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

Abstract

The present disclosure provides an object recognition method, which can be used in the field of artificial intelligence technology or other fields. The method includes: receiving a request for identifying an object, wherein the request carries attribute information of the object to be identified; obtaining social relationship 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 the object association similarity of the object to be identified; and determining the recognition 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 recognition result includes risk or no risk. The present disclosure also provides an object recognition device, a computer system, a readable storage medium, and a computer program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology or other fields, and more specifically, to an object recognition method, device, computer system, readable storage medium, and computer program product. Background Art

[0002] With the rise of Internet technology and the impact of new policies, a large number of new market players and new customer groups have emerged. At the same time, new market players and new customer groups have increased their demands for convenient account opening.

[0003] In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related art: the user's due diligence workload has increased, the manual investigation is inefficient, and there is a lag. Summary of the invention

[0004] In view of this, the present disclosure provides an object recognition method, device, computer system, readable storage medium, and computer program product.

[0005] One aspect of the present disclosure provides an object recognition method, comprising:

[0006] Receiving a request for identifying an object, wherein the request carries attribute information of the object to be identified;

[0007] Based on the attribute information of the object to be identified, obtaining the social relationship behavior information of the object to be identified;

[0008] 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

[0009] Based on the attribute information of the object to be identified and the object association similarity of the object to be identified, an identification result of the object to be identified is determined, wherein the identification result includes risk or no risk.

[0010] According to an 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 association similarity of the object to be recognized includes:

[0011] Preprocessing the attribute information of the object to be identified to obtain first processed information;

[0012] Inputting the first processed information and the object association similarity into a first logistic regression model, and outputting a predicted probability of the object to be identified; and

[0013] Based on the predicted probability of the object to be identified, the identification result of the object to be identified is determined.

[0014] According to an embodiment of the present disclosure, before preprocessing the attribute information of the object to be identified to obtain the first processed information, the method further includes:

[0015] Judging the attribute information of the object to be identified, and determining whether the attribute information includes feature uniqueness information;

[0016] In the case where the attribute information of the object to be identified includes feature singularity information, the feature singularity information is filtered out so that the remaining information in the attribute information except the feature singularity information is preprocessed;

[0017] When the attribute information of the object to be identified does not include feature uniqueness, the attribute information is preprocessed.

[0018] According to an embodiment of the present disclosure, preprocessing the attribute information of the object to be identified to obtain first processed information includes:

[0019] Classify and process the attribute information of the object to be identified according to preset rules to obtain preliminary preprocessing information;

[0020] The preliminary preprocessing information is discretized to obtain first processed information.

[0021] According to an embodiment of the present disclosure, the social relationship behavior information of the object to be identified is processed to obtain the object association similarity of the object to be identified, which includes:

[0022] Using the knowledge graph algorithm to process the social relationship behavior information of the object to be identified, and generate a social graph associated with the object to be identified;

[0023] The social graph is processed using recursive logic to obtain the object association similarity of the objects to be identified.

[0024] According to an embodiment of the present disclosure, the object identification 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;

[0025] Determining the recognition result of the object to be recognized based on the attribute information of the object to be recognized and the association similarity of the object to be recognized includes:

[0026] Preprocessing the attribute information of the object to be identified to obtain first processed information;

[0027] Processing the historical transaction behavior information of the object to be identified to obtain second processed information;

[0028] Inputting the first processed information, the second processed information and the object association similarity into a second logistic regression model, and outputting a predicted probability of the object to be identified; and

[0029] Based on the predicted probability of the object to be identified, the identification result of the object to be identified is determined.

[0030] According to an embodiment of the present disclosure, the historical transaction behavior information of the object to be identified is processed to obtain the second processed information, which includes:

[0031] Use the knowledge graph algorithm to process the historical transaction behavior information of the object to be identified and generate a transaction graph associated with the object to be identified;

[0032] The random walk method is used to extract information from the transaction graph and obtain the behavior sequence of the object to be identified;

[0033] Perform one-hot encoding on the behavior sequence of the object to be identified to generate an encoding result corresponding to the behavior sequence; and

[0034] Feature extraction is performed on the encoding result to obtain second processing information.

[0035] Another aspect of the present disclosure further provides an object recognition device, comprising:

[0036] A receiving module, used to receive a request for identifying an object, wherein the request carries attribute information of the object to be identified;

[0037] An acquisition module, used to acquire social relationship behavior information of the object to be identified based on the attribute information of the object to be identified;

[0038] A processing module, used to process the social relationship behavior information of the object to be identified to obtain the object association similarity of the object to be identified; and

[0039] The determination module is used to determine the recognition result of the object to be recognized based on the attribute information of the object to be recognized and the object association similarity of the object to be recognized, wherein the recognition result includes risk or no risk.

[0040] Another aspect of the present disclosure provides a computer system, comprising:

[0041] one or more processors;

[0042] a memory for storing one or more programs,

[0043] When one or more programs are executed by one or more processors, the one or more processors implement the above-mentioned object recognition method.

[0044] Another aspect of the present disclosure provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the above-mentioned object recognition method.

[0045] Another aspect of the present disclosure provides a computer program product, including a computer program, wherein the computer program includes computer executable instructions, and the instructions are used to implement the above-mentioned object recognition method when being executed.

