on the plurality of third spectrums, where the probability that the fourth sub-spectrum appears in the third spectrum is 0. And finally, performing iterative training on the initial graph embedding algorithm according to the fourth sub-graphs, the third sub-graphs and the objective function to obtain the graph embedding algorithm. The efficiency and quality of training the graph embedding algorithm can be effectively improved through the negative sample, and the effect of improving the accuracy of the follow-up risk community determination is achieved.
In an alternative embodiment, the determination of the risk community may be implemented through a flowchart as shown in fig. 2, (1) Graph2Vec embedding training is performed to obtain an embedding algorithm M;
(2) the account with active funds is patterned according to whether funds are available or not as edges, and a full graph is obtained; performing community mining by using a louvain community discovery algorithm, and dividing the whole graph into communities with moderate scale;
(3) carrying out graph embedding on a historical known partner A with transaction risk by using an embedding algorithm M obtained in the step 1, and representing the partner A as an n-dimensional vector VA;
(4) For unknown group B, calculating Euclidean distance S of vector VA and vector VB (S is the similarity between two communities);
according to the actual business situation, a threshold value e is selected, and when S < e, the partner B is considered to be the partner with transaction risk, and screening can be carried out or account numbers in the partner B can be controlled and limited.
According to the processing method of the fund accounts, a plurality of first fund accounts are obtained, and a plurality of first fund account groups and a first map corresponding to each first fund account group are determined according to fund transactions among the plurality of first fund accounts, wherein the first fund account groups are composed of the plurality of first fund accounts; acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk; judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first atlas and the second atlas to obtain a judging result, wherein the judging result represents whether the first fund account groups are the fund account groups with the transaction risks, and the problem that the accuracy rate of excavating the group accounts is lower due to the fact that the group accounts with the transaction risks are excavated through simple logic rules in the related technology is solved. In the scheme, the association relation between the first funds accounts is accurately described through the patterns, the first funds account groups possibly having transaction risks and the first patterns corresponding to each first funds account group are obtained through the patterns, and then whether the first funds account groups have transaction risks or not is accurately judged through the second patterns corresponding to the second funds account groups with determined transaction risks, so that the effect of improving the accuracy of mining the group accounts is achieved.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment of the application also provides a processing device for the fund account, and the processing device for the fund account can be used for executing the processing method for the fund account. The following describes a processing device for a fund account provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of a processing device for a funds account according to an embodiment of the application. As shown in fig. 3, the apparatus includes: a first acquisition unit 301, a second acquisition unit 302, and a judgment unit 303.
A first obtaining unit 301, configured to obtain a plurality of first funds accounts, and determine a plurality of first funds account groups and a first map corresponding to each first funds account group according to funds between the plurality of first funds accounts, where the first funds account groups are composed of the plurality of first funds accounts;
A second obtaining unit 302, configured to obtain a second map corresponding to a second fund account group, where the second fund account group is a fund account group with transaction risk;
and the judging unit 303 is configured to judge whether the plurality of first funds account groups have transaction risks according to the similarity between the first map and the second map, so as to obtain a judgment result, where the judgment result represents whether the first funds account group is a funds account group having transaction risks.
According to the processing device for the fund accounts, a plurality of first fund accounts are acquired through the first acquisition unit 301, and a plurality of first fund account groups and a first map corresponding to each first fund account group are determined according to fund transactions among the plurality of first fund accounts, wherein the first fund account groups are composed of the plurality of first fund accounts; the second obtaining unit 302 obtains a second map corresponding to a second fund account group, where the second fund account group is a fund account group with transaction risk; the judging unit 303 judges whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map, so as to obtain a judging result, wherein the judging result represents whether the first fund account groups are the fund account groups having transaction risks, and the problem that the accuracy rate of excavating the group accounts is lower due to the fact that the group accounts are excavated through simple logic rules in the related art is solved. In the scheme, the association relation between the first funds accounts is accurately described through the patterns, the first funds account groups possibly having transaction risks and the first patterns corresponding to each first funds account group are obtained through the patterns, and then whether the first funds account groups have transaction risks or not is accurately judged through the second patterns corresponding to the second funds account groups with determined transaction risks, so that the effect of improving the accuracy of mining the group accounts is achieved.
