CN113095841A - Transaction identification method and device, electronic equipment and storage medium - Google Patents
Transaction identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113095841A CN113095841A CN202110490029.2A CN202110490029A CN113095841A CN 113095841 A CN113095841 A CN 113095841A CN 202110490029 A CN202110490029 A CN 202110490029A CN 113095841 A CN113095841 A CN 113095841A
- Authority
- CN
- China
- Prior art keywords
- transaction
- target
- attribute
- fraud
- attribute information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
Abstract
The transaction identification method, the transaction identification device, the electronic equipment and the storage medium provided by the invention can analyze the attribute difference degree between the attribute information of the current time and the attribute information of the historical transaction initiation every time the target client initiates the transaction, thereby determining the difference between the target client and the transaction habit of the target client, further accurately identifying the fraud of the current transaction by considering the figure of the target client, and further effectively identifying that the transaction is normally initiated by the user. Based on the invention, the fraudulent transactions can be accurately identified, the generation of the fraudulent transactions is reduced and even avoided, and the property safety of the customers is guaranteed.
Description
Technical Field
The present invention relates to the field of software technologies, and in particular, to a transaction identification method and apparatus, an electronic device, and a storage medium.
Background
In life, the mobile phone is closely related to our life, but the bank card is stolen and swiped due to the loss of the mobile phone is a frequent occurrence, which causes great harm to both bank customers and banks themselves.
Therefore, how to safely and securely prevent transaction fraud becomes an urgent problem to be solved.
Disclosure of Invention
In view of the above, to solve the above problems, the present invention provides a transaction identification method, a transaction identification device, an electronic device, and a storage medium, and the technical solution is as follows:
one aspect of the present invention provides a transaction identification method, including:
responding to a target transaction initiated by a target client currently, and acquiring portrait information of the target client and current first attribute information of the target transaction;
calling second attribute information when the target client initiates the target transaction in history, and analyzing the attribute difference degree between the first attribute information and the second attribute information;
and identifying the fraud of the target client initiating the target transaction currently according to the attribute difference degree and the portrait information of the target client.
Optionally, the analyzing the degree of attribute difference between the first attribute information and the second attribute information includes:
constructing a first transaction knowledge graph of the target customer by taking the target transaction as an entity and taking the first attribute information as a side;
constructing a second transaction knowledge graph of the target customer by taking the target transaction as an entity and the second attribute information as a side;
and comparing the first transaction knowledge graph with the second transaction knowledge graph to calculate the attribute difference degree.
Optionally, the target customer history initiates a plurality of target transactions, and the second transaction knowledge graph is a plurality of second transaction knowledge graphs;
the comparing the first transaction knowledge graph and the second transaction knowledge graph to calculate the degree of attribute difference comprises:
aggregating the plurality of second transaction knowledge maps to obtain an average transaction knowledge map of the target customer, wherein the entity of the average transaction knowledge map is the target transaction and the aggregate result of the second attribute information;
and comparing the first transaction knowledge graph with the average transaction knowledge graph to calculate a first attribute difference degree.
Optionally, the comparing the first transaction knowledge graph and the second transaction knowledge graph to calculate the degree of attribute difference further includes:
screening a target transaction knowledge graph meeting preset conditions from the second transaction knowledge graphs;
and comparing the first transaction knowledge graph with the target transaction knowledge graph to calculate a second attribute difference degree.
Optionally, the identifying, according to the attribute difference degree and the portrait information of the target customer, the target customer's current fraud initiating the target transaction includes:
calling a fraud prediction model, wherein the fraud prediction model is obtained by training a basic model by taking the historical attribute difference degree of the target transaction when a specified client initiates and the portrait information of the specified client as samples in advance and taking the fraud prediction result of the samples approaching to the fraud marking result as a target;
inputting the attribute difference degree and the portrait information of the target customer into the fraud prediction model to obtain the fraud probability output by the fraud prediction model;
judging whether the fraud probability is greater than a preset probability threshold value or not;
if yes, determining that fraud exists;
if not, determining that no fraud exists.
Optionally, the method further includes:
in the event of fraud, a transaction confirmation is made to the target customer.
