Object Recognition Method, Apparatus, Computer System, and Readable Storage Medium

Abstract

The present disclosure provides an object recognition method that can be used in the field of artificial intelligence technology or other fields. The method comprises: receiving a request for object recognition, wherein the request carries attribute information of the object to be recognized; obtaining historical transaction behavior information of the object to be recognized based on the attribute information of the object to be recognized; processing the historical transaction behavior information of the object to be recognized to obtain a behavior sequence of the object to be recognized; and determining an identification result for the object to be recognized based on the attribute information of the object to be recognized and the behavior sequence of the object to be recognized, wherein the identification result includes whether the object is risky or not risky. 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] The rise of internet technology and the impact of new policies have spawned a large number of new market players and new customer groups. At the same time, these new market players and new customer groups are increasingly demanding convenient account opening.

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

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

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

[0006] An object recognition method, comprising:

[0007] receiving a request for identifying an object, wherein the request carries attribute information of the object to be identified;

[0008] Based on the attribute information of the object to be identified, obtain the historical transaction behavior information of the object to be identified;

[0009] Processing the historical transaction behavior information of the object to be identified to obtain the behavior sequence of the object to be identified; and

[0010] Based on the attribute information of the object to be identified and the behavior sequence 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.

[0011] According to an embodiment of the present disclosure, the historical transaction behavior information of the object to be identified is processed to obtain the behavior sequence of the object to be identified, including:

[0012] 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;

[0013] The random walk method is used to extract information from the transaction graph and obtain the behavior sequence of the object to be identified.

[0014] According to an embodiment of the present disclosure, determining a recognition result of the object to be recognized based on attribute information of the object to be recognized and a behavior sequence of the object to be recognized includes:

[0015] Preprocessing the attribute information of the object to be identified to obtain first processed information;

[0016] Extract features from the behavior sequence of the object to be identified to obtain second processing information;

[0017] Inputting the first processed information and the second processed information into a logistic regression model, and outputting a predicted probability of the object to be identified;

[0018] Based on the predicted probability of the object to be identified, the identification result of the object to be identified is determined.

[0019] According to an embodiment of the present disclosure, feature extraction is performed on the behavior sequence of the object to be identified to obtain second processing information including:

[0020] Perform one-hot encoding on the behavior sequence of the object to be identified to generate an encoding result corresponding to the behavior sequence;

[0021] Feature extraction is performed on the encoding result to obtain second processing information.

[0022] According to an embodiment of the present disclosure, performing feature extraction on the encoding result to obtain the second processing information includes:

[0023] The encoding result is input into a deep long short-term memory neural network to obtain second processed information.

[0024] 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:

[0025] Judging the attribute information of the object to be identified and determining whether the attribute information includes feature uniqueness information;

[0026] 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;

[0027] When the attribute information of the object to be identified does not include feature uniqueness, the attribute information is preprocessed.

[0028] According to an embodiment of the present disclosure, preprocessing the attribute information of the object to be identified to obtain first processed information includes:

[0029] Classify and process the attribute information of the object to be identified according to preset rules to obtain preliminary preprocessing information;

[0030] Discretization is performed on the preliminary preprocessing information to obtain first processed information.

[0031] Another aspect of the present disclosure provides an object recognition device, comprising:

[0032] A receiving module, configured to receive a request for identifying an object, wherein the request carries attribute information of the object to be identified;

[0033] An acquisition module, configured to acquire historical transaction behavior information of an object to be identified based on attribute information of the object to be identified;

[0034] A processing module, configured to process historical transaction behavior information of the object to be identified to obtain a behavior sequence of the object to be identified; and

[0035] 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 behavior sequence of the object to be recognized, wherein the recognition result includes risk or no risk.

[0036] Another aspect of the present disclosure provides a computer system, comprising:

[0037] one or more processors;

[0038] a memory for storing one or more programs,

[0039] When one or more programs are executed by one or more processors, the one or more processors implement the above-mentioned object recognition method.

[0040] 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.

[0041] Yet 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 executed.