Optionally, in the processing apparatus for a funds account provided in the embodiment of the present application, the first obtaining unit includes: the first construction subunit is used for constructing a map according to the funds of the plurality of first funds accounts; the first determining subunit is used for determining a plurality of first fund account groups and first maps corresponding to each first fund account group according to the initial maps and the community finding algorithm.
Optionally, in the processing apparatus for a funds account provided in the embodiment of the present application, the apparatus further includes: the first processing unit is used for judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first atlas and the second atlas, and processing the first atlas through a graph embedding algorithm before a judgment result is obtained to obtain a first embedding vector set corresponding to the first atlas; the second processing unit is used for processing the second atlas through an atlas embedding algorithm to obtain a second embedding vector set corresponding to the second atlas; the computing unit is used for computing according to the first embedded vector set and the second embedded vector set to obtain the similarity between the first map and the second map.
Optionally, in the processing device for a funds account provided in the embodiment of the present application, the first processing unit includes: the traversing subunit is used for traversing the first atlas through a graph embedding algorithm to obtain a plurality of first sub atlas; the coding subunit is used for coding the plurality of first sub-spectrums through a graph embedding algorithm to obtain a first embedding vector corresponding to each first sub-spectrum; and the second determining subunit is used for determining a first embedded vector set according to the first embedded vector corresponding to each first sub-spectrum.
Optionally, in the processing apparatus for a funds account provided in the embodiment of the present application, the constructing subunit includes: the determining module is used for determining nodes of the map according to the plurality of first fund accounts; the acquisition module is used for acquiring the fund transaction information among the plurality of first fund accounts and determining the edges of the map according to the fund transaction information; the construction module is used for constructing the map according to the nodes of the map and the sides of the map to obtain an initial map.
Optionally, in the processing device for a funds account provided in the embodiment of the present application, the computing unit includes: a calculating subunit, configured to calculate a euclidean distance between a first embedded vector in the first embedded vector set and a second embedded vector in the second embedded vector set, to obtain a target euclidean distance; and a third determining subunit configured to determine the target euclidean distance as a similarity between the first map and the second map.
Optionally, in the processing apparatus for a funds account provided in the embodiment of the present application, the determining unit includes: the judging subunit is used for judging whether the similarity between the first map and the second map is smaller than a preset threshold value; a fourth determining subunit, configured to determine that the first fund account group is a fund account group with transaction risk if the similarity is smaller than a preset threshold; and the fifth determining subunit is configured to determine that the first fund account group is not a fund account group with transaction risk if the similarity is greater than or equal to the preset threshold.
Optionally, in the processing apparatus for a funds account provided in the embodiment of the present application, the apparatus further includes: the third acquisition unit is used for acquiring a plurality of third maps constructed based on the fund transactions among a plurality of second fund accounts before the first maps are processed through a map embedding algorithm to obtain a first embedded vector set corresponding to the first maps; the traversing unit is used for traversing the plurality of third patterns through an initial pattern embedding algorithm to obtain a plurality of third sub patterns corresponding to each third pattern; the training unit is used for carrying out iterative training on the initial graph embedding algorithm according to a plurality of third sub-graphs and an objective function to obtain the graph embedding algorithm, wherein the objective function is used for calculating the probability of the third sub-graphs in the third graphs.
Optionally, in the processing device for a fund account provided in the embodiment of the present application, the training unit includes: a second construction subunit, configured to construct a plurality of fourth sub-maps corresponding to each third map according to the plurality of third maps, where a probability that the fourth sub-map appears in the third map is 0; and the training subunit is used for carrying out iterative training on the initial graph embedding algorithm according to the plurality of fourth sub-graphs, the plurality of third sub-graphs and the objective function to obtain the graph embedding algorithm.
