CN113094595A

CN113094595A - Object recognition method, device, computer system and readable storage medium

Info

Publication number: CN113094595A
Application number: CN202110380034.8A
Authority: CN
Inventors: 陈志泉; 彭正强; 何珍珍; 黄星瑜
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2021-04-08
Filing date: 2021-04-08
Publication date: 2021-07-09

Abstract

The present disclosure provides an object recognition method, which can be used in the technical field of artificial intelligence or other fields. Wherein, the method comprises the following steps: receiving a request for identifying an object, wherein the request carries attribute information of the object to be identified; acquiring social relation behavior information of the object to be identified based on the attribute information of the object to be identified; processing the social relationship behavior information of the object to be identified to obtain object association similarity of the object to be identified; and determining the identification result of the object to be identified based on the attribute information of the object to be identified and the object association similarity of the object to be identified, wherein the identification result comprises risks or no risks. The present disclosure also provides an object recognition apparatus, a computer system, a readable storage medium, and a computer program product.

Description

Object recognition method, device, computer system and readable storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence technology or other fields, and more particularly, to an object recognition method, apparatus, computer system, readable storage medium, and computer program product.

Background

With the rise of internet technology and the influence of new policies, a large number of new market subjects and new customer groups are promoted. Meanwhile, the new market main body and the new client group have increased demands for convenient account opening.

In implementing the disclosed concept, the inventors found that there are at least the following problems in the related art: the full-time investigation business volume of the user is increased, the manual investigation efficiency is low, and hysteresis exists.

Disclosure of Invention

In view of the above, the present disclosure provides an object recognition method, an object recognition apparatus, a computer system, a readable storage medium, and a computer program product.

One aspect of the present disclosure provides an object recognition method, including:

receiving a request for identifying an object, wherein the request carries attribute information of the object to be identified;

acquiring social relation behavior information of the object to be identified based on the attribute information of the object to be identified;

processing the social relationship behavior information of the object to be identified to obtain object association similarity of the object to be identified; and

and determining the identification result of the object to be identified based on the attribute information of the object to be identified and the object association similarity of the object to be identified, wherein the identification result comprises risks or no risks.

According to the embodiment of the present disclosure, determining the identification result of the object to be identified based on the attribute information of the object to be identified and the associated similarity of the object to be identified includes:

preprocessing attribute information of an object to be identified to obtain first processing information;

inputting the first processing information and the object association similarity into a first logistic regression model, and outputting the prediction probability of the object to be recognized; and

and determining the recognition result of the object to be recognized based on the prediction probability of the object to be recognized.

According to the embodiment of the present disclosure, before the attribute information of the object to be recognized is preprocessed to obtain the first processing information, the method further includes:

judging the attribute information of the object to be identified, and determining whether the attribute information comprises characteristic unicity information;

under the condition that the attribute information of the object to be identified comprises the characteristic unicity information, filtering the characteristic unicity information so as to preprocess the residual information except the characteristic unicity information in the attribute information;

and preprocessing the attribute information under the condition that the attribute information of the object to be identified does not comprise feature unicity.

According to an embodiment of the present disclosure, preprocessing attribute information of an object to be recognized to obtain first processing information includes:

classifying the attribute information of the object to be identified according to a preset rule to obtain preliminary preprocessing information;

and carrying out discretization processing on the preliminary preprocessing information to obtain first processing information.

According to the embodiment of the disclosure, processing the social relationship behavior information of the object to be recognized to obtain the object association similarity of the object to be recognized includes:

processing the social relationship behavior information of the object to be recognized by using a knowledge graph algorithm to generate a social graph associated with the object to be recognized;

and processing the social graph by using recursive logic to obtain the object association similarity of the object to be identified.

According to an embodiment of the present disclosure, the object recognition method further includes: acquiring historical transaction behavior information of the object to be identified based on the attribute information of the object to be identified;

determining the identification result of the object to be identified based on the attribute information of the object to be identified and the associated similarity of the object to be identified comprises:

processing the historical transaction behavior information of the object to be identified to obtain second processing information;

inputting the first processing information, the second processing information and the object association similarity into a second logistic regression model, and outputting the prediction probability of the object to be identified; and

According to the embodiment of the disclosure, processing the historical transaction behavior information of the object to be identified to obtain the second processing information includes:

processing historical transaction behavior information of an object to be identified by using a knowledge graph algorithm to generate a transaction graph associated with the object to be identified;

extracting information in a transaction map by using a random walk mode to obtain a behavior sequence of an object to be identified;

carrying out one-hot coding processing on the behavior sequence of the object to be recognized to generate a coding result corresponding to the behavior sequence; and

and performing feature extraction on the encoding result to obtain second processing information.

Another aspect of the present disclosure also provides an object recognition apparatus, including:

the device comprises a receiving module, a judging module and a judging module, wherein the receiving module is used for receiving a request for identifying an object, and the request carries attribute information of the object to be identified;

the acquiring module is used for acquiring social relationship behavior information of the object to be identified based on the attribute information of the object to be identified;

the processing module is used for processing the social relationship behavior information of the object to be identified to obtain the object association similarity of the object to be identified; and

the determining module is used for determining the identification result of the object to be identified based on the attribute information of the object to be identified and the object association similarity of the object to be identified, wherein the identification result comprises risks or no risks.