[0042] 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, historical transaction behavior information of the object to be identified is obtained; the historical transaction behavior information of the object to be identified is processed to obtain a behavior sequence of the object to be identified; and based on the attribute information of the object to be identified and the behavior sequence of the object to be identified, an identification result of the object to be identified is determined, wherein the identification result includes technical means of risk or no risk, and the attribute information and behavior sequence of the object to be identified are used as a judgment basis to realize automatic identification and risk estimation; therefore, the technical problem of low processing efficiency caused by due diligence investigation in the prior art is at least partially overcome, thereby achieving the technical effect of efficient and rapid risk estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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:

[0044] Figure 1 Schematically illustrates an exemplary system architecture to which the object recognition method and apparatus disclosed herein can be applied;

[0045] Figure 2 Schematically shows a flow chart of an object recognition method according to an embodiment of the present disclosure;

[0046] Figure 3 Schematically shows a flow chart of an object recognition method according to another embodiment of the present disclosure;

[0047] Figure 4 Schematically illustrates a transaction graph associated with an object to be identified according to an embodiment of the present disclosure;

[0048] Figure 5 Schematically shows a flow chart of an application object recognition method according to another embodiment of the present disclosure;

[0049] Figure 6 A block diagram schematically shows an object recognition device according to an embodiment of the present disclosure; and

[0050] Figure 7 The block diagram schematically shows a computer system suitable for implementing an object recognition method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0051] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, 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 well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0052] 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 presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0053] All terms used herein (including technical and scientific terms) 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.

[0054] When expressions such as “at least one of A, B, and C, etc.” are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (e.g., “a system having at least one of A, B, and C” should include but is not limited to systems having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, and C, etc.). When expressions such as “at least one of A, B, or C, etc.” are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (e.g., “a system having at least one of A, B, or C” should include but is not limited to systems having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, and C, etc.).

[0055] Embodiments of the present disclosure provide an object recognition method. The method includes: receiving a request for object recognition, wherein the request carries attribute information of the object to be recognized; obtaining historical transaction behavior information of the object to be recognized based on the attribute information of the object to be recognized; processing the historical transaction behavior information of the object to be recognized to obtain a behavior sequence of the object to be recognized; and determining an recognition result of the object to be recognized based on the attribute information of the object to be recognized and the behavior sequence of the object to be recognized, wherein the recognition result includes whether the object is risky or not risky.

[0056] Figure 1 The following schematically illustrates an exemplary system architecture 100 to which the object recognition method and apparatus according to an embodiment of the present disclosure can be applied. Figure 1 The examples shown are merely examples of system architectures 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, but do not mean that the embodiments of the present disclosure may not be used in other devices, systems, environments or scenarios.

[0057] 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 as a medium for providing 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.

[0058] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software (for example only).

[0059] 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.

[0060] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process received data such as user requests, and feed back processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0061] 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 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 in other terminal devices different from the terminal devices 101, 102, or 103.

[0062] For example, the 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 imported into the terminal device 101. The terminal device 101 may then send the 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 recognition method provided by the embodiments of the present disclosure.

[0063] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0064] It should be noted that the object recognition method, object recognition device, computer system, computer-readable storage medium, and computer program product disclosed herein can be used in the field of artificial intelligence technology, and can also be used in any field other than the field of artificial intelligence technology. The application fields of the object recognition method, object recognition device, computer system, computer-readable storage medium, and computer program product disclosed herein are not limited.

[0065] Figure 2 The flowchart of the object recognition method according to the embodiment of the present disclosure is schematically shown.

[0066] like Figure 2 As shown, the method includes operations S210 to S240.

[0067] In operation S210 , a request for identifying an object is received, wherein the request carries attribute information of the object to be identified.

[0068] According to embodiments of the present disclosure, the object recognition methods of the embodiments of the present disclosure can be applied to financial institutions such as banks. When facing emerging market players and new customer groups, new policies require stricter account opening qualifications and enhanced bank principal responsibilities. Therefore, due diligence has become a critical task. However, to meet regulatory requirements, manual verification is becoming increasingly time-consuming. Furthermore, data incompleteness and the continuous emergence of telecommunications fraud cases have made manual due diligence increasingly difficult and labor-intensive, gradually becoming a process bottleneck.