The processing device of the fund account includes a processor and a memory, where the first acquiring unit 301, the second acquiring unit 302, the judging unit 303, and the like are stored as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the accurate mining of the group accounts with transaction risks is realized by adjusting kernel parameters.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
The embodiment of the invention provides a computer readable storage medium, wherein a program is stored on the computer readable storage medium, and the program is executed by a processor to realize a processing method of a fund account.
The embodiment of the invention provides a processor, which is used for running a program, wherein the processing method of a fund account is executed when the program runs.
As shown in fig. 4, an embodiment of the present invention provides an electronic device, where the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, the following steps are implemented: acquiring a plurality of first funds accounts, and determining a plurality of first funds account groups and a first map corresponding to each first funds account group according to funds exchange among the plurality of first funds accounts, wherein the first funds account groups are composed of the plurality of first funds accounts; acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk; judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map, and obtaining a judging result, wherein the judging result represents whether the first fund account groups are the fund account groups having the transaction risks.
Optionally, determining the plurality of first funds account groups and the first map corresponding to each first funds account group according to the funds exchange between the plurality of first funds accounts includes: performing map construction according to the funds of the plurality of first funds accounts to obtain an initial map; and determining a plurality of first fund account groups and first maps corresponding to each first fund account group according to the initial maps and the community finding algorithm.
Optionally, before determining whether the plurality of first funds account groups have transaction risk according to the similarity between the first map and the second map, the method further includes: processing the first map through a map embedding algorithm to obtain a first embedded vector set corresponding to the first map; processing the second map through a map embedding algorithm to obtain a second embedded vector set corresponding to the second map; and calculating according to the first embedded vector set and the second embedded vector set to obtain the similarity between the first map and the second map.
Optionally, processing the first map through a map embedding algorithm, and obtaining a first embedded vector set corresponding to the first map includes: traversing the first atlas through an image embedding algorithm to obtain a plurality of first sub atlases; encoding a plurality of first sub-spectrums by a graph embedding algorithm to obtain a first embedding vector corresponding to each first sub-spectrum; and determining a first embedded vector set according to the first embedded vector corresponding to each first sub-graph.
Optionally, performing map construction according to funds exchange among the plurality of first funds accounts, and obtaining the initial map includes: determining nodes of the map according to the plurality of first fund accounts; acquiring fund transaction information among a plurality of first fund accounts, and determining edges of the map according to the fund transaction information; and constructing the map according to the nodes of the map and the sides of the map to obtain an initial map.
Optionally, calculating according to the first embedded vector set and the second embedded vector set, the obtaining the similarity between the first spectrum and the second spectrum includes: calculating Euclidean distance between a first embedded vector in a first embedded vector set and a second embedded vector in a second embedded vector set to obtain a target Euclidean distance; the target euclidean distance is determined as a similarity between the first map and the second map.
Optionally, determining whether the plurality of first funds account groups have transaction risk according to the similarity between the first map and the second map, and obtaining the determination result includes: judging whether the similarity between the first map and the second map is smaller than a preset threshold value or not; if the similarity is smaller than a preset threshold value, determining that the first fund account group is a fund account group with transaction risk as a judgment result; if the similarity is greater than or equal to a preset threshold, determining that the first fund account group is not the fund account group with transaction risk.
Optionally, before the first map is processed by the map embedding algorithm to obtain a first embedded vector set corresponding to the first map, the method further includes: acquiring a plurality of third maps constructed based on funds transactions between the plurality of second funds accounts; traversing the plurality of third patterns through an initial pattern embedding algorithm to obtain a plurality of third sub patterns corresponding to each third pattern; and carrying out iterative training on the initial graph embedding algorithm according to a plurality of third sub-graphs and an objective function to obtain the graph embedding algorithm, wherein the objective function is used for calculating the probability of the third sub-graphs in the third graphs.