Yet another aspect of the present disclosure provides a computer system comprising:

one or more processors;

a 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 object recognition method described above.

Yet another aspect of the present disclosure provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the object recognition method described above.

Yet another aspect of the present disclosure provides a computer program product comprising a computer program comprising computer executable instructions for implementing the object recognition method described above when executed.

According to the embodiment of the disclosure, the method comprises the steps of receiving a request for identifying an object, wherein the request carries attribute information of the object to be identified; acquiring social relation behavior information of the object to be identified based on the attribute information of the object to be identified; processing the social relationship behavior information of the object to be identified to obtain object association similarity of the object to be identified; determining an identification result of the object to be identified based on the attribute information of the object to be identified and the object association similarity of the object to be identified, wherein the identification result comprises risky or risk-free technical means, and the automatic identification and risk estimation are realized by using the attribute information of the object to be identified and the object association similarity as judgment references; therefore, the technical problem of low processing efficiency caused by investigation of full-time personnel in the prior art is at least partially solved, and the technical effect of efficient and rapid risk estimation is achieved.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an exemplary system architecture to which the object recognition methods and apparatus of the present disclosure may be applied;

FIG. 2 schematically illustrates a flow chart of an object recognition method according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a flow chart of an object recognition method according to another embodiment of the present disclosure;

FIG. 4 schematically illustrates a social graph associated with an object to be identified, in accordance with an embodiment of the present disclosure;

FIG. 5 schematically illustrates a social graph associated with an object to be identified according to another embodiment of the present disclosure;

figure 6 schematically illustrates a transaction map associated with an object to be identified according to an embodiment of the disclosure;

FIG. 7 schematically illustrates a flow diagram of an application object recognition method according to another embodiment of the present disclosure;

fig. 8 schematically shows a block diagram of an object recognition arrangement according to an embodiment of the present disclosure; and

FIG. 9 schematically shows a block diagram of a computer system suitable for implementing an object recognition method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

The embodiment of the disclosure provides an object identification method. The method comprises the following steps: receiving a request for identifying an object, wherein the request carries attribute information of the object to be identified; acquiring social relation behavior information of the object to be identified based on the attribute information of the object to be identified; processing the social relationship behavior information of the object to be identified to obtain object association similarity of the object to be identified; and determining the identification result of the object to be identified based on the attribute information of the object to be identified and the object association similarity of the object to be identified, wherein the identification result comprises risks or no risks.

Fig. 1 schematically illustrates an exemplary system architecture 100 to which the object recognition methods and apparatus may be applied, according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, the system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired and/or wireless communication links, and so forth.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as a shopping-like application, a web browser application, a search-like application, an instant messaging tool, a mailbox client, and/or social platform software, etc. (by way of example only).

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the object identification method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the object recognition apparatus provided by the embodiments of the present disclosure may be generally disposed in the server 105. The object identification method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Accordingly, the object recognition apparatus provided in the embodiments of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Alternatively, the object identification method provided by the embodiment of the present disclosure may also be executed by the

terminal device

101, 102, or 103, or may also be executed by another terminal device different from the

terminal device

101, 102, or 103. Accordingly, the object recognition apparatus provided in the embodiments of the present disclosure may also be disposed in the

terminal device

101, 102, or 103, or in another terminal device different from the

terminal device

101, 102, or 103.

For example, the first logistic regression model or the second logistic regression model may be originally stored in any one of the

terminal devices

101, 102, or 103 (e.g., the terminal device 101, but not limited thereto), or stored on an external storage device and may be imported into the terminal device 101. Then, the terminal device 101 may send the first logistic regression model or the second logistic regression model to other terminal devices, servers, or server clusters, and execute the object identification method provided by the embodiment of the present disclosure by the other servers or server clusters receiving the attribute information of the object to be identified.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

It should be noted that the object identification method, the object identification device, the computer system, the computer readable storage medium, and the computer program product of the present disclosure may be used in the technical field of artificial intelligence, and may also be used in any fields other than the technical field of artificial intelligence.

Fig. 2 schematically shows a flow chart of an object recognition method according to an embodiment of the present disclosure.

As shown in fig. 2, the method includes operations S210 to S240.

In operation S210, a request for identifying an object is received, where the request carries attribute information of the object to be identified.

According to the embodiment of the disclosure, the object identification method in the embodiment of the disclosure can be applied to financial institutions such as banks, and when facing new market subjects and new customer groups, new policies require to strengthen account opening qualification and bank subject responsibility, so due diligence becomes an important task. On the one hand, however, in order to meet the regulatory requirements, the manual checking is more and more time-consuming, the data is incomplete, and the telecommunication fraud cases are layered endlessly, so that the difficulty of manual due diligence is more and more, and the workload is more and more, which gradually becomes a flow bottleneck.

According to the embodiment of the disclosure, by using the object identification method of the embodiment of the disclosure, the data required by the current due diligence process can be compared automatically in the due diligence process, manual checking is omitted, and the approval efficiency is improved.