In another aspect, the present invention provides a transaction identification device, the device comprising:
the information acquisition module is used for responding to a target transaction initiated by a target client currently and acquiring portrait information of the target client and current first attribute information of the target transaction;
the attribute analysis module is used for calling second attribute information when the target client initiates the target transaction historically and analyzing the attribute difference degree between the first attribute information and the second attribute information;
and the fraud identification module is used for identifying the current fraud of the target transaction initiated by the target client according to the attribute difference degree and the portrait information of the target client.
Optionally, the attribute analysis module is specifically configured to:
constructing a first transaction knowledge graph of the target customer by taking the target transaction as an entity and taking the first attribute information as a side; constructing a second transaction knowledge graph of the target customer by taking the target transaction as an entity and the second attribute information as a side; and comparing the first transaction knowledge graph with the second transaction knowledge graph to calculate the attribute difference degree.
Another aspect of the present invention provides an electronic device, including: at least one memory and at least one processor; the memory stores a program, and the processor calls the program stored in the memory, wherein the program is used for realizing any transaction identification method.
In another aspect, the present invention provides a storage medium having stored thereon computer-executable instructions for performing any of the transaction identification methods described herein.
Compared with the prior art, the invention has the following beneficial effects:
the transaction identification method, the transaction identification device, the electronic equipment and the storage medium provided by the invention can analyze the attribute difference degree between the attribute information of the current time and the attribute information of the historical transaction initiation every time the target client initiates the transaction, thereby determining the difference between the target client and the transaction habit of the target client, further accurately identifying the fraud of the current transaction by considering the figure of the target client, and further effectively identifying that the transaction is normally initiated by the user. Based on the invention, the fraudulent transactions can be accurately identified, the generation of the fraudulent transactions is reduced and even avoided, and the property safety of the customers is guaranteed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method of transaction identification provided by an embodiment of the present invention;
FIG. 2 is a partial method flow diagram of a transaction identification method provided by an embodiment of the present invention;
FIG. 3 is a flow chart of another part of a transaction identification method according to an embodiment of the present invention;
FIG. 4 is a flow chart of a further portion of a transaction identification method according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a transaction identification device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The embodiment of the invention provides a transaction identification method, and the flow chart of the method is shown in figure 1, and the method comprises the following steps:
s10, responding to the target trade initiated by the target customer, obtaining the portrait information of the target customer and the current first attribute information of the target trade.
In an embodiment of the invention, for a transaction, a plurality of attributes that may be relevant when the transaction is initiated are assigned, such as transaction amount, transaction date, transaction time, transaction week number (day of week), transaction type (other, same), transaction age (real-time, common), transaction location, transaction channel (cell phone bank, ATM, etc.).
Thus, each time a transaction is initiated by a customer, a plurality of attributes associated with the transaction have corresponding values, whereby the values of these attributes may constitute attribute information for the transaction.
But rather, image information, which can describe some of the attributes of the customer himself, such as gender, age, marital status, residence, age, income, etc.
S20, second attribute information of the target client when initiating the target transaction is called, and the attribute difference degree between the first attribute information and the second attribute information is analyzed.
In the embodiment of the invention, the client is taken as a dimension, the attribute information of each transaction initiated by the client is counted, and the attribute information of the client initiated for the same transaction for multiple times is stored together. Therefore, when the target client initiates the target transaction currently, the attribute information of the target transaction which is initiated by the target client historically, namely the second attribute information, can be obtained, and the target transaction is initiated once, namely a group of second attribute information is obtained.
Because the first attribute information is the attribute information of the target transaction initiated by the target client currently, the first attribute information and the second attribute information have the same attribute, and the numerical difference degree of the first attribute information and the second attribute information under different attributes can be obtained by aligning the attributes. In one attribute, the greater the degree of difference between numerical values, the greater the degree of difference between attributes, and the greater the number of attributes having differences between numerical values, the greater the degree of difference between attributes.
Of course, one set of the second attribute information has a corresponding attribute difference degree with the first attribute information, and the plurality of sets of the second attribute information correspond to a plurality of attribute difference degrees with the first attribute information. Therefore, when the second attribute information is a plurality of groups, the attribute difference degrees of the plurality of groups of second attribute information may be processed to obtain a final attribute difference degree for identifying the fraudulence, for example, the attribute difference degree of one group of second attribute information is randomly selected, and for example, the attribute difference degree of one second attribute information whose transaction time is closest to the current transaction time is selected.