Optionally, performing iterative training on the initial graph embedding algorithm according to the plurality of third sub-graphs and the objective function, and obtaining the graph embedding algorithm includes: constructing a plurality of fourth sub-spectrums corresponding to each third spectrum according to the plurality of third spectrums, wherein the probability that the fourth sub-spectrum appears in the third spectrum is 0; and carrying out iterative training on the initial graph embedding algorithm according to the fourth sub-graphs, the third sub-graphs and the objective function to obtain the graph embedding algorithm.
The device herein may be a server, PC, PAD, cell phone, etc.
The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: acquiring a plurality of first funds accounts, and determining a plurality of first funds account groups and a first map corresponding to each first funds account group according to funds exchange among the plurality of first funds accounts, wherein the first funds account groups are composed of the plurality of first funds accounts; acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk; judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map, and obtaining a judging result, wherein the judging result represents whether the first fund account groups are the fund account groups having the transaction risks.
Optionally, determining the plurality of first funds account groups and the first map corresponding to each first funds account group according to the funds exchange between the plurality of first funds accounts includes: performing map construction according to the funds of the plurality of first funds accounts to obtain an initial map; and determining a plurality of first fund account groups and first maps corresponding to each first fund account group according to the initial maps and the community finding algorithm.
Optionally, before determining whether the plurality of first funds account groups have transaction risk according to the similarity between the first map and the second map, the method further includes: processing the first map through a map embedding algorithm to obtain a first embedded vector set corresponding to the first map; processing the second map through a map embedding algorithm to obtain a second embedded vector set corresponding to the second map; and calculating according to the first embedded vector set and the second embedded vector set to obtain the similarity between the first map and the second map.
Optionally, processing the first map through a map embedding algorithm, and obtaining a first embedded vector set corresponding to the first map includes: traversing the first atlas through an image embedding algorithm to obtain a plurality of first sub atlases; encoding a plurality of first sub-spectrums by a graph embedding algorithm to obtain a first embedding vector corresponding to each first sub-spectrum; and determining a first embedded vector set according to the first embedded vector corresponding to each first sub-graph.
Optionally, performing map construction according to funds exchange among the plurality of first funds accounts, and obtaining the initial map includes: determining nodes of the map according to the plurality of first fund accounts; acquiring fund transaction information among a plurality of first fund accounts, and determining edges of the map according to the fund transaction information; and constructing the map according to the nodes of the map and the sides of the map to obtain an initial map.
Optionally, calculating according to the first embedded vector set and the second embedded vector set, the obtaining the similarity between the first spectrum and the second spectrum includes: calculating Euclidean distance between a first embedded vector in a first embedded vector set and a second embedded vector in a second embedded vector set to obtain a target Euclidean distance; the target euclidean distance is determined as a similarity between the first map and the second map.
Optionally, determining whether the plurality of first funds account groups have transaction risk according to the similarity between the first map and the second map, and obtaining the determination result includes: judging whether the similarity between the first map and the second map is smaller than a preset threshold value or not; if the similarity is smaller than a preset threshold value, determining that the first fund account group is a fund account group with transaction risk as a judgment result; if the similarity is greater than or equal to a preset threshold, determining that the first fund account group is not the fund account group with transaction risk.
Optionally, before the first map is processed by the map embedding algorithm to obtain a first embedded vector set corresponding to the first map, the method further includes: acquiring a plurality of third maps constructed based on funds transactions between the plurality of second funds accounts; traversing the plurality of third patterns through an initial pattern embedding algorithm to obtain a plurality of third sub patterns corresponding to each third pattern; and carrying out iterative training on the initial graph embedding algorithm according to a plurality of third sub-graphs and an objective function to obtain the graph embedding algorithm, wherein the objective function is used for calculating the probability of the third sub-graphs in the third graphs.