According to the embodiment of the present disclosure, the object to be recognized may be a person, but is not limited thereto and may also be an enterprise client. Any object which is used for making an account with a bank can be automatically identified by adopting an object identification method.

According to the embodiment of the present disclosure, the attribute information of the object to be recognized may include basic information of the object to be recognized.

According to the embodiment of the present disclosure, the basic information of the customer may include the sex, age, city, occupation, academic calendar, credit investigation and punishment of the customer, etc. The method can also comprise the identity of the client in the enterprise, the share right of the client in the enterprise, the area occupied by the enterprise, credit investigation of the enterprise, the number of the enterprise, the property of the enterprise, the enterprise asset, the enterprise creation time and the like. The information is not limited to the above information, and may also include social behavior information between the client and the client, such as social relationship between the client and the client, information that the client and the client are connected through social means such as telephone, WeChat, etc. within a period of time, and the like.

In operation S220, social relationship behavior information of the object to be recognized is acquired based on the attribute information of the object to be recognized.

In operation S230, the social relationship behavior information of the object to be recognized is processed to obtain the object association similarity of the object to be recognized.

According to an embodiment of the present disclosure, the social relationship behavior information of the object to be identified may include social relationship behavior information between the object to be identified, for example, client a and several clients. For example, social relationship information between the client a and the client B, social relationship information between the client a and the client C, and social association application information used in the near term, for example, 15 days or within one year, and the like.

According to an embodiment of the present disclosure, several objects having social relationship behavior with the object to be identified may be objects known to be at risk or objects known to be not at risk. But not limited to this, but may also be several objects at known risk that have social relationship behavior with the object to be identified.

According to the embodiment of the disclosure, the social relationship behavior between the object to be recognized and the object with known risk is analyzed, the social relationship behavior between the object to be recognized and the object with known risk is also analyzed, the object association similarity between the object to be recognized and the object with known risk and known risk is obtained, the obtained information is more comprehensive, and comprehensive analysis is facilitated.

According to another embodiment of the disclosure, the social relationship behavior between the object to be recognized and the object with known risk is analyzed, the object association similarity between the object to be recognized and the object with known risk is obtained, the risk of the object to be recognized is predicted in a follow-up mode, and the prediction accuracy is improved.

In operation S240, an identification result of the object to be identified is determined based on the attribute information of the object to be identified and the object association similarity of the object to be identified, wherein the identification result includes at risk or no risk.

According to an embodiment of the present disclosure, the risk in the identification result is a risk with a fraudulent purpose or intent. While risk-free is risk-free with a normal purpose.

According to the embodiment of the disclosure, based on the attribute information and the object association similarity of the object to be identified, the basic information and social relationship and behavior of the client (namely, the association similarity of the object to be identified and the client with known risk and/or no risk) are utilized to simulate manual due investigation, the investigation information is complete and sufficient, and in combination with the fact, the speed of identifying the risk persons with different fraud behaviors is high, the accuracy is high, and the risk is reduced.

The method shown in fig. 2 is further described with reference to fig. 3-7 in conjunction with specific embodiments.

Fig. 3 schematically shows a flow chart of an object recognition method according to an embodiment of the present disclosure.

As shown in fig. 3, determining the recognition result of the object to be recognized based on the attribute information of the object to be recognized and the associated similarity of the object to be recognized includes operations S310 to S330.

In operation S310, the attribute information of the object to be recognized is preprocessed, so as to obtain first processing information.

According to the embodiment of the disclosure, the attribute information of the object to be recognized comprises various features, and has diversity and complexity, so that the attribute information of the object to be recognized is preprocessed, and is favorable for being subsequently input into the first logistic regression model for prediction processing.

In operation S320, the first processing information and the object association similarity are input into the first logistic regression model, and the prediction probability of the object to be recognized is output.

In operation S330, a recognition result of the object to be recognized is determined based on the predicted probability of the object to be recognized.

According to the embodiment of the disclosure, a prediction threshold value can be preset, after the prediction probability of the object to be recognized is obtained, the prediction threshold value is compared with the prediction probability, and the recognition result of the object to be recognized is determined through the comparison result. For example, in the case where the prediction probability is greater than or equal to the prediction threshold, the object to be identified is declared to be a risky object; and in the case that the prediction probability is smaller than the prediction threshold value, the object to be identified is an object without risk.

According to the embodiment of the present disclosure, the prediction threshold may be designed to be 0.9 or 0.8, but is not limited thereto, and may be specifically adjusted according to the actual situation.

According to the embodiment of the disclosure, the object identification method combines the attribute information and the object association similarity of an object to be identified, utilizes the social relationship behaviors between the client to be identified and a plurality of known clients, and combines the attribute information of the client to be identified, and provides the object identification method for predicting the risk level of the object to be identified by utilizing the social relationship behavior information of the object; and the prediction is carried out by combining with a logistic regression model, the prediction mode is novel, and the recognition precision is high.

According to an embodiment of the present disclosure, preprocessing the attribute information of the object to be recognized to obtain the first processing information may include the following operations.

Classifying the attribute information of the object to be identified according to a preset rule to obtain preliminary preprocessing information; and carrying out discretization processing on the preliminary preprocessing information to obtain first processing information.