In a specific implementation process, in step S20, the "analyzing the attribute difference degree between the first attribute information and the second attribute information" may adopt the following steps, and a flowchart of the method is shown in fig. 2:
s201, a first transaction knowledge graph of a target customer is constructed by taking a target transaction as an entity and taking first attribute information as a side.
S202, a second transaction knowledge graph of the target customer is constructed by taking the target transaction as an entity and taking the second attribute information as a side.
And S203, comparing the first transaction knowledge graph with the second transaction knowledge graph to calculate the attribute difference degree.
In the embodiment of the invention, the transaction knowledge graph is respectively constructed for the first attribute information and the second attribute information by means of a knowledge graph technology. Of course, since the transaction time corresponding to the first attribute information and the second attribute information is different, the embodiment of the present invention constructs the transaction knowledge graph of the target customer according to the time axis.
Therefore, the basic architecture of the first transaction knowledge graph and the basic architecture of the second transaction knowledge graph are the same, namely, the target transaction is taken as an entity, the attribute related to the target transaction is taken as an edge, and the difference is that the numerical values of the attribute corresponding to the edge are different.
When the target client initiates the target transaction for multiple times in history, the second attribute information is multiple groups, and the second attribute information that is the multiple groups may be further processed to determine second attribute information for calculating the attribute difference degree, for example, to randomly select one second attribute information, and for example, to select one second attribute information whose transaction time is closest to the current time.
After determining the second attribute information used for calculating the attribute difference degree, based on the knowledge-graph technology, a corresponding knowledge-graph, namely a second transaction knowledge-graph, can be constructed. For the second transaction knowledge graph and the first transaction knowledge graph, the difference degrees of different edges can be accurately obtained by comparing the edges with the same attributes, and the attribute difference degrees can be obtained by summarizing the difference degrees of all the edges or screening the difference degrees of partial edges.
In some other embodiments, when the target customer initiates the target transaction for multiple times in history, the second attribute information is in multiple groups, and for each group of second attribute information, a corresponding transaction knowledge graph is constructed, that is, multiple second transaction knowledge graphs are obtained.
At this time, in the process of executing step S203 "calculating the attribute difference degree by comparing the first transaction knowledge graph and the second transaction knowledge graph", the following steps may be adopted, and the method flowchart is shown in fig. 3:
and S2031, aggregating the plurality of second transaction knowledge maps to obtain an average transaction knowledge map of the target customer, wherein the entity of the average transaction knowledge map is the target transaction and the aggregate result of the second attribute information.
In the embodiment of the present invention, based on the edges, that is, attributes, of the plurality of second transaction knowledge graphs, aggregation processing can be performed on the numerical values under different attributes, where the aggregation processing includes, but is not limited to, operations such as averaging or mode taking, and the like, and the plurality of numerical values under the same attribute are aggregated into one, so that the edges with the same attribute of the plurality of second transaction knowledge graphs are aggregated into one edge, thereby obtaining an average transaction knowledge graph with a target transaction as an entity.
Taking the transaction amount as an example, when the value under the attribute is aggregated, since the value belongs to the continuous variable, the average value can be taken as the aggregation result corresponding to the attribute. Taking the transaction type as an example, when aggregation processing is performed on the value under the attribute, the value belongs to the discrete variable, so that a mode, that is, the value with the largest occurrence number can be taken as the aggregation result corresponding to the attribute.
S2032, comparing the first transaction knowledge map with the average transaction knowledge map to calculate the difference degree of the first attribute.
In the embodiment of the invention, for the first transaction knowledge graph and the average transaction knowledge graph, the difference degrees of different sides can be vectorized and calculated, so that the difference degrees of all sides or the difference degrees of some sides are screened to be used as the attribute difference degree of the first aspect, namely the first attribute difference degree. This can reduce the amount of map difference calculation.
On this basis, in order to improve the comprehensiveness of the attribute difference degree calculation, the embodiment of the present invention may further include the following steps:
screening a target transaction knowledge graph meeting preset conditions from the plurality of second transaction knowledge graphs; and comparing the first transaction knowledge graph with the target transaction knowledge graph to calculate the second attribute difference degree.
In the embodiment of the present invention, one or more second transaction knowledge maps with transaction time closest to the current transaction time may be screened as target transaction knowledge maps, and a second transaction knowledge map with a value satisfying a corresponding threshold value under an assigned attribute may also be screened as a target transaction knowledge map, for example, the second transaction knowledge map with the largest transaction amount is used as the target transaction knowledge map.