[0069] According to the embodiments of the present disclosure, by utilizing the object recognition method of the embodiments of the present disclosure, the data required for the current due diligence process can be automatically compared during the due diligence process, eliminating manual verification and improving approval efficiency.

[0070] According to the embodiment of the present disclosure, the object to be identified can be an individual, but is not limited thereto, and can also be a corporate customer. As long as the object comes to the bank to open an account, the object recognition method can be used for automatic identification.

[0071] 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.

[0072] According to embodiments of the present disclosure, basic customer information may include the customer's gender, age, city, occupation, education level, credit history, and penalties. It may also include the customer's corporate identity, equity held by the customer in the company, the region occupied by the company, the company's credit history, the number of employees, the nature of the company, the company's assets, and the time of establishment of the company.

[0073] In operation S220 , historical transaction behavior information of the object to be identified is obtained based on the attribute information of the object to be identified.

[0074] According to embodiments of the present disclosure, historical transaction behavior information of the subject to be identified may include historical customer-product interaction information. For example, this information may include information about a customer's clicks and purchases of products in a mobile banking product list over the past year. However, this information is not limited to this and may also include transaction behavior of the customer or their affiliated enterprise over the past 15 days, specifically, information such as the time, amount, debit / credit direction, transaction region, transaction channel, and counterparty for each transaction for each customer or their affiliated enterprise.

[0075] In operation S230 , the historical transaction behavior information of the object to be identified is processed to obtain a behavior sequence of the object to be identified.

[0076] 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 behavior sequence of the object to be recognized, wherein the recognition result includes risk or no risk.

[0077] According to an embodiment of the present disclosure, the risk in the identification result is a risk with fraudulent purpose or intention, while the risk-free result is a risk-free result with normal purpose.

[0078] According to the embodiments of the present disclosure, based on the attribute information and behavior sequence of the object to be identified, the basic information, historical transaction behavior and operations of the customer are used to simulate manual due diligence. The investigation information is complete and sufficient, and combined with reality, it not only identifies risky people with different fraudulent behaviors quickly, but also with high accuracy, thereby reducing risks.

[0079] Reference below Figures 3 to 5 , combined with specific embodiments Figure 2 The method shown is further explained.

[0080] Figure 3 The flowchart of the object recognition method according to another embodiment of the present disclosure is schematically shown.

[0081] 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 behavior sequence of the object to be recognized includes operations S310 to S340.

[0082] In operation S310, attribute information of the object to be identified is pre-processed to obtain first processed information.

[0083] According to the embodiments of the present disclosure, the attribute information of the object to be identified includes multiple features and is diverse and complex. Therefore, preprocessing the attribute information of the object to be identified is beneficial for subsequent input into the logistic regression model for prediction processing.

[0084] In operation S320 , feature extraction is performed on the behavior sequence of the object to be identified to obtain second processing information.

[0085] According to the embodiments of the present disclosure, feature extraction is performed on the behavior sequence of the object to be identified, which is conducive to further screening and refining the data and is more conducive to improving the recognition accuracy of subsequent logistic regression model processing.

[0086] In operation S330 , the first processed information and the second processed information are input into a logistic regression model, and a predicted probability of the object to be identified is output.

[0087] In operation S340 , a recognition result of the object to be recognized is determined based on the predicted probability of the object to be recognized.

[0088] According to the embodiments of the present disclosure, a prediction threshold can be pre-set. After obtaining the predicted probability of the object to be identified, the prediction threshold is compared with the predicted probability, and the identification result of the object to be identified is determined based on the comparison result. For example, if the predicted probability is greater than or equal to the prediction threshold, it indicates that the object to be identified is a risky object; if the predicted probability is less than the prediction threshold, it indicates that the object to be identified is a non-risk object.

[0089] According to an 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 actual conditions.

[0090] According to the embodiments of the present disclosure, the object recognition method of the present disclosure combines the attribute information and behavior sequence of the object to be recognized, takes into account multiple aspects of characteristics, and has high data integrity; in addition, it uses a logistic regression model for prediction, and has high recognition accuracy.