According to embodiments of the present disclosure, there may be multiple records per customer, and this raw data cannot be used directly for model identification. The data needs to be processed and integrated.

According to the embodiment of the disclosure, the preset rule may be classification according to different data types, and classification processing is performed on the attribute information. The preliminary preprocessing information can be obtained by classifying according to data type discrete, continuous, text and time sequence types.

According to the embodiment of the disclosure, the preliminary preprocessing information can be discretized into the continuous value according to the actual business meaning of the data, for example, the income amount of the customer per month is discretized into 0-5000, 5000-. The time series data is converted into discrete or continuous values that can be used for calculations.

According to the embodiment of the disclosure, the first processing information is obtained by preprocessing the attribute information of the object to be recognized, and the original data can be integrated and processed so as to be used as an input value and input to a subsequent logistic regression model for risk prediction.

According to the optional embodiment of the disclosure, before the attribute information of the object to be recognized is classified according to the preset rule, the attribute information format of the object to be recognized can be processed uniformly, for example, data in the attribute information has the problems of empty key field, abnormal numerical value, data format, single value and the like, and therefore data cleaning is required. For example, adjusting data with inconsistent data formats and cleaning records with null key fields such as abnormal values, client numbers, enterprise numbers and the like.

According to an optional embodiment of the present disclosure, the historical transaction behavior information in the object to be identified may also be subjected to data processing such as classification, cleaning, processing, and integration of the above operations, which is not described herein again.

According to an optional embodiment of the present disclosure, before the attribute information of the object to be recognized is preprocessed to obtain the first processing information, the object recognition method may further include the following operation.

Judging the attribute information of the object to be identified, and determining whether the attribute information comprises characteristic unicity information; under the condition that the attribute information of the object to be identified comprises the characteristic unicity information, filtering the characteristic unicity information so as to preprocess the residual information except the characteristic unicity information in the attribute information; and preprocessing the attribute information under the condition that the attribute information of the object to be identified does not include the feature unicity.

According to embodiments of the present disclosure, feature uniqueness information may be understood as information that is too single to distinguish normal, risk-free clients from abnormal, risk-risky clients based on the information. For example, gender in the attribute information is only male and female. When the feature uniqueness is checked, if the gender in the attribute information is not male or female, and there is no feature, the attribute information is regarded as the feature uniqueness information, and the feature information can be deleted before the attribute information of the object to be recognized is preprocessed.

According to the embodiment of the disclosure, the attribute information of the object to be recognized is judged before the attribute information of the object to be recognized is preprocessed, the attribute information can be filtered in advance in one step, useless characteristic unicity information is filtered, the data volume of subsequent preprocessing operation is reduced, and the working efficiency of subsequent data processing and the recognition precision of the object to be recognized are improved.

Fig. 4 schematically shows a social graph associated with an object to be identified according to an embodiment of the present disclosure.

As shown in FIG. 4, there is a history of social relationship behavior records for clients A, B, C, D, E, and F with transactions, each of which may be represented by node A, node B, node C, node D, node E, and node F. According to the social relationship as the connection between the clients, the connection attributes include relationship types (such as parent-child relationship, co-worker relationship, classmate relationship, and the like), application association (such as WeChat friends and WeChat communication) and/or coincidence relationship (such as co-workers and classmates), and finally a social relationship graph, namely a social graph, is formed.

According to the embodiment of the disclosure, the social graph shown in fig. 4 is processed by using recursive logic, so that the object association similarity of the object to be identified can be obtained.

According to an alternative embodiment of the present disclosure, the object association similarity between clients may be a similarity between client nodes in a social graph. The object association similarity of the object to be recognized is determined by the object associated with the object to be recognized.

According to the embodiment of the disclosure, the relationship network among the clients can be analyzed by utilizing the social graph, and mining and identification of telecommunication fraud groups in group work are facilitated.

According to an alternative embodiment of the present disclosure, a mathematical expression of the object association similarity obtained by processing the social graph with recursive logic may be defined as the following formula (one).

Where a and b represent customer nodes, s (a, b) represents object association similarity of customers a and b, i (a), i (b) represent a set of nodes associated with customers a and b, | i (a) |, | i (b) | represents the number of sets of customers associated with customers a and b, c is an attenuation coefficient, and the empirical value may be a constant of 0.8.

As can be seen from the calculation formula, the object association similarity of the client a and the client b depends on the object association similarity of all nodes connected with the client a and the client b.

It should be noted that the start of the recursion is: the similarity between each node and the node is 1; the inter-node similarity for no association is 0 (in one case, the two nodes do not have an association with the other node). However, the present invention is not limited to this, and may be such that the initial similarity between all nodes is 0 in the recursive initial state.

Fig. 5 schematically shows a social graph associated with an object to be identified according to another embodiment of the present disclosure.

As shown in fig. 5, the application association number may be obtained by associating the application graph. Specifically, the social ways used by the client U1 to perform social activities are telephone, WeChat, and QQ; the social ways used by the client U2 to conduct social activities are WeChat and microblog. The association between guest U1 and guest U2 applies as a WeChat.