For the first transaction knowledge graph and each target transaction knowledge graph, the difference degrees of different edges can be obtained through vectorization calculation, so that the difference degrees of all the edges or the difference degrees of partial edges are screened to be used as the attribute difference degree of the second aspect, namely the second attribute difference degree.
Thereby, the set of the first attribute degree and the second attribute degree is set as the attribute difference degree between the first attribute information and the second attribute information.
S30, identifying the fraud of the target client initiating the target transaction according to the attribute difference degree and the image information of the target client.
In the embodiment of the invention, the difference of the transaction attribute directions and the portrait of the client are comprehensively considered to identify whether the target transaction initiated at this time is fraudulent.
In the specific implementation process, in step S30, "identify the fraud that the target client currently initiates the target transaction according to the attribute difference degree and the portrait information of the target client" may adopt the following steps, and a flowchart of the method is shown in fig. 4:
s301, a fraud prediction model is called, the fraud prediction model is obtained by training a basic model by taking the historical attribute difference degree of a target transaction when a designated client initiates and the portrait information of the designated client as samples in advance and taking the fraud prediction result of the samples approaching to the fraud marking result as a target.
In the embodiment of the invention, the basic model of the fraud prediction model can be a fully-connected multilayer deep neural network, the attribute difference degree and the portrait information are taken as characteristics, and the basic model is continuously subjected to iterative training by marking samples to finally obtain the fraud prediction model.
S302, the attribute difference degree and the portrait information of the target client are input into the fraud prediction model to obtain the fraud probability output by the fraud prediction model.
In the embodiment of the invention, the fraud prediction model is input to the fraud prediction model based on the attribute difference degree of the target customer initiating the target transaction at present and the portrait information of the target customer as characteristics, the fraud prediction model outputs the predicted fraud probability, and the higher the fraud probability is, the higher the probability of fraud occurring in the transaction is.
S303, judging whether the fraud probability is greater than a preset probability threshold value; if yes, go to step S304; if not, step S305 is executed.
S304, determining that fraud exists.
S305, determining that no fraud exists.
On the basis, under the condition that the fraud is determined, the embodiment of the invention can also adopt the modes of telephone, mail or short message and the like to confirm the transaction to the target client, and execute the target transaction after obtaining the confirmation information fed back by the target client.
The transaction identification method provided by the embodiment of the invention can analyze the attribute difference degree between the attribute information when the target client initiates the transaction every time, namely the current time and the historical time of initiating the transaction, thereby determining the difference between the target client and the transaction habit of the target client, and further accurately identifying the fraud of the current transaction by considering the portrait of the target client, thereby effectively identifying that the transaction is normally initiated by the user. Based on the invention, the fraudulent transactions can be accurately identified, the generation of the fraudulent transactions is reduced and even avoided, and the property safety of the customers is guaranteed.
Based on the transaction identification method provided by the above embodiment, an embodiment of the present invention further provides a device for executing the above transaction identification method, where a schematic structural diagram of the device is shown in fig. 5, and the device includes:
the information acquisition module 10 is used for responding to a target transaction initiated by a target client currently, and acquiring portrait information of the target client and current first attribute information of the target transaction;
the attribute analysis module 20 is configured to retrieve second attribute information of the target client when the target client initiates the target transaction in history, and analyze an attribute difference degree between the first attribute information and the second attribute information;
and a fraud identification module 30 for identifying the fraud of the target transaction initiated by the target client currently according to the attribute difference degree and the portrait information of the target client.
Optionally, the attribute analysis module 20 performs a process of analyzing the degree of attribute difference between the first attribute information and the second attribute information, including:
constructing a first transaction knowledge graph of a target customer by taking the target transaction as an entity and taking the first attribute information as a side; constructing a second transaction knowledge graph of the target customer by taking the target transaction as an entity and taking the second attribute information as a side; and comparing the first transaction knowledge graph with the second transaction knowledge graph to calculate the attribute difference degree.
Optionally, the target client initiates multiple target transactions historically, and the second transaction knowledge graph is multiple;
aggregating the plurality of second transaction knowledge maps to obtain an average transaction knowledge map of the target customer, wherein the entity of the average transaction knowledge map is the target transaction and the aggregate result of the second attribute information; and comparing the first transaction knowledge graph with the average transaction knowledge graph to calculate the difference degree of the first attribute.