[0091] According to an embodiment of the present disclosure, processing historical transaction behavior information of an object to be identified to obtain a behavior sequence of the object to be identified may include the following operations.

[0092] The knowledge graph algorithm is used to process the historical transaction behavior information of the object to be identified to generate a transaction graph associated with the object to be identified; and the random walk method is used to extract information from the transaction graph to obtain the behavior sequence of the object to be identified.

[0093] Figure 4The transaction graph associated with the object to be identified according to an embodiment of the present disclosure is schematically shown.

[0094] like Figure 4 As shown in the figure, 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.

[0095] 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.

[0096] According to an embodiment of the present disclosure, after the transaction graph is constructed, a random walk method with moderate time complexity can be selected to extract information from the transaction graph to obtain the behavior sequence of the object to be identified.

[0097] According to the embodiments of the present disclosure, we first regenerate the behavior sequence using a random walk approach, starting with each customer or their affiliated enterprise. Specifically, we use each customer or their affiliated enterprise as the starting point Vi, calculate the jump probability of the nodes connected to it, select the node with the highest probability for jump, and then continue to calculate the jump probability of the random walk with Vj.

[0098] Stop roaming when one or more of the following conditions are met.

[0099] 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.

[0100] 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.

[0101] According to an embodiment of the present disclosure, the node jump probability can be calculated according to Formula 1.

[0102]

[0103] Among them, Mij is the transaction amount from node vi to node vj; N+(vi) is the set of nodes connected by all outgoing edges (borrowing direction is borrowing) of node vi; eij is the set of all connected edges between node i and node j, and ε is the set of connected edges of all nodes.

[0104] According to an embodiment of the present disclosure, performing feature extraction on a behavior sequence of an object to be identified to obtain second processing information may include the following operations.

[0105] 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.

[0106] According to an embodiment of the present disclosure, one-hot encoding is performed on the behavior sequence of the object to be identified. 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.

[0107] For example, there are three customers U1 to U3, whose transaction behavior sequences are:

[0108]

[0109] There are only three categories for transaction customers, amounts, and transaction types. Each code has 3 digits, and each digit represents a type:

[0110] U1:100;U2:010;U3:001.

[0111] So after one-hot encoding:

[0112] U1: {[010, 100, 100]};

[0113] U2: {[001, 001, 010]};

[0114] U3: {[100, 010, 001]}.

[0115] According to an optional embodiment of the present disclosure, after one-hot encoding, each customer's behavior sequence is converted into a dense vector using the word2dev algorithm. This reduces the large amount of unnecessary zeros in the behavior sequence after one-hot encoding, thereby avoiding unnecessary burden on subsequent calculations.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] According to an embodiment of the present disclosure, when training a logistic regression model, the first processed information and the second processed information obtained after processing the attribute information and the behavior sequence can be combined with the third processed information for training, so that the final logistic regression model has high recognition accuracy.

[0120] According to an embodiment of the present disclosure, pre-processing the attribute information of the object to be identified to obtain first processed information may include the following operations.

[0121] 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.

[0122] 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.

[0123] According to an embodiment of the present disclosure, the preset rule can be to classify by different data types, classify the attribute information, and classify it according to the data types of discrete, continuous, text and time series to obtain preliminary preprocessing information.

[0124] According to embodiments of the present disclosure, preliminary preprocessing information can be discretized into continuous values based on the actual business significance of the data. For example, a customer's monthly income can be discretized into values between 0 and 5,000, 5,000 and 1,000, 10,000 and 30,000, and greater than 30,000. This converts time series data into discrete or continuous values that can be used for calculations.

[0125] 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 input as an input value into a subsequent logistic regression model for risk prediction.

[0126] According to an optional embodiment of the present disclosure, before classifying the attribute information of the target object according to preset rules, the format of the target object's attribute information can also be uniformly processed. For example, the attribute information may contain issues such as empty key fields, abnormal values, data format, and single values, thus requiring data cleaning. For example, data with inconsistent data formats can be adjusted, and records with abnormal values, empty key fields such as customer numbers and company numbers can be cleaned.