[0046] According to the embodiments of the present disclosure, a request for identifying an object is received, wherein the request carries attribute information of the object to be identified; based on the attribute information of the object to be identified, social relationship behavior information of the object to be identified is obtained; the social relationship behavior information of the object to be identified is processed to obtain the object association similarity of the object to be identified; and based on the attribute information of the object to be identified and the object association similarity of the object to be identified, an identification result of the object to be identified is determined, wherein the identification result includes technical means with or without risk, and the attribute information of the object to be identified and the object association similarity are used as a judgment basis to realize automatic identification and risk estimation; therefore, the technical problem of due diligence investigation in the prior art resulting in low processing efficiency is at least partially overcome, thereby achieving the technical effect of efficient and rapid risk estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0048] Figure 1 An exemplary system architecture to which the object recognition method and apparatus of the present disclosure can be applied is schematically shown;

[0049] Figure 2 A flowchart of an object recognition method according to an embodiment of the present disclosure is schematically shown;

[0050] Figure 3 A flowchart of an object recognition method according to another embodiment of the present disclosure is schematically shown;

[0051] Figure 4 A social graph associated with an object to be identified according to an embodiment of the present disclosure is schematically shown;

[0052] Figure 5 A social graph associated with an object to be identified according to another embodiment of the present disclosure is schematically shown;

[0053] Figure 6 Schematically shows a transaction graph associated with an object to be identified according to an embodiment of the present disclosure;

[0054] Figure 7 A flowchart of an application object recognition method according to another embodiment of the present disclosure is schematically shown;

[0055] Figure 8A block diagram schematically shows an object recognition device according to an embodiment of the present disclosure; and

[0056] Fig. 9 A block diagram of a computer system suitable for implementing an object recognition method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0057] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0058] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0059] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0060] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0061] The embodiment of the present disclosure provides an object recognition method. The method includes: receiving a request for identifying an object, wherein the request carries attribute information of the object to be recognized; obtaining social relationship behavior information of the object to be recognized based on the attribute information of the object to be recognized; processing the social relationship behavior information of the object to be recognized to obtain the object association similarity of the object to be recognized; and determining the recognition result of the object to be recognized based on the attribute information of the object to be recognized and the object association similarity of the object to be recognized, wherein the recognition result includes risk or no risk.

[0062] Figure 1 The exemplary system architecture 100 to which the object recognition method and apparatus according to the embodiment of the present disclosure can be applied is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0063] like Figure 1 As shown, 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 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0064] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0065] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0066] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0067] It should be noted that the object recognition method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the object recognition device provided in the embodiment of the present disclosure can generally be set in the server 105. The object recognition method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the object recognition device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Alternatively, the object recognition method provided in the embodiment of the present disclosure can also be executed by the terminal devices 101, 102, or 103, or can also be executed by other terminal devices different from the terminal devices 101, 102, or 103. Accordingly, the object recognition device provided in the embodiment of the present disclosure can also be set in the terminal devices 101, 102, or 103, or can be set in other terminal devices different from the terminal devices 101, 102, or 103.

[0068] 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 (for example, the terminal device 101, but not limited thereto), or stored in 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 the other servers or server clusters that receive the attribute information of the object to be identified may execute the object identification method provided in the embodiment of the present disclosure.

[0069] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0070] It should be noted that the object recognition method, object recognition device, computer system, computer-readable storage medium and computer program product disclosed in the present invention can be used in the field of artificial intelligence technology, and can also be used in any field outside the field of artificial intelligence technology. The application field of the object recognition method, object recognition device, computer system, computer-readable storage medium and computer program product disclosed in the present invention is not limited.

[0071] Figure 2 The flowchart of the object recognition method according to the embodiment of the present disclosure is schematically shown.

[0072] like Figure 2 As shown, the method includes operations S210 to S240.

[0073] In operation S210, a request for identifying an object is received, wherein the request carries attribute information of the object to be identified.

[0074] According to the embodiments of the present disclosure, the object recognition method in the embodiments of the present disclosure can be applied to financial institutions such as banks. When facing new market entities and new customer groups, new policies require strengthening account opening qualifications and enhancing bank principal responsibilities. Therefore, due diligence becomes an important task. However, on the one hand, in order to meet regulatory requirements, manual verification takes more and more time, and incomplete data and the endless emergence of telecommunications fraud cases have made manual due diligence more and more difficult and the workload has increased, which has gradually become a process bottleneck.

[0075] According to the embodiments of the present disclosure, by using the object recognition method of the embodiments of the present disclosure, during the due diligence process, the data required for the current due diligence process can be automatically compared, eliminating the need for manual verification and improving approval efficiency.

[0076] According to the embodiments of the present disclosure, the object to be identified may be an individual, but is not limited thereto, and may also be a corporate customer. As long as the object comes to the bank to open an account, the object identification method may be used for automatic identification.

[0077] According to an embodiment of the present disclosure, the attribute information of the object to be identified may include basic information of the object to be identified.

[0078] According to the embodiments of the present disclosure, the basic information of a customer may include the customer's gender, age, city, occupation, education, credit report, and penalty status, etc. It may also include the customer's identity in the enterprise, the customer's equity in the enterprise, the region occupied by the enterprise, the enterprise's credit report, the number of employees in the enterprise, the nature of the enterprise, the enterprise's assets, and the time of establishment of the enterprise, etc. It is not limited to the above information, and may also include social behavior information between customers, such as the social relationship between customers, and information about the contact between customers through social means such as telephone and WeChat within a period of time, etc.