Optionally, the attribute analysis module 20 performs a process of comparing the first transaction knowledge graph and the second transaction knowledge graph to calculate the attribute difference degree, and further includes:
screening a target transaction knowledge graph meeting preset conditions from the plurality of second transaction knowledge graphs; and comparing the first transaction knowledge graph with the target transaction knowledge graph to calculate the second attribute difference degree.
Optionally, the fraud identification module 30 executes a process for identifying the fraud that the target client currently initiates the target transaction based on the attribute difference degree and the representation information of the target client, including:
calling a fraud prediction model, wherein the fraud prediction model is obtained by training a basic model by taking the historical attribute difference degree of a target transaction when a specified client initiates and the portrait information of the specified client as samples in advance and taking the fraud prediction result of the samples approaching to the fraud marking result as a target; inputting the attribute difference degree and the portrait information of the target customer into a fraud prediction model to obtain fraud probability output by the fraud prediction model; judging whether the fraud probability is greater than a preset probability threshold value or not; if yes, determining that fraud exists; if not, determining that no fraud exists.
Optionally, fraud identification module 30 is further configured to:
in the event of fraud, a transaction confirmation is made to the target customer.
The transaction identification device provided by the embodiment of the invention can analyze the attribute difference degree between the attribute information of the current transaction and the attribute information of the historical transaction when the target client initiates the transaction each time, thereby determining the difference between the target client and the transaction habit of the target client, and further accurately identifying the fraud of the current transaction by considering the portrait of the target client, thereby effectively identifying that the transaction is normally initiated by the user each time. Based on the invention, the fraudulent transactions can be accurately identified, the generation of the fraudulent transactions is reduced and even avoided, and the property safety of the customers is guaranteed.
Based on the transaction identification method provided by the above embodiment, an embodiment of the present invention further provides an electronic device, including: at least one memory and at least one processor; the memory stores a program, and the processor invokes the program stored in the memory to implement the transaction identification method of any one of the embodiments.
Based on the transaction identification method provided by the above embodiment, an embodiment of the present invention further provides a storage medium, where the storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the transaction identification method according to any one of the embodiments.
The transaction identification method, the transaction identification device, the electronic device and the storage medium provided by the invention are described in detail, specific examples are applied in the description to explain the principle and the implementation of the invention, and the description of the above embodiments is only used to help understanding the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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 or 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 an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A transaction identification method, the method comprising:
responding to a target transaction initiated by a target client currently, and acquiring portrait information of the target client and current first attribute information of the target transaction;
calling second attribute information when the target client initiates the target transaction in history, and analyzing the attribute difference degree between the first attribute information and the second attribute information;
and identifying the fraud of the target client initiating the target transaction currently according to the attribute difference degree and the portrait information of the target client.
2. The method of claim 1, wherein analyzing the degree of attribute difference between the first attribute information and the second attribute information comprises:
constructing a first transaction knowledge graph of the target customer by taking the target transaction as an entity and taking the first attribute information as a side;
constructing a second transaction knowledge graph of the target customer by taking the target transaction as an entity and the second attribute information as a side;
and comparing the first transaction knowledge graph with the second transaction knowledge graph to calculate the attribute difference degree.
3. The method of claim 2, wherein the target customer history initiates a plurality of the target transactions, and the second transaction knowledge graph is a plurality;
the comparing the first transaction knowledge graph and the second transaction knowledge graph to calculate the degree of attribute difference comprises:
aggregating the plurality of second transaction knowledge maps to obtain an average transaction knowledge map of the target customer, wherein the entity of the average transaction knowledge map is the target transaction and the aggregate result of the second attribute information;
and comparing the first transaction knowledge graph with the average transaction knowledge graph to calculate a first attribute difference degree.
4. The method of claim 3, wherein said comparing said first transaction knowledge-graph and said second transaction knowledge-graph to calculate said degree of attribute variation further comprises:
screening a target transaction knowledge graph meeting preset conditions from the second transaction knowledge graphs;
and comparing the first transaction knowledge graph with the target transaction knowledge graph to calculate a second attribute difference degree.