[0127] According to an optional embodiment of the present disclosure, the historical transaction behavior information in the object to be identified can also be subjected to data processing such as classification, cleaning, processing and integration as described above, which will not be repeated here.

[0128] According to an optional embodiment of the present disclosure, before pre-processing 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.

[0129] The attribute information of the object to be identified is judged to determine whether the attribute information includes feature uniqueness information; if the attribute information of the object to be identified includes feature uniqueness information, the feature uniqueness information is filtered out so that the remaining information in the attribute information except the feature uniqueness information is preprocessed; and if the attribute information of the object to be identified does not include feature uniqueness, the attribute information is preprocessed.

[0130] According to the embodiments of the present disclosure, feature singularity information can be understood as information that is too singular, making it impossible to distinguish between normal, risk-free customers and abnormal, risky customers. For example, the gender in attribute information only includes male and female. When checking for feature singularity, if the gender in this attribute information is either male or female for each customer, lacking any specific characteristics, the attribute information is considered singular and can be deleted before preprocessing the attribute information of the target to be identified.

[0131] 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, reduce the data volume of subsequent preprocessing operations, and improve the work efficiency of subsequent data processing and the recognition accuracy of the object to be identified.

[0132] Figure 5 The flowchart of the object recognition method according to another embodiment of the present disclosure is schematically shown.

[0133] like Figure 5 As shown, the object recognition method includes operations S510 to S530 , S541 , S5421 to S5424 , S550 and S560 .

[0134] In operation S510, a user (eg, a customer manager of a bank) inputs the customer's application information into an operation terminal.

[0135] 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).

[0136] In operation S520, the operation terminal transmits the request carrying the application document information to a server having an object recognition method processing function.

[0137] In operation S530 , the server obtains the client's historical transaction behavior information based on the client's application information.

[0138] In operation S541, the server pre-processes the attribute information to obtain first processed information.

[0139] The server performs the following operations on the historical transaction behavior information in sequence.

[0140] In operation S5421, a transaction graph is generated;

[0141] In operation S5422, a behavior sequence is obtained;

[0142] In operation S5423, one-hot encoding is performed;

[0143] In operation S5424, feature extraction is performed to obtain second processing information.

[0144] In operation S550 , the first processed information and the second processed information are processed using a logistic regression model to obtain a customer identification result.

[0145] In operation S560, the identification result of the customer is sent to the operation terminal so that the customer manager can reasonably plan subsequent operations.

[0146] 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 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 identification 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.

[0147] Figure 6 The block diagram schematically shows an object recognition device according to an embodiment of the present disclosure.

[0148] like Figure 6 As shown, the object recognition device 600 includes a receiving module 610 , an acquiring module 620 , a processing module 630 , and a determining module 640 .

[0149] A receiving module 610 is configured to receive a request for identifying an object, wherein the request carries attribute information of the object to be identified;

[0150] An acquisition module 620 is configured to acquire historical transaction behavior information of the object to be identified based on the attribute information of the object to be identified;

[0151] A processing module 630 is configured to process the historical transaction behavior information of the object to be identified to obtain a behavior sequence of the object to be identified; and

[0152] The determination module 640 is 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 behavior sequence of the object to be identified, wherein the identification result includes risk or no risk.

[0153] 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, historical transaction behavior information of the object to be identified is obtained; the historical transaction behavior information of the object to be identified is processed to obtain a behavior sequence of the object to be identified; and based on the attribute information of the object to be identified and the behavior sequence of the object to be identified, an identification result of the object to be identified is determined, wherein the identification result includes technical means of risk or no risk, and the attribute information and behavior sequence of the object to be identified are used as a judgment basis to realize automatic identification and risk estimation; therefore, the technical problem of low processing efficiency caused by due diligence investigation in the prior art is at least partially overcome, thereby achieving the technical effect of efficient and rapid risk estimation.

[0154] According to an embodiment of the present disclosure, the processing module 630 includes a processing submodule and an extraction submodule.

[0155] a processing submodule, configured to process 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; and

[0156] The extraction submodule is used to extract information from the transaction graph using a random walk method to obtain the behavior sequence of the object to be identified.