[0079] In operation S220, social relationship behavior information of the object to be identified is acquired based on the attribute information of the object to be identified.

[0080] In operation S230 , the social relationship behavior information of the object to be identified is processed to obtain the object association similarity of the object to be identified.

[0081] According to an embodiment of the present disclosure, the social relationship behavior information of the object to be identified may include the social relationship behavior information between the object to be identified, such as customer A, and several customers. For example, the social relationship information between customer A and customer B, customer A and customer C, and the social related application information used in the recent period, such as within 15 days or one year.

[0082] According to an embodiment of the present disclosure, several objects that have social relationship behaviors with the object to be identified may be known risky objects or known risk-free objects. However, it is not limited thereto, and may also be several known risky objects that have social relationship behaviors with the object to be identified.

[0083] According to the embodiments of the present disclosure, the social relationship behaviors between the object to be identified and the objects known to be risky, and the social relationship behaviors between the object to be identified and the objects known to be risk-free are analyzed, so as to obtain the object association similarity between the object to be identified and the objects known to be risky and known to be risk-free. The information obtained is more comprehensive, which is conducive to comprehensive analysis.

[0084] According to another embodiment of the present disclosure, the social relationship behavior between the object to be identified and the object known to be at risk is analyzed to obtain the object association similarity between the object to be identified and the object known to be at risk, which is beneficial for subsequent prediction of whether the object to be identified has risks and improves the prediction accuracy.

[0085] In operation S240 , a recognition result of the object to be recognized is determined based on the attribute information of the object to be recognized and the object association similarity of the object to be recognized, wherein the recognition result includes risk or no risk.

[0086] According to an embodiment of the present disclosure, the risk in the identification result is a risk with a fraudulent purpose or intention, while the risk-free is a risk-free with a normal purpose.

[0087] According to the embodiments of the present disclosure, based on the attribute information of the object to be identified and the object association similarity, the basic information of the customer as well as the social relationship and behavior (i.e., determining the association similarity between the object to be identified and known risky and / or risk-free customers) is used to simulate manual due diligence. The investigation information is complete and sufficient, and combined with reality, not only can the risky people with different fraudulent behaviors be identified quickly, but also with high accuracy, thereby reducing risks.

[0088] Reference below Figure 3 to Figure 7 , combined with specific embodiments Figure 2 The method shown is further explained.

[0089] Figure 3 The flowchart of the object recognition method according to the embodiment of the present disclosure is schematically shown.

[0090] like Figure 3 As shown, 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.

[0091] In operation S310, attribute information of the object to be identified is preprocessed to obtain first processed information.

[0092] According to the embodiments of the present disclosure, the attribute information of the object to be identified includes multiple features, which are diverse and complex. Therefore, preprocessing the attribute information of the object to be identified is beneficial for subsequent input into the first logistic regression model for prediction processing.

[0093] In operation S320, the first processing information and the object association similarity are input into a first logistic regression model, and a predicted probability of the object to be identified is output.

[0094] 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.

[0095] According to the embodiments of the present disclosure, a prediction threshold may be pre-set, and after obtaining the prediction probability of the object to be identified, the prediction threshold is compared with the prediction probability, and the identification result of the object to be identified is determined by comparing the result. For example, when the prediction probability is greater than or equal to the prediction threshold, it indicates that the object to be identified is a risky object; when the prediction probability is less than the prediction threshold, it indicates that the object to be identified is a risk-free object.

[0096] According to the embodiments 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 actual conditions.

[0097] According to the embodiments of the present disclosure, the object recognition method of the present disclosure, combined with the attribute information of the object to be identified and the object association similarity, utilizes the social relationship behavior between the customer to be identified and multiple known customers, and combines with the attribute information of the customer to be identified, to propose an object recognition method that uses the social relationship behavior information of the object to predict the risk level of the object to be identified; and combines with the logistic regression model for prediction, with a novel prediction method and high recognition accuracy.

[0098] According to an embodiment of the present disclosure, preprocessing the attribute information of the object to be identified to obtain first processed information may include the following operations.

[0099] The attribute information of the object to be identified is classified according to preset rules to obtain preliminary preprocessing information; and the preliminary preprocessing information is discretized to obtain first processed information.

[0100] According to the embodiments of the present disclosure, there may be multiple records for each customer, and the original data cannot be directly used for model recognition. Therefore, the data needs to be processed and integrated.

[0101] According to an embodiment of the present disclosure, the preset rule can be to classify the attribute information according to different data types, and classify the attribute information according to the data types of discrete, continuous, text and time series to obtain preliminary preprocessing information.

[0102] According to the embodiments of the present disclosure, the preliminary preprocessing information can be discretized into continuous values ​​according to the actual business significance of the data, such as the monthly income of customers can be discretized into 0-5000, 5000-1000, 10000-30000, and greater than 30000. The time series data can be converted into discrete values ​​or continuous values ​​that can be used for calculation.

[0103] According to an embodiment of the present disclosure, by preprocessing the attribute information of the object to be identified to obtain first processed information, the original data can be integrated and processed so that it can be used as an input value and input into a subsequent logistic regression model for risk prediction.