Based on the above equation (one), 5 iterations of the similarity between U1 and U2 are calculated, and the process can operate as follows.

1. First, s (U1, U2) is 0.8.

2. Respectively calculating the similarity between the associated node sets Pn of U1 and U2:

u1 associated node (P1-Phone, P2-WeChat, P3-QQ);

u2 association node (P2-WeChat, P4-microblog);

s(p1，p2)，s(p1，p4)，s(p2，p2)，s(p2，p4)，s(p3，p2)，s(p3，p4)。

based on equation (one), the calculation results are as follows:

s(p1，p2)＝0.8*(s(U1，U1)+s(U1，U2))/(1*2)＝0.8*(1+0.8)/(1*2)；

s(p1，p4)＝0.8*(s(U1，U2))/(1*1)＝0.8*0.8/(1*1)；

s(p2，p2)＝1；

s(p2，p4)＝0.8*(s(U1，U2)+s(U2，U2))/(1*2)＝0.8*(0.8+0.1)/(1*2)；

s(p2，p3)＝0.8*(s(U1，U1)+s(U1，U2))/(1*2)＝0.8*(1+0.8)/(1*2)；

s(p3，p4)＝0.8*(s(U1，U2))/(1*1)＝0.8*0.8/(1*1)。

3. after the similarity of each node is calculated, recalculating s (U1, U2):

s(U1，U2)＝0.8/(|I(U1)|*|I(U2)|)*(s(p1，p2)+s(p1，p4)+s(p2，p2)+s(p2，p4)+s(p3，p2)+s(p3，p4))。

4. continuing from step 2, 5 successive calculations are carried out, resulting in the relative final results s (U1, U2) of client U1 and client U2.

By utilizing the calculation mode of the object association similarity, the object association similarity between the object to be identified and the risky known client can be accurately and quickly extracted, so that the risk level of the object to be identified can be predicted by the aid of the object association similarity.

According to another embodiment of the present disclosure, the object identification method may further include acquiring historical transaction behavior information of the object to be identified based on the attribute information of the object to be identified.

According to an embodiment of the present disclosure, the historical transaction behavior information of the object to be identified may include historical behavior information of customer interactions with the product. For example, the historical behavior information of the customer interacting with the product may include behavior information of clicking on a list of mobile banking products, purchasing the product and the like within 1 year of the customer. But not limited to this, the transaction behavior of the client or the enterprise to which the client belongs may also be the transaction behavior in the last 15 days, that is, the transaction time, amount, loan direction, transaction area, transaction channel, and transaction opponent information of each client or the enterprise to which the client belongs are counted.

According to another embodiment of the present disclosure, determining the recognition result of the object to be recognized based on the attribute information of the object to be recognized and the associated similarity of the object to be recognized may further include the following operations.

Preprocessing attribute information of an object to be identified to obtain first processing information; processing the historical transaction behavior information of the object to be identified to obtain second processing information; inputting the first processing information, the second processing information and the object association similarity into a second logistic regression model, and outputting the prediction probability of the object to be identified; and determining the recognition result of the object to be recognized based on the prediction probability of the object to be recognized.

According to the embodiment of the present disclosure, the identification result of the object to be identified is determined based on the prediction probability of the object to be identified, which may be the same as the manner of determining the identification result of the object to be identified by using the prediction probability output by the first logistic regression model described in the above embodiment, and is not described herein again.

According to the embodiment of the present disclosure, the attribute information of the object to be recognized is preprocessed to obtain the first processing information, which may be consistent with the manner described in the above embodiment and is not described herein again.

It should be noted that, according to the embodiment of the present disclosure, the second logistic regression model may be obtained by training the same initial logistic regression model as the first logistic regression model. In training, the initial logistic regression model may be trained using training samples of known labels, where the training samples of known labels include known labels, attribute information of objects, social relationship behavior information of objects with other objects, and historical transaction behavior information of objects with other objects. The attribute information of the object may be preprocessed to obtain first processed information. And processing the social relationship behavior information of the object and other objects to obtain the object association similarity. And processing the historical transaction behavior information of the object and other objects to obtain second processing information. And inputting the first processing information, the object association similarity and the second processing information into the initial logistic regression model for training, and taking the obtained convergent model as a second logistic regression model, wherein the second logistic regression model is high in identification precision.

By using the object identification method of the embodiment of the disclosure, the attribute information, the object association similarity and the behavior sequence of the object to be identified are combined, and the characteristics in multiple aspects are combined for consideration, so that the data integrity is high; in addition, the prediction is carried out by using a logistic regression model, so that the recognition precision is high.

According to an embodiment of the disclosure, processing the historical transaction behavior information of the object to be identified to obtain the second processing information may include the following operations.

Processing historical transaction behavior information of an object to be identified by using a knowledge graph algorithm to generate a transaction graph associated with the object to be identified; extracting information in a transaction map by using a random walk mode to obtain a behavior sequence of an object to be identified; carrying out one-hot coding processing on the behavior sequence of the object to be recognized to generate a coding result corresponding to the behavior sequence; and performing feature extraction on the coding result to obtain second processing information.

Fig. 6 schematically illustrates a transaction map associated with an object to be identified according to an embodiment of the disclosure.