Optionally, performing iterative training on the initial graph embedding algorithm according to the plurality of third sub-graphs and the objective function, and obtaining the graph embedding algorithm includes: constructing a plurality of fourth sub-spectrums corresponding to each third spectrum according to the plurality of third spectrums, wherein the probability that the fourth sub-spectrum appears in the third spectrum is 0; and carrying out iterative training on the initial graph embedding algorithm according to the fourth sub-graphs, the third sub-graphs and the objective function to obtain the graph embedding algorithm.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (12)
1. A method of processing a funds account, comprising:
acquiring a plurality of first funds accounts, and determining a plurality of first funds account groups and a first map corresponding to each first funds account group according to funds traffic among the plurality of first funds accounts, wherein the first funds account groups are composed of a plurality of first funds accounts;
acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk;
judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map to obtain a judging result, wherein the judging result represents whether the first fund account groups are fund account groups with transaction risks.
2. The method of claim 1, wherein determining a plurality of first funds account groups and a first profile corresponding to each first funds account group as a function of funds transactions between the plurality of first funds accounts comprises:
performing map construction according to the funds of the plurality of first funds accounts to obtain an initial map;
And determining the first funds account groups and the first atlas corresponding to each first funds account group according to the initial atlas and the community finding algorithm.
3. The method of claim 1, wherein prior to determining whether the plurality of first funds account parties have transaction risk based on the similarity between the first profile and the second profile, the method further comprises:
processing the first map through a map embedding algorithm to obtain a first embedded vector set corresponding to the first map;
processing the second map through the map embedding algorithm to obtain a second embedded vector set corresponding to the second map;
and calculating according to the first embedded vector set and the second embedded vector set to obtain the similarity between the first map and the second map.
4. The method of claim 3, wherein processing the first map by a map embedding algorithm to obtain a first set of embedded vectors corresponding to the first map comprises:
traversing the first map through the map embedding algorithm to obtain a plurality of first sub-maps;
Encoding the plurality of first sub-spectrums by the graph embedding algorithm to obtain a first embedded vector corresponding to each first sub-spectrum;
and determining the first embedded vector set according to the first embedded vector corresponding to each first sub-graph.
5. The method of claim 2, wherein performing the profile construction based on the funds transactions between the plurality of first funds accounts, the obtaining the initial profile comprising:
determining nodes of the map according to the plurality of first fund accounts;
acquiring fund transaction information among the plurality of first fund accounts, and determining edges of the map according to the fund transaction information;
and constructing the spectrum according to the nodes of the spectrum and the edges of the spectrum to obtain the initial spectrum.
6. The method of claim 3, wherein computing from the first set of embedded vectors and the second set of embedded vectors to obtain a similarity between the first map and the second map comprises:
calculating Euclidean distance between a first embedded vector in the first embedded vector set and a second embedded vector in the second embedded vector set to obtain a target Euclidean distance;
And determining the target Euclidean distance as the similarity between the first map and the second map.
7. The method of claim 6, wherein determining whether the plurality of first funds account parties have transaction risk based on the similarity between the first profile and the second profile, the determining comprising:
judging whether the similarity between the first map and the second map is smaller than a preset threshold value or not;
if the similarity is smaller than the preset threshold, determining that the first fund account group is a fund account group with transaction risk;
and if the similarity is greater than or equal to the preset threshold, determining that the first fund account group is not the fund account group with transaction risk.
8. A method according to claim 3, wherein before processing the first map by a map embedding algorithm to obtain a first set of embedded vectors corresponding to the first map, the method further comprises:
acquiring a plurality of third maps constructed based on funds transactions between the plurality of second funds accounts;
traversing the plurality of third patterns through an initial pattern embedding algorithm to obtain a plurality of third sub-patterns corresponding to each third pattern;
And carrying out iterative training on the initial graph embedding algorithm according to the plurality of third sub-graphs and an objective function to obtain the graph embedding algorithm, wherein the objective function is used for calculating the probability of the third sub-graphs in the third graphs.