[0104] According to an optional embodiment of the present disclosure, before the attribute information of the object to be identified is classified according to the preset rules, the format of the attribute information of the object to be identified can also be uniformly processed. For example, the data in the attribute information may have problems such as key fields being empty, abnormal values, data format and single value, so data cleaning is required. For example, data with inconsistent data formats are adjusted, and records with abnormal values, customer numbers, enterprise numbers and other key fields that are empty are cleaned.

[0105] 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 as described above, which will not be elaborated here.

[0106] According to an optional embodiment of the present disclosure, before preprocessing the attribute information of the object to be identified and obtaining the first processed information, the object identification method may further include the following operations.

[0107] Judging the attribute information of the object to be identified to determine whether the attribute information includes feature singularity information; in the case where the attribute information of the object to be identified includes feature singularity information, filtering out the feature singularity information so as to pre-process the remaining information in the attribute information except the feature singularity information; and in the case where the attribute information of the object to be identified does not include feature singularity, pre-processing the attribute information.

[0108] According to the embodiments of the present disclosure, feature singularity information can be understood as information that is too singular and cannot distinguish between normal risk-free customers and abnormal risky customers based on the information. For example, the gender in the attribute information only includes male and female. When checking the situation of feature singularity, if the gender in the attribute information is either male or female for each customer and has no characteristics, the attribute information is considered to be feature singularity information, and the feature information can be deleted before preprocessing the attribute information of the object to be identified.

[0109] According to the embodiments of the present disclosure, it is designed to judge the attribute information of the object to be identified before preprocessing the attribute information of the object to be identified. The attribute information can be filtered in advance to filter out useless feature uniqueness information, thereby reducing the amount of data for subsequent preprocessing operations and improving the work efficiency of subsequent data processing and the recognition accuracy of the object to be identified.

[0110] Figure 4 The social graph associated with the object to be identified according to an embodiment of the present disclosure is schematically shown.

[0111] like Figure 4 As shown in the figure, the historical social relationship behavior records of customers A, B, C, D, E and F who have transactions can be represented by nodes A, B, C, D, E and F. Based on the social relationship as the connection between customers, the connection attributes include relationship type (such as parent-child relationship, colleague relationship, classmate relationship, etc.), application association (for example, WeChat friends, using WeChat to communicate) and / or overlap relationship (for example, both colleagues and classmates), and finally form a social relationship diagram, that is, a social graph.

[0112] According to an embodiment of the present disclosure, recursive logic is used to process Figure 4 The social graph shown can obtain the object association similarity of the object to be identified.

[0113] According to an optional embodiment of the present disclosure, the object association similarity between customers can be calculated by calculating the similarity between customer nodes in the social graph. The object association similarity of the object to be identified is determined by its associated objects.

[0114] According to the embodiments of the present disclosure, the relationship network between customers can be analyzed by using the social graph, which is conducive to discovering and identifying telecommunications fraud gangs that commit crimes in groups.

[0115] According to an optional embodiment of the present disclosure, a mathematical expression of object association similarity obtained by processing a social graph using recursive logic may be defined as the following formula (1).

[0116]

[0117] Where a and b represent customer nodes, s(a, b) represents the object association similarity between customers a and b, I(a) and I(b) represent the node sets associated with customers a and b, |I(a)| and |I(b)| represent the number of customer sets associated with customers a and b, and c is the attenuation coefficient, which can be a constant of 0.8.

[0118] It can be seen from the calculation formula that the object association similarity between customer a and customer b depends on the object association similarity of all nodes connected to customer a and customer b.

[0119] It should be noted that the starting point of the recursion is that the similarity between each node and itself is 1, and the similarity between unrelated nodes is 0 (one case is that the two nodes have no connection with other nodes). However, it is not limited to this, and the initial similarity between all nodes can also be 0 at the initial state of the recursion.

[0120] Figure 5 A social graph associated with an object to be identified according to another embodiment of the present disclosure is schematically shown.

[0121] like Figure 5 As shown, the application association number can be obtained through the associated application graph. Specifically, the social methods used by customer U1 for social behavior are phone, WeChat and QQ; the social methods used by customer U2 for social behavior are WeChat and Weibo. Then the associated application between customer U1 and customer U2 is WeChat.

[0122] Based on the above formula (I), the similarity between U1 and U2 is iterated and calculated 5 times. The process can be performed as follows.

[0123] 1. First assume s(U1, U2) = 0.8.

[0124] 2. Calculate the similarity between each associated node set Pn of U1 and U2 respectively:

[0125] U1 associated nodes (P1-phone, P2-WeChat, P3-QQ);

[0126] U2 associated nodes (P2-WeChat, P4-Weibo);

[0127] s(p1, p2), s(p1, p4), s(p2, p2), s(p2, p4), s(p3, p2), s(p3, p4).

[0128] Based on formula (1), the calculation results are as follows:

[0129] s(p1, p2)=0.8*(s(U1, U1)+s(U1, U2)) / (1*2)=0.8*(1+0.8) / (1*2);

[0130] s(p1, p4)=0.8*(s(U1, U2)) / (1*1)=0.8*0.8 / (1*1);

[0131] s(p2, p2) = 1;

[0132] s(p2, p4)=0.8*(s(U1, U2)+s(U2, U2)) / (1*2)=0.8*(0.8+0.1) / (1*2);

[0133] s(p2, p3)=0.8*(s(U1, U1)+s(U1, U2)) / (1*2)=0.8*(1+0.8) / (1*2);

[0134] s(p3, p4)=0.8*(s(U1, U2)) / (1*1)=0.8*0.8 / (1*1).