As shown in fig. 6, there are historical transaction behavior records of the client a, the client B, the client C, the client D, the client E and the client F in transaction, each client or its affiliated enterprise may be represented by the node a, the node B, the node C, the node D, the node E and the node F, a client-to-client connection line is taken according to the transaction direction, a transaction loan direction is taken as a connection line direction (for example, arrows in the figure indicate directions), connection line attributes include behavior types and transaction amounts, and finally a relationship graph with a behavior sequence of an object to be identified, that is, a transaction graph, is formed.

According to the embodiment of the disclosure, the knowledge graph algorithm is used for generating the transaction graph associated with the object to be identified, the relationship network among the clients can be analyzed, and mining and identification of telecommunication fraud gangs in ganged-up operation are facilitated.

According to the embodiment of the disclosure, after the construction of the transaction map is completed, the information in the transaction map can be extracted by selecting a random walk mode with moderate time complexity, so as to obtain the behavior sequence of the object to be identified.

According to the embodiment of the disclosure, firstly, each client or the enterprise to which the client belongs is taken as a starting point, and a random walk mode is adopted to regenerate the behavior sequence. Namely, each client or the enterprise to which the client belongs is taken as a starting point Vv, the node jump probability connected with the client is calculated, the node Vx with the highest probability is selected for jumping, and the jump probability randomly wandering with the Vx is continuously calculated.

The wandering is stopped when one or more of the following conditions are achieved.

For example, the transaction interval is equal to 15 days up to date; jumping to the starting point (no adjacent node); the number of jumping-nodes exceeds 50.

And when the walking is finished, all nodes and edges from the starting point to the end point are used as a behavior sequence of the object to be identified.

According to an embodiment of the present disclosure, the hop probability of a node may be calculated according to formula (two).

π_VX＝α_pq(V，X)·ω_VX(ii) a Formula 2

Wherein, pi_VXThe hop probability of node v and node x; omega_VXIs the weight between node v and node x; alpha is alpha_pq(V, X) is defined as formula (III).

Wherein d is_vxRefers to the distance from node v to node x. The return parameter p may be a constant of 0.85 and the in-out parameter q may be a constant of 0.2.

By utilizing the jump probability calculation mode of the embodiment of the disclosure, the jump to the directly connected nodes can be biased, and the similarity between the nodes can be better excavated.

According to the embodiment of the disclosure, the feature extraction is performed on the behavior sequence of the object to be recognized, and the obtaining of the second processing information may include the following operations.

According to the embodiment of the disclosure, the behavior sequence of the object to be recognized is subjected to one-hot encoding processing, and an encoding result corresponding to the behavior sequence is generated; and performing feature extraction on the coding result to obtain second processing information.

According to the embodiment of the disclosure, one-hot-only encoding processing is performed on the behavior sequence of the object to be recognized, N states can be encoded by using an N-bit state register, each state has an independent register bit, and only one of the states is valid at any time.

For example, there are 3 clients U1-U3, and the action sequence of the transaction is:

customer transaction customer amount transaction type

U1: { [ U2: 1000, payment ] };

u2: { [ U3: 2000, transfer ] };

u3: { [ U1: 1500, payment ] }.

The transaction client, amount and transaction type are all only three types, each code has 3 bits, each bit represents a type:

U1：100；U2：010；U3：001。

thus, after unique hot encoding:

U1：{[010，100，100]}；

U2：{[001，001，010]}；

U3：{[100，010，001]}。

according to an alternative embodiment of the present disclosure, after the one-hot encoding, the behavior sequence of each customer is converted into a dense vector by word2dev algorithm. Thereby reducing the existence of a large amount of unnecessary data 0 in the behavior sequence after the one-hot coding. Thereby avoiding unnecessary burden on subsequent calculations.

According to an optional embodiment of the present disclosure, the performing feature extraction on the encoding result to obtain the second processing information may include an operation of inputting the encoding result to the deep long-short term memory neural network to obtain the second processing information.

According to the embodiment of the disclosure, the deep long-short term memory neural network comprises one layer of LSTM network as a further feature extraction layer, and then comprises two layers of LSTM deep networks.

According to the embodiment of the disclosure, after the deep long-short term memory neural network is constructed, a historical client can be used as a training sample to train the network and the model in the object recognition method, and the node parameters in the two-layer LSTM deep network in the trained deep long-short term memory neural network are used as third processing information.

According to the embodiment of the disclosure, when the second logistic regression model is trained, the first processing information, the second processing information and the object associated similarity obtained after the attribute information and the behavior sequence are processed can be trained by combining with the third processing information, so that the obtained final logistic regression model is high in identification precision.

Fig. 7 schematically shows a flow chart of an object recognition method according to another embodiment of the present disclosure.

As shown in fig. 7, the object recognition method includes operations S710 to S740, S731 to S734, S741, and S750 to S770.

In operation S710, a user (e.g., a customer manager of a bank) inputs application material information of the customer to an operation terminal.

According to the embodiment of the disclosure, due diligence application data provided by the customer may include, for example, a customer name, business registration information, a business registration address, a customer identification card, and the like (attribute information).