[0157] According to an embodiment of the present disclosure, the determination module 640 includes a pre-processing sub-module, a feature extraction sub-module, an input sub-module and a determination sub-module.

[0158] A preprocessing submodule, configured to preprocess the attribute information of the object to be identified to obtain first processed information;

[0159] A feature extraction submodule is used to extract features from the behavior sequence of the object to be identified to obtain second processing information;

[0160] an input submodule, configured to input the first processed information and the second processed information into a logistic regression model and output a predicted probability of an object to be identified; and

[0161] The 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.

[0162] According to an embodiment of the present disclosure, the feature extraction submodule includes an encoding unit and a feature extraction unit.

[0163] an encoding unit, configured to perform one-hot encoding on the behavior sequence of the object to be identified, and generate an encoding result corresponding to the behavior sequence; and

[0164] The feature extraction unit is used to extract features from the encoding result to obtain second processing information.

[0165] According to an embodiment of the present disclosure, the feature extraction unit includes a feature extraction subunit.

[0166] The feature extraction subunit is used to input the behavior sequence of the object to be identified into the deep long short-term memory neural network to obtain second processing information.

[0167] According to an embodiment of the present disclosure, the object recognition device 600 further includes a judgment module.

[0168] A judgment module is used to judge the attribute information of the object to be identified and determine whether the attribute information includes feature uniqueness information; if the attribute information of the object to be identified includes feature uniqueness information, filter out the feature uniqueness information so as to preprocess the remaining information in the attribute information except the feature uniqueness information; and if the attribute information of the object to be identified does not include feature uniqueness, preprocess the attribute information.

[0169] According to an embodiment of the present disclosure, the preprocessing submodule includes a classification unit and a discretization unit.

[0170] A classification unit, configured to classify the attribute information of the object to be identified according to preset rules to obtain preliminary preprocessing information; and

[0171] The discretization unit is used to discretize the preliminary preprocessing information to obtain first processed information.

[0172] According to the modules, submodules, units, and subunits of the embodiments of the present invention, any multiple or at least part of the functions of any multiple thereof can be implemented in one module. According to the modules, submodules, units, and subunits of the embodiments of the present invention, any one or more thereof can be split into multiple modules for implementation. According to the modules, submodules, units, and subunits of the embodiments of the present invention, any one or more thereof 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 of any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware, and firmware or in an appropriate combination of any of them. Alternatively, according to the modules, submodules, units, and subunits of the embodiments of the present invention, one or more thereof can be at least partially implemented as a computer program module, which can perform the corresponding function when the computer program module is run.

[0173] For example, any multiple of the receiving module 610, the acquisition module 620, the processing module 630, and the determination module 640 can be combined into one module / unit / sub-unit for implementation, or any one of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the receiving module 610, the acquisition module 620, the processing module 630, and the determination module 640 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 modes of software, hardware, and firmware, or in an appropriate combination of any of them. Alternatively, at least one of the receiving module 610 , the acquiring module 620 , the processing module 630 , and the determining module 640 may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be performed.

[0174] 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.

[0175] Figure 7The block diagram schematically shows a computer system suitable for implementing the above-described method according to an embodiment of the present disclosure. Figure 7 The computer system shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0176] like Figure 7 As shown, the computer system 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. The processor 701 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 (such as an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for executing different actions of the method flow according to an embodiment of the present disclosure.

[0177] Various programs and data required for the operation of the computer system 700 are stored in the RAM 703. The processor 701, ROM 702, and RAM 703 are connected to each other via a bus 704. The processor 701 executes the various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 702 and / or RAM 703. It should be noted that the programs may also be stored in one or more memories other than the ROM 702 and RAM 703. The processor 701 may also execute the various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0178] According to an embodiment of the present disclosure, the computer system 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The system 700 may also include one or more of the following components connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 708 including a hard disk; and a communication section 709 including a network interface card such as a LAN card or a modem. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed in the drive 710 as needed, so that computer programs read therefrom can be installed into the storage section 708 as needed.

[0179] 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 includes 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 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, 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.