[0135] 3. After calculating the similarity of each node, recalculate s(U1, U2):

[0136] 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)).

[0137] 4. Continue from step 2 and calculate 5 times in a row to obtain the final result s(U1, U2) relative to customer U1 and customer U2.

[0138] By using the object association similarity calculation method of the embodiment of the present disclosure, the object association similarity between the object to be identified and the known risky customers can be accurately and quickly extracted, which is conducive to the subsequent prediction of the risk level of the object to be identified through the object association similarity.

[0139] According to another embodiment of the present disclosure, the object recognition method may further include acquiring historical transaction behavior information of the object to be recognized based on the attribute information of the object to be recognized.

[0140] According to an embodiment of the present disclosure, the historical transaction behavior information of the object to be identified may include the historical behavior information of the interaction between the customer and the product. For example, the historical behavior information of the interaction between the customer and the product may include the customer's clicks on the mobile banking product list and the product purchase behavior information in the past year. However, it is not limited to this, and it can also be the transaction behavior of the customer or its affiliated enterprise in the past 15 days, that is, statistics of each transaction time, amount, lending direction, transaction area, transaction channel and counterparty information of each customer or its affiliated enterprise.

[0141] 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 association similarity of the object to be recognized may further include the following operations.

[0142] Preprocess the attribute information of the object to be identified to obtain first processed information; process the historical transaction behavior information of the object to be identified to obtain second processed information; input the first processed information, the second processed information and the object association similarity into a second logistic regression model to output the predicted probability of the object to be identified; and determine the identification result of the object to be identified based on the predicted probability of the object to be identified.

[0143] According to an embodiment of the present disclosure, the recognition result of the object to be recognized is determined based on the predicted probability of the object to be recognized. This can be the same as the method described in the above embodiment of using the predicted probability output by the first logistic regression model to determine the recognition result of the object to be recognized, which will not be repeated here.

[0144] According to an embodiment of the present disclosure, the attribute information of the object to be identified is preprocessed to obtain the first processed information, which may be consistent with the method introduced in the above embodiment and will not be described in detail here.

[0145] It should be noted that, according to an embodiment of the present disclosure, the second logistic regression model can be obtained by training with the same initial logistic regression model as the first logistic regression model. During training, the initial logistic regression model can be trained using training samples with known labels, wherein the training samples with known labels include known labels, attribute information of the object, social relationship behavior information between the object and other objects, and historical transaction behavior information between the object and other objects. The attribute information of the object can be preprocessed to obtain the first processing information. The social relationship behavior information between the object and other objects is processed to obtain the object association similarity. The historical transaction behavior information between the object and other objects is processed to obtain the second processing information. The first processing information, the object association similarity, and the second processing information are input into the initial logistic regression model for training, and the converged model obtained is used as the second logistic regression model, and the recognition accuracy using the second logistic regression model is high.

[0146] The object recognition method of the embodiment of the present disclosure combines the attribute information of the object to be recognized, the object association similarity and the behavior sequence, and considers multiple aspects of features, so the data integrity is high; in addition, the logistic regression model is used for prediction, so the recognition accuracy is high.

[0147] According to an embodiment of the present disclosure, processing the historical transaction behavior information of the object to be identified to obtain the second processing information may include the following operations.

[0148] The historical transaction behavior information of the object to be identified is processed using a knowledge graph algorithm to generate a transaction graph associated with the object to be identified; the information in the transaction graph is extracted using a random walk method to obtain a behavior sequence of the object to be identified; the behavior sequence of the object to be identified is processed by one-hot encoding to generate an encoding result corresponding to the behavior sequence; and feature extraction is performed on the encoding result to obtain second processing information.

[0149] According to an embodiment of the present disclosure, the historical transaction behavior information of the object to be identified may include the historical behavior information of the interaction between the customer and the product. For example, the historical behavior information of the interaction between the customer and the product may include the customer's clicks on the mobile banking product list and the product purchase behavior information in the past year. However, it is not limited to this, and it can also be the transaction behavior of the customer or its affiliated enterprise in the past 15 days, that is, statistics of each transaction time, amount, lending direction, transaction area, transaction channel and counterparty information of each customer or its affiliated enterprise.

[0150] Figure 6 A transaction graph associated with an object to be identified according to an embodiment of the present disclosure is schematically shown.

[0151] like Figure 6 As shown, the historical transaction behavior records of customers A, B, C, D, E and F who have transactions can be represented by nodes A, B, C, D, E and F to represent each customer or their affiliated enterprises. The transaction direction is used as the connection between customers, the transaction lending direction is used as the connection direction (for example, the arrow in the figure indicates the direction), and the connection attributes include the behavior type and the transaction amount, ultimately forming a relationship diagram with the behavior sequence of the object to be identified, that is, the transaction map.

[0152] According to the embodiments of the present disclosure, a knowledge graph algorithm is used to generate a transaction graph associated with the object to be identified, which can analyze the relationship network between customers and is conducive to discovering and identifying telecommunications fraud gangs that commit crimes in groups.