In operation S720, the operation terminal transmits the request carrying the application information to the server having the object identification method processing function.

In operation S730, the server acquires historical transaction behavior information of the client based on the application profile information of the client.

In operation S740, the server acquires social relationship behavior information of the client based on the application profile information of the client.

In operation S750, the server performs a pre-processing on the attribute information to obtain first processed information.

The server sequentially performs the following operation processing on the historical transaction behavior information.

In operation S731, a transaction map is generated;

in operation S732, a behavior sequence is obtained;

in operation S733, one-hot encoding;

in operation S734, feature extraction results in second processing information.

In operation S741, the server processes the social relationship behavior information to obtain an object association similarity between the client and the client with the known risk.

In operation S760, the first processing information, the second processing information, and the object association similarity are processed using the second logistic regression model to obtain a recognition result of the client.

In operation S770, the recognition result of the client is transmitted to the operation terminal, so that the client manager can reasonably plan the subsequent operation.

In summary, the embodiment of the disclosure provides an object identification method for solving the hysteresis of manual processing for identifying novel fraud measures, which utilizes various intra-row structured and unstructured financial data such as attribute information, social relationship behavior information, historical transaction behavior information and the like to automatically process and identify so as to identify different fraud behaviors of telecommunication fraud staff, and presents identification results and identification explanations to dispatching staff, thereby improving identification rate and reducing risks; in addition, automatic comparison is carried out, manual checking is omitted, and examination and approval efficiency is improved.

Fig. 8 schematically shows a block diagram of an object recognition apparatus according to an embodiment of the present disclosure.

As shown in fig. 8, the object recognition apparatus 800 includes a receiving module 810, an obtaining module 820, a processing module 830, and a determining module 840.

A receiving module 810, configured to receive a request for identifying an object, where the request carries attribute information of the object to be identified;

an obtaining module 820, configured to obtain social relationship behavior information of an object to be identified based on attribute information of the object to be identified;

the processing module 830 is configured to process the social relationship behavior information of the object to be identified to obtain an object association similarity of the object to be identified; and

a determining module 840, configured to determine an identification result of the object to be identified based on the attribute information of the object to be identified and the object association similarity of the object to be identified, where the identification result includes at risk or no risk.

According to an embodiment of the present disclosure, the determining module 840 includes a first preprocessing submodule, a first input submodule, and a first determining submodule.

The first preprocessing submodule is used for preprocessing the attribute information of the object to be identified to obtain first processing information;

the first input submodule is used for inputting the first processing information and the object association similarity into the first logistic regression model and outputting the prediction probability of the object to be identified; and

and the first determining submodule is used for determining the recognition result of the object to be recognized based on the prediction probability of the object to be recognized.

According to an embodiment of the present disclosure, the object recognition apparatus 800 further includes a determination module.

The judging module is used for judging the attribute information of the object to be identified before preprocessing the attribute information of the object to be identified to obtain first processing information and determining whether the attribute information comprises characteristic unicity information; under the condition that the attribute information of the object to be identified comprises the characteristic unicity information, filtering the characteristic unicity information so as to preprocess the residual information except the characteristic unicity information in the attribute information; and preprocessing the attribute information under the condition that the attribute information of the object to be identified does not comprise feature unicity.

According to an embodiment of the present disclosure, the preprocessing submodule includes a classification unit and a discretization unit.

The classification unit is used for classifying the attribute information of the object to be identified according to a preset rule to obtain preliminary preprocessing information;

and the discretization unit is used for performing discretization processing on the preliminary preprocessing information to obtain first processing information.

According to an embodiment of the present disclosure, the processing module 830 includes a first processing unit and a second processing unit.

The first processing unit is used for processing the social relationship behavior information of the object to be recognized by using a knowledge graph algorithm to generate a social graph associated with the object to be recognized;

and the second processing unit is used for processing the social graph by using recursive logic to obtain the object association similarity of the object to be identified.

According to an embodiment of the present disclosure, the object recognition device 800 further includes a historical transaction acquisition module.

And the historical transaction acquisition module is used for acquiring historical transaction behavior information of the object to be identified based on the attribute information of the object to be identified.

The determination module 840 includes a second pre-processing submodule, a second input submodule, and a second determination submodule.

The second preprocessing submodule is used for preprocessing the attribute information of the object to be identified to obtain first processing information;

the second processing submodule is used for processing the historical transaction behavior information of the object to be identified to obtain second processing information;

the second input submodule is used for inputting the first processing information, the second processing information and the object association similarity into a second logistic regression model and outputting the prediction probability of the object to be recognized; and

and the second determining submodule is used for determining the recognition result of the object to be recognized based on the prediction probability of the object to be recognized.

According to an embodiment of the present disclosure, wherein the second processing submodule includes a third processing unit, a first extraction unit, an encoding unit, and a second extraction unit.

The third processing unit is used for processing the historical transaction behavior information of the object to be identified by using a knowledge graph algorithm to generate a transaction graph associated with the object to be identified;

the first extraction unit is used for extracting information in the transaction map by using a random walk mode to obtain a behavior sequence of an object to be identified;

the encoding unit is used for carrying out one-hot encoding processing on the behavior sequence of the object to be identified and generating an encoding result corresponding to the behavior sequence; and

and the second extraction unit is used for extracting the characteristics of the coding result to obtain second processing information.

Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.

For example, any plurality of the receiving module 810, the obtaining module 820, the processing module 830, and the determining module 840 may be combined into one module/unit/sub-unit to be implemented, or any one of the modules/units/sub-units may be split into a plurality of modules/units/sub-units. Alternatively, at least part of the functionality of one or more of these modules/units/sub-units may be combined with at least part of the functionality of other modules/units/sub-units and implemented in one module/unit/sub-unit. According to an embodiment of the disclosure, at least one of the receiving module 810, the obtaining module 820, the processing module 830, and the determining module 840 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or in any one of three implementations of software, hardware, and firmware, or in any suitable combination of any of them. Alternatively, at least one of the receiving module 810, the obtaining module 820, the processing module 830, and the determining module 840 may be at least partially implemented as a computer program module, which when executed may perform corresponding functions.

It should be noted that the object identification apparatus part in the embodiment of the present disclosure corresponds to the object identification method part in the embodiment of the present disclosure, and the description of the object identification apparatus part specifically refers to the object identification method part, which is not described herein again.

FIG. 9 schematically shows a block diagram of a computer system suitable for implementing the above described method according to an embodiment of the present disclosure. The computer system illustrated in FIG. 9 is only one example and should not impose any limitations on the scope of use or functionality of embodiments of the disclosure.

As shown in fig. 9, a computer system 900 according to an embodiment of the present disclosure includes a processor 901 which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)902 or a program loaded from a storage section 908 into a Random Access Memory (RAM) 903. Processor 901 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 901 may also include on-board memory for caching purposes. The processor 901 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the present disclosure.

In the RAM 903, various programs and data necessary for the operation of the computer system 900 are stored. The processor 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. The processor 901 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 902 and/or the RAM 903. Note that the programs may also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

Computer system 900 may also include an input/output (I/O) interface 905, input/output (I/O) interface 905 also connected to bus 904, according to an embodiment of the present disclosure. The system 900 may also include one or more of the following components connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including components such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as necessary. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary, so that a computer program read out therefrom is mounted into the storage section 908 as necessary.

According to embodiments of the present disclosure, method flows according to embodiments of the present disclosure may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 909, and/or installed from the removable medium 911. The computer program, when executed by the processor 901, performs the above-described functions defined in the system of the embodiment of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples may include, but are not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 902 and/or the RAM 903 described above and/or one or more memories other than the ROM 902 and the RAM 903.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method provided by the embodiments of the present disclosure, when the computer program product is run on an electronic device, the program code being adapted to cause the electronic device to carry out the object recognition method provided by the embodiments of the present disclosure.

The computer program, when executed by the processor 901, performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, and downloaded and installed through the communication section 909 and/or installed from the removable medium 911. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. An object recognition method, comprising:

processing the social relationship behavior information of the object to be identified to obtain the object association similarity of the object to be identified; and

determining an identification result of the object to be identified based on the attribute information of the object to be identified and the object association similarity of the object to be identified, wherein the identification result comprises risks or no risks.

2. The method of claim 1, wherein the determining the recognition result of the object to be recognized based on the attribute information of the object to be recognized and the associated similarity of the object to be recognized comprises:

preprocessing the attribute information of the object to be identified to obtain first processing information;

3. The method according to claim 2, wherein before preprocessing the attribute information of the object to be identified to obtain the first processing information, the method further comprises:

4. The method according to claim 2, wherein the preprocessing the attribute information of the object to be identified to obtain first processing information comprises:

5. The method of claim 1, wherein the processing the social relationship behavior information of the object to be recognized to obtain the object association similarity of the object to be recognized comprises:

processing the social relationship behavior information of the object to be identified by using a knowledge graph algorithm to generate a social graph associated with the object to be identified;

6. The method of claim 1, further comprising: acquiring historical transaction behavior information of the object to be identified based on the attribute information of the object to be identified;

the determining the identification result of the object to be identified based on the attribute information of the object to be identified and the associated similarity of the object to be identified comprises:

7. The method of claim 6, wherein the processing the historical transaction behavior information of the object to be identified to obtain second processing information comprises:

processing the historical transaction behavior information of the object to be identified by using a knowledge graph algorithm to generate a transaction graph associated with the object to be identified;

extracting information in the transaction map by using a random walk mode to obtain a behavior sequence of the object to be identified;

carrying out one-hot coding processing on the behavior sequence of the object to be identified to generate a coding result corresponding to the behavior sequence; and

and performing feature extraction on the coding result to obtain second processing information.

8. An object recognition apparatus comprising:

the obtaining module is used for obtaining the social relationship behavior information of the object to be identified based on the attribute information of the object to be identified;

the determination module is used for determining the identification result of the object to be identified based on the attribute information of the object to be identified and the object association similarity of the object to be identified, wherein the identification result comprises risks or no risks.

9. A computer system, comprising:

one or more processors;

a 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 any of claims 1-7.

10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 7.

11. A computer program product comprising a computer program comprising computer executable instructions for implementing the method of any one of claims 1 to 7 when executed.