[0180] 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 and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0181] According to an embodiment of the present disclosure, a 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 can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0182] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 702 and / or the RAM 703 described above and / or one or more memories other than the ROM 702 and the RAM 703 .

[0183] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, which contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product is run 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.

[0184] When the computer program is executed by the processor 701, the above functions defined in the system / device of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0185] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 709, and / or installed from a removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0186] 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 computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, languages such as Java, C++, python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving 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 via the Internet).

[0187] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, 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, program segment, or portion of code, which 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 boxes may occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession may actually be executed substantially in parallel, or they may 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, as well as the combination of boxes in the block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or may be implemented using a combination of dedicated hardware and computer instructions. It will be understood by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or coupled in various ways, and all such combinations and / or couplings fall within the scope of the present disclosure.

[0188] The embodiments of the present disclosure are described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be used in combination to advantage. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make various 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 historical transaction behavior information of the object to be identified; Processing the historical transaction behavior information of the object to be identified to obtain a behavior sequence 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 behavior sequence of the object to be identified, wherein the identification result includes risk or no risk; The processing of the historical transaction behavior information of the object to be identified to obtain the behavior sequence of the object to be identified includes: Using a knowledge graph algorithm to process historical transaction behavior information of the object to be identified, generating a transaction graph associated with the object to be identified, wherein the transaction graph includes nodes representing customers, connections between customers based on transaction relationships, transaction lending directions as connection directions, and connection attributes including behavior type and transaction amount; The information in the transaction graph is extracted using a random walk method to obtain a behavior sequence of the object to be identified, including: taking the node of the object to be identified as the starting point, using a random walk method to calculate the jump probability of the nodes connected to it, and selecting the node with the highest jump probability for jumping; and using the information of all nodes and edges from the starting point to the end point at the end of the walk as the behavior sequence of the object to be identified.

2. The method according to claim 1, wherein Determining the recognition result of the object to be recognized based on the attribute information of the object to be recognized and the behavior sequence of the object to be recognized includes: Preprocessing the attribute information of the object to be identified to obtain first processed information; Extracting features from the behavior sequence of the object to be identified to obtain second processing information; Inputting the first processed information and the second processed information into a logistic regression model, and outputting a predicted probability of the object to be identified; Based on the predicted probability of the object to be identified, a recognition result of the object to be identified is determined.

3. The method according to claim 2, wherein extracting features from the behavior sequence of the object to be identified to obtain the second processing information comprises: 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; Feature extraction is performed on the encoding result to obtain second processing information.

4. The method according to claim 3, wherein: The performing feature extraction on the encoding result to obtain second processing information includes: The encoding result is input into a deep long short-term memory neural network to obtain the second processed information.

5. 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 to determine whether the attribute information includes feature uniqueness information; In a 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; In the case that the attribute information of the object to be identified does not include feature uniqueness, the attribute information is preprocessed.

6. The method according to claim 1, wherein preprocessing the attribute information of the object to be identified to obtain first processed information comprises: Classify 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.

7. An object recognition device comprising: A receiving module, configured to receive a request for identifying an object, wherein the request carries attribute information of the object to be identified; An acquisition module, configured to acquire 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 historical transaction behavior information of the object to be identified to obtain a behavior sequence of the object to be identified; and a determination module, 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 behavior sequence of the object to be identified, wherein the identification result includes risk or no risk; Wherein, the processing module includes: a processing submodule, configured to process 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, wherein the transaction graph includes nodes representing customers, connections between customers based on transaction relationships, transaction lending directions as connection directions, and connection attributes including behavior type and transaction amount; and The extraction submodule is used to extract information from the transaction graph using a random walk method to obtain the behavior sequence of the object to be identified, including: taking the node of the object to be identified as the starting point, using a random walk method to calculate the jump probability of the nodes connected to it, and selecting the node with the highest jump probability for jumping; and using the information of all nodes and edges from the starting point to the end point at the end of the walk as the behavior sequence of the object to be identified.

8. 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 are enabled to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to implement the method according to any one of claims 1 to 6.

10. 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 6 when executed.

Images