[0153] According to the embodiments of the present disclosure, after the transaction graph is constructed, a random walk method with moderate time complexity can be selected to extract information in the transaction graph to obtain the behavior sequence of the object to be identified.

[0154] According to the embodiment of the present disclosure, each customer or its affiliated enterprise is firstly used as a starting point, and a random walk is adopted to regenerate the behavior sequence. That is, each customer or its affiliated enterprise is used as a starting point Vv, the jump probability of the node connected to it is calculated, the node Vx with the highest probability is selected for jumping, and the jump probability of random walking with Vx is continued to be calculated.

[0155] Stop wandering when one or more of the following conditions are met.

[0156] For example, the transaction interval is equal to 15 days; jump to the starting point (no adjacent node); the number of jump nodes exceeds 50.

[0157] At the end of the walk, all nodes and edges from the starting point to the end point are taken as the behavior sequence of the object to be identified.

[0158] According to an embodiment of the present disclosure, the jump probability of a node can be calculated according to formula (ii).

[0159] π VX =α pq (V, X)·ω VX ; Formula (II)

[0160] Among them, π VX The jump probability between node v and node x; ω VX is the weight between node v and node x; α pq (V, X) is defined as in formula (III).

[0161]

[0162] Among them, d vx Refers to the distance from node v to node x. The return parameter p can be a constant of 0.85, and the input and output parameter q can be a constant of 0.2.

[0163] By using the jump probability calculation method of the embodiment of the present disclosure, it is possible to be more inclined to jump to directly connected nodes, and the similarities between nodes can be better mined.

[0164] According to an embodiment of the present disclosure, extracting features from a behavior sequence of an object to be identified to obtain second processing information may include the following operations.

[0165] According to an embodiment of the present disclosure, a behavior sequence of an object to be identified is subjected to one-hot encoding processing to generate an encoding result corresponding to the behavior sequence; and feature extraction is performed on the encoding result to obtain second processing information.

[0166] According to an embodiment of the present disclosure, one-hot encoding is performed on the behavior sequence of the object to be identified, and an N-bit state register can be used to encode N states, each state has an independent register bit, and at any time, only one of them is valid.

[0167] For example, there are three customers U1 to U3, whose transaction behavior sequences are:

[0168] Customer transaction Customer amount Transaction type

[0169] U1: {[U2: 1000, payment]};

[0170] U2: {[U3: 2000, transfer]};

[0171] U3: {[U1: 1500, payment]}.

[0172] There are only three types of transaction customers, amounts and transaction types. Each code has 3 digits, and each digit represents a type:

[0173] U1:100; U2:010; U3:001.

[0174] So after one-hot encoding:

[0175] U1: {[010, 100, 100]};

[0176] U2: {[001, 001, 010]};

[0177] U3: {[100, 010, 001]}.

[0178] According to an optional embodiment of the present disclosure, after one-hot encoding, the behavior sequence of each customer is converted into a dense vector by the word2dev algorithm, thereby reducing a large amount of unnecessary data 0 in the behavior sequence after one-hot encoding, thereby avoiding unnecessary burden on subsequent calculations.

[0179] According to an optional embodiment of the present disclosure, performing feature extraction on the encoding result to obtain the second processing information may include an operation of inputting the encoding result into a deep long short-term memory neural network to obtain the second processing information.

[0180] According to an embodiment of the present disclosure, the deep long short-term memory neural network includes a layer of LSTM network as a further feature extraction layer, and subsequently includes two layers of LSTM deep network.

[0181] According to an embodiment of the present disclosure, after the deep long short-term memory neural network is constructed, historical customers can be used as training samples to train the network and 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 can be used as the third processing information.

[0182] According to an embodiment of the present disclosure, when training the second logistic regression model, the first processed information, the second processed information and the object association similarity obtained after processing the attribute information and the behavior sequence, and the third processed information can be combined for training, so that the final logistic regression model has high recognition accuracy.

[0183] Figure 7 The flowchart of an object recognition method according to another embodiment of the present disclosure is schematically shown.

[0184] like Figure 7 As shown, the object recognition method includes operations S710 to S740, S731 to S734, S741, and S750 to S770.

[0185] In operation S710, a user (eg, a customer manager of a bank) inputs the customer's application information into an operation terminal.

[0186] According to an embodiment of the present disclosure, the due diligence application materials provided by the customer may include, for example, the customer's name, business registration information, business registration address, and customer ID card (attribute information).

[0187] In operation S720, the operation terminal transmits the request carrying the application material information to a server having an object recognition method processing function.

[0188] In operation S730, the server obtains the client's historical transaction behavior information based on the client's application information.

[0189] In operation S740 , the server obtains the client's social relationship behavior information based on the client's application information.

[0190] In operation S750, the server pre-processes the attribute information to obtain first processed information.

[0191] The server performs the following operations on the historical transaction behavior information in sequence.

[0192] In operation S731, a transaction graph is generated;

[0193] In operation S732, a behavior sequence is obtained;

[0194] In operation S733, one-hot encoding;

[0195] In operation S734, feature extraction is performed to obtain second processing information.

[0196] In operation S741, the server processes the social relationship behavior information to obtain the object association similarity between the customer and existing known risk customers.

[0197] In operation S760, the first processed information, the second processed information, and the object association similarity are processed using a second logistic regression model to obtain a customer recognition result.