9. The method of claim 8, wherein iteratively training the initial graph embedding algorithm in accordance with the plurality of third sub-graphs and objective functions, the obtaining the graph embedding algorithm comprises:
constructing a plurality of fourth sub-maps corresponding to each third map according to the third maps, wherein the probability of the fourth sub-map appearing in the third map is 0;
and carrying out iterative training on the initial graph embedding algorithm according to the fourth sub-graphs, the third sub-graphs and the objective function to obtain the graph embedding algorithm.
10. A funds account processing apparatus, comprising:
the first acquisition unit is used for acquiring a plurality of first fund accounts, and determining a plurality of first fund account groups and a first map corresponding to each first fund account group according to fund transactions among the plurality of first fund accounts, wherein the first fund account groups consist of a plurality of first fund accounts;
The second acquisition unit is used for acquiring a second map corresponding to a second fund account group, wherein the second fund account group is a fund account group with transaction risk;
and the judging unit is used for judging whether the plurality of first fund account groups have transaction risks according to the similarity between the first map and the second map to obtain a judging result, wherein the judging result represents whether the first fund account groups are fund account groups with transaction risks.
11. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program, when run, controls the storage medium to perform the method of processing a funds account according to any of claims 1 to 9 at a device.
12. An electronic device comprising one or more processors and memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of processing a funds account of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311282759.9A CN117314639A (en) | 2023-09-28 | 2023-09-28 | Processing method and device of fund account, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311282759.9A CN117314639A (en) | 2023-09-28 | 2023-09-28 | Processing method and device of fund account, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117314639A true CN117314639A (en) | 2023-12-29 |
Family
ID=89242178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311282759.9A Pending CN117314639A (en) | 2023-09-28 | 2023-09-28 | Processing method and device of fund account, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314639A (en) |
-
2023
- 2023-09-28 CN CN202311282759.9A patent/CN117314639A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272031B (en) | Training sample generation method, device, equipment and medium | |
| CN109657696B (en) | Multi-task supervised learning model training and predicting method and device | |
| CN111553488B (en) | Risk recognition model training method and system for user behaviors | |
| CN111415015B (en) | Business model training method, device and system and electronic equipment | |
| CN110276492A (en) | A kind of node data prediction technique and device | |
| CN111882426A (en) | Business risk classifier training method, device, equipment and storage medium | |
| CN112819157B (en) | Neural network training method and device, intelligent driving control method and device | |
| CN110969200A (en) | Image target detection model training method and device based on consistency negative sample | |
| CN111832693B (en) | Neural network layer operation and model training method, device and equipment | |
| CN110909878A (en) | Training method and device of neural network model for estimating resource usage share | |
| CN113743678B (en) | User credit score prediction method and related equipment | |
| CN113989574B (en) | Image interpretation method, image interpretation device, electronic device, and storage medium | |
| CN109492891B (en) | User loss prediction method and device | |
| CN113436006A (en) | Loan risk prediction method and device based on block chain | |
| CN112258129A (en) | Distribution path prediction network training and distribution resource scheduling method and device | |
| US20230068381A1 (en) | Method and electronic device for quantizing dnn model | |
| CN117314639A (en) | Processing method and device of fund account, storage medium and electronic equipment | |
| CN116720214A (en) | Model training method and device for privacy protection | |
| CN116129325A (en) | Urban treatment image target extraction method and device and application thereof | |
| CN115034887A (en) | Cash transfer control method, system, equipment and storage medium | |
| CN116152542A (en) | Training method, device, equipment and storage medium for image classification model | |
| CN116071375B (en) | Image segmentation method and device, storage medium and electronic equipment | |
| CN117036000A (en) | Processing method and device of fund account, storage medium and electronic equipment | |
| CN115730823A (en) | Risk probability identification method and device, processor and electronic equipment | |
| CN115953440B (en) | Registration method and device of medical image, storage medium and electronic equipment |
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 |