5. The method of claim 1, wherein said identifying the target customer as currently initiating the target transaction as fraudulent based on the degree of difference in the attribute and the target customer's representation information comprises:
calling a fraud prediction model, wherein the fraud prediction model is obtained by training a basic model by taking the historical attribute difference degree of the target transaction when a specified client initiates and the portrait information of the specified client as samples in advance and taking the fraud prediction result of the samples approaching to the fraud marking result as a target;
inputting the attribute difference degree and the portrait information of the target customer into the fraud prediction model to obtain the fraud probability output by the fraud prediction model;
judging whether the fraud probability is greater than a preset probability threshold value or not;
if yes, determining that fraud exists;
if not, determining that no fraud exists.
6. The method of claim 5, further comprising:
in the event of fraud, a transaction confirmation is made to the target customer.
7. A transaction identification device, the device comprising:
the information acquisition module is used for responding to a target transaction initiated by a target client currently and acquiring portrait information of the target client and current first attribute information of the target transaction;
the attribute analysis module is used for calling second attribute information when the target client initiates the target transaction historically and analyzing the attribute difference degree between the first attribute information and the second attribute information;
and the fraud identification module is used for identifying the current fraud of the target transaction initiated by the target client according to the attribute difference degree and the portrait information of the target client.
8. The apparatus of claim 7, wherein the attribute analysis module is specifically configured to:
constructing a first transaction knowledge graph of the target customer by taking the target transaction as an entity and taking the first attribute information as a side; constructing a second transaction knowledge graph of the target customer by taking the target transaction as an entity and the second attribute information as a side; and comparing the first transaction knowledge graph with the second transaction knowledge graph to calculate the attribute difference degree.
9. An electronic device, comprising: at least one memory and at least one processor; the memory stores a program that the processor invokes, the program stored by the memory for implementing the transaction identification method according to any one of claims 1 to 6.
10. A storage medium having stored thereon computer-executable instructions for performing the transaction identification method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110490029.2A CN113095841A (en) | 2021-05-06 | 2021-05-06 | Transaction identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110490029.2A CN113095841A (en) | 2021-05-06 | 2021-05-06 | Transaction identification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113095841A true CN113095841A (en) | 2021-07-09 |
Family
ID=76681474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110490029.2A Pending CN113095841A (en) | 2021-05-06 | 2021-05-06 | Transaction identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095841A (en) |
-
2021
- 2021-05-06 CN CN202110490029.2A patent/CN113095841A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11783028B2 (en) | Systems and methods for detecting resources responsible for events | |
| US10178108B1 (en) | System, method, and computer program for automatically classifying user accounts in a computer network based on account behavior | |
| US20130124393A1 (en) | Connecting decisions through customer transaction profiles | |
| US20190294612A1 (en) | Classification for Asymmetric Error Costs | |
| CN111614690A (en) | Abnormal behavior detection method and device | |
| CN110807699B (en) | Overdue event payment collection method and device and computer readable storage medium | |
| CN111325550A (en) | Method and device for identifying fraudulent transaction behaviors | |
| CN113627566A (en) | Early warning method and device for phishing and computer equipment | |
| CN112561685B (en) | Customer classification method and device | |
| CN109583731B (en) | Risk identification method, device and equipment | |
| CN111062808B (en) | Credit card limit evaluation method, credit card limit evaluation device, computer equipment and storage medium | |
| CN114022151A (en) | Block chain data visualization method and system, electronic device and storage medium | |
| US20200151200A1 (en) | Feature transformation and missing values | |
| CN111611519A (en) | Method and device for detecting personal abnormal behaviors | |
| CN113095841A (en) | Transaction identification method and device, electronic equipment and storage medium | |
| CN110781410A (en) | Community detection method and device | |
| CN115130577A (en) | Method and device for identifying fraudulent number and electronic equipment | |
| CN114913015A (en) | Hot account identification method and device and electronic equipment | |
| Lopes et al. | Applying user signatures on fraud detection in telecommunications networks | |
| CN114707420A (en) | Credit fraud behavior identification method, device, equipment and storage medium | |
| CN110399399B (en) | User analysis method, device, electronic equipment and storage medium | |
| CN112417007A (en) | Data analysis method and device, electronic equipment and storage medium | |
| CN112163155A (en) | Information processing method, device, equipment and storage medium | |
| CN111429257A (en) | Transaction monitoring method and device | |
| US20110055145A1 (en) | Method and apparatus for insightful dimensional clustering |
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 |