[0198] In operation S770, the identification result of the customer is sent to the operation terminal so that the customer manager can reasonably plan subsequent operations.

[0199] In summary, in order to solve the lag in manual processing in identifying new fraud methods, the embodiments of the present disclosure provide an object recognition method, which utilizes various structured and unstructured financial data within the bank, such as attribute information, social relationship behavior information, and historical transaction behavior information, for automated processing and recognition, so as to identify different fraud behaviors of telecommunications fraudsters, and present the recognition results and recognition explanations to due diligence personnel, thereby improving recognition rates and reducing risks; in addition, automated comparison eliminates the need for manual verification and improves approval efficiency.

[0200] Figure 8The block diagram of the object recognition device according to the embodiment of the present disclosure is schematically shown.

[0201] like Figure 8 As shown, the object recognition device 800 includes a receiving module 810 , an acquisition module 820 , a processing module 830 , and a determination module 840 .

[0202] A receiving module 810 is used to receive a request for identifying an object, wherein the request carries attribute information of the object to be identified;

[0203] An acquisition module 820 is used to acquire social relationship behavior information of the object to be identified based on the attribute information of the object to be identified;

[0204] A processing module 830 is used to process the social relationship behavior information of the object to be identified to obtain the object association similarity of the object to be identified; and

[0205] The determination module 840 is used to determine the recognition result of the object to be recognized based on the attribute information of the object to be recognized and the object association similarity of the object to be recognized, wherein the recognition result includes risk or no risk.

[0206] According to the embodiments of the present disclosure, a request for identifying an object is received, wherein the request carries attribute information of the object to be identified; based on the attribute information of the object to be identified, social relationship behavior information of the object to be identified is obtained; the social relationship behavior information of the object to be identified is processed to obtain the object association similarity of the object to be identified; and based on the attribute information of the object to be identified and the object association similarity of the object to be identified, an identification result of the object to be identified is determined, wherein the identification result includes technical means with or without risk, and the attribute information of the object to be identified and the object association similarity are used as a judgment basis to realize automatic identification and risk estimation; therefore, the technical problem of due diligence investigation in the prior art resulting in low processing efficiency is at least partially overcome, thereby achieving the technical effect of efficient and rapid risk estimation.

[0207] According to an embodiment of the present disclosure, the determination module 840 includes a first preprocessing submodule, a first input submodule and a first determination submodule.

[0208] A first preprocessing submodule, used for preprocessing the attribute information of the object to be identified to obtain first processed information;

[0209] A first input submodule, configured to input the first processed information and the object association similarity into a first logistic regression model, and output a predicted probability of the object to be identified; and

[0210] The first determination submodule is used to determine the recognition result of the object to be recognized based on the predicted probability of the object to be recognized.

[0211] According to an embodiment of the present disclosure, the object recognition device 800 further includes a determination module.

[0212] A judgment module is used to preprocess the attribute information of the object to be identified, and before obtaining the first processing information, judge the attribute information of the object to be identified to determine whether the attribute information includes feature uniqueness information; when the attribute information of the object to be identified includes feature uniqueness information, filter out the feature uniqueness information so that the remaining information in the attribute information except the feature uniqueness information can be preprocessed; when the attribute information of the object to be identified does not include feature uniqueness, preprocess the attribute information.

[0213] According to an embodiment of the present disclosure, the preprocessing submodule includes a classification unit and a discretization unit.

[0214] A classification unit, used to classify the attribute information of the object to be identified according to preset rules to obtain preliminary preprocessing information;

[0215] The discretization unit is used to discretize the preliminary preprocessing information to obtain first processed information.

[0216] According to an embodiment of the present disclosure, the processing module 830 includes a first processing unit and a second processing unit.

[0217] A first processing unit, configured to process 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;

[0218] The second processing unit is used to process the social graph using recursive logic to obtain the object association similarity of the object to be identified.

[0219] According to an embodiment of the present disclosure, the object recognition device 800 further includes a historical transaction acquisition module.

[0220] The historical transaction acquisition module is used to acquire historical transaction behavior information of the object to be identified based on the attribute information of the object to be identified.

[0221] The determination module 840 includes a second preprocessing submodule, a second processing submodule, a second input submodule and a second determination submodule.

[0222] A second preprocessing submodule is used to preprocess the attribute information of the object to be identified to obtain first processed information;

[0223] The second processing submodule is used to process the historical transaction behavior information of the object to be identified to obtain second processing information;

[0224] A second input submodule, configured to input the first processed information, the second processed information and the object association similarity into a second logistic regression model, and output a predicted probability of the object to be identified; and

[0225] The second determination submodule is used to determine the recognition result of the object to be recognized based on the predicted probability of the object to be recognized.

[0226] According to an embodiment of the present disclosure, the second processing submodule includes a third processing unit, a first extraction unit, an encoding unit and a second extraction unit.

[0227] A third processing unit is used to process 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;

[0228] The first extraction unit is used to extract information from the transaction graph using a random walk method to obtain a behavior sequence of the object to be identified;

[0229] an encoding unit, configured to perform one-hot encoding processing on the behavior sequence of the object to be identified, and generate an encoding result corresponding to the behavior sequence; and

[0230] The second extraction unit is used to extract features from the encoding result to obtain second processing information.

[0231] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0232] For example, any multiple of the receiving module 810, the acquisition module 820, the processing module 830, and the determination module 840 can be combined in one module / unit / subunit for implementation, or any one of the modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functions of one or more modules / units / subunits in these modules / units / subunits can be combined with at least part of the functions of other modules / units / subunits and implemented in one module / unit / subunit. According to an embodiment of the present disclosure, at least one of the receiving module 810, the acquisition module 820, the processing module 830, and the determination module 840 can be at least partially implemented 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 can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware or in any appropriate combination of any of them. Alternatively, at least one of the receiving module 810 , the acquiring module 820 , the processing module 830 , and the determining module 840 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0233] It should be noted that the object recognition device part in the embodiment of the present disclosure corresponds to the object recognition method part in the embodiment of the present disclosure. The description of the object recognition device part specifically refers to the object recognition method part, which will not be repeated here.

[0234] Fig. 9 A block diagram of a computer system suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Fig. 9 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0235] like Fig. 9 As shown, the computer system 900 according to the embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 902 or the program loaded from the storage part 908 to the random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0236] In RAM 903, various programs and data required for the operation of computer system 900 are stored. Processor 901, ROM 902 and RAM 903 are connected to each other through bus 904. Processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 902 and / or RAM 903. It should be noted that the program can also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0237] According to an embodiment of the present disclosure, the computer system 900 may further include an input / output (I / O) interface 905, which is also connected to the bus 904. The system 900 may further include one or more of the following components connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage section 908 as needed.

[0238] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0239] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0240] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0241] For example, according to an embodiment of the present disclosure, the 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 .

[0242] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains a program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the object recognition method provided by the embodiment of the present disclosure.

[0243] When the computer program is executed by the processor 901, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0244] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 909, and / or installed from a removable medium 911. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0245] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0246] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0247] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for object recognition, comprising: Receiving a request for identifying an object, wherein the request carries attribute information of the object to be identified; Based on the attribute information of the object to be identified, obtaining social relationship behavior information of the object to be identified; Processing the social relationship behavior information of the object to be identified to obtain the object association similarity of the object to be identified; Based on the attribute information of the object to be identified, obtaining historical transaction behavior information of the object to be identified; Preprocessing the attribute information of the object to be identified to obtain first processed information; Processing the historical transaction behavior information of the object to be identified to obtain second processed information; Inputting the first processed information, the second processed information and the object association similarity into a second logistic regression model, and outputting a predicted probability of the object to be identified; and Based on the predicted probability of the object to be identified, an identification result of the object to be identified is determined, wherein the identification result includes risk or no risk.

2. The method according to claim 1, wherein: Before preprocessing the attribute information of the object to be identified to obtain first processed information, the method further includes: Judging the attribute information of the object to be identified, and determining whether the attribute information includes feature uniqueness information; In the case where the attribute information of the object to be identified includes the feature singularity information, filtering out the feature singularity information so as to pre-process the remaining information in the attribute information except the feature singularity information; When the attribute information of the object to be identified does not include feature uniqueness, the attribute information is preprocessed.

3. According to the method of claim 1, the preprocessing of the attribute information of the object to be identified to obtain the first processed information comprises: Classify and process the attribute information of the object to be identified according to preset rules to obtain preliminary preprocessing information; Discretization processing is performed on the preliminary preprocessing information to obtain first processed information.

4. The method according to claim 1, wherein: The processing of the social relationship behavior information of the object to be identified to obtain the object association similarity of the object to be identified includes: Using a knowledge graph algorithm to process the social relationship behavior information of the object to be identified, and generate a social graph associated with the object to be identified; The social graph is processed using recursive logic to obtain the object association similarity of the object to be identified.

5. The method according to claim 1, wherein: The processing of the historical transaction behavior information of the object to be identified to obtain the second processed information includes: Processing the historical transaction behavior information of the object to be identified using a knowledge graph algorithm to generate a transaction graph associated with the object to be identified; Extracting information from the transaction graph using a random walk method to obtain a behavior sequence of the object to be identified; Performing one-hot encoding processing on the behavior sequence of the object to be identified to generate an encoding result corresponding to the behavior sequence; and Feature extraction is performed on the encoding result to obtain second processing information.

6. An object recognition device, comprising: A receiving module, used to receive a request for identifying an object, wherein the request carries attribute information of the object to be identified; An acquisition module, used to acquire social relationship behavior information of the object to be identified based on the attribute information of the object to be identified; A historical transaction acquisition module, which acquires historical transaction behavior information of the object to be identified based on the attribute information of the object to be identified; a processing module, configured to process the social relationship behavior information of the object to be identified to obtain the object association similarity of the object to be identified; and A determination module, comprising a second preprocessing submodule, a second processing submodule, a second input submodule and a second determination submodule; A second preprocessing submodule is used to preprocess the attribute information of the object to be identified to obtain first processed information; A second processing submodule is used to process the historical transaction behavior information of the object to be identified to obtain second processing information; A second input submodule, configured to input the first processed information, the second processed information and the object association similarity into a second logistic regression model, and output a predicted probability of the object to be identified; and The second determination submodule is used to determine the recognition result of the object to be recognized based on the predicted probability of the object to be recognized, wherein the recognition result includes risk or no risk.

7. A computer system comprising: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, the computer program comprising computer executable instructions, the instructions being used to implement the method according to any one of claims 1 to 5 when executed.

Images