Object state determination method, apparatus, device, and readable storage medium

Abstract

This application provides a method, apparatus, device, and readable storage medium for determining the state of an object, relating to the field of artificial intelligence technology, to improve the accuracy of determining whether the state of an object is abnormal. The method includes: determining a set of target accounts corresponding to each abnormal state object; each target account having interaction information with both the corresponding abnormal state object and the object to be processed; determining a reference similarity between the object to be processed and each abnormal state object based on the basic interaction information and target interaction information of each target account in each target account set; the basic interaction information includes the interaction information between the target account and the corresponding abnormal state object, and the target interaction information includes the interaction information between the target account and the object to be processed; and determining whether the object state of the object to be processed is abnormal based on the reference similarity. This method analyzes the interaction information of the target accounts, which can improve the accuracy of determining whether the object state is abnormal.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, device, and readable storage medium for determining the state of an object. Background Technology

[0002] In the process of investigating objects with abnormal states in target business, the investigation is often based on the object attribute characteristics of the object to be processed. For example, in the process of investigating objects related to the transfer of electronic resources, the investigation of objects with abnormal states is often based on the object attribute characteristics of the electronic resources held by the object to be processed, the account attribute characteristics of the account interacting with the account, the area of ​​interaction with the account, and the object attribute characteristics of the electronic resources held. However, in this investigation method, the accuracy of state identification for objects with unclear object attribute characteristics is low, and the accuracy of state identification for objects with incomplete object attribute characteristic information is also low. Therefore, the accuracy of determining whether the state of an object is abnormal is low. Summary of the Invention

[0003] This application provides a method, apparatus, device, and readable storage medium for determining the state of an object, which improves the accuracy of determining whether the state of an object is abnormal.

[0004] In a first aspect, this application provides a method for determining the state of an object, comprising:

[0005] Determine the target account set corresponding to each abnormal state object in the abnormal state object set, wherein each target account has interaction information with the corresponding abnormal state object and the object to be processed;

[0006] Based on the basic interaction information and target interaction information of each target account in the obtained target account sets, the reference similarity between the object to be processed and each abnormal state object is determined respectively; wherein, the basic interaction information includes the interaction information between the target account and the corresponding abnormal state object, and the target interaction information includes the interaction information between the target account and the object to be processed;

[0007] Based on the obtained reference similarities, it is determined whether the object state of the object to be processed is abnormal.

[0008] In one possible implementation, determining the sub-basic interaction reference value corresponding to the target account based on the result of the weighted summation process includes:

[0009] The result of the weighted summation process is determined as the sub-basic interaction reference value corresponding to the target account; or the ratio of the result of the weighted summation process to the sum of the weights corresponding to each sub-interaction information is determined as the sub-basic interaction reference value corresponding to the target account.

[0010] A second aspect of this application provides an apparatus for determining the state of an object, comprising:

[0011] The target account determination unit is used to determine the target account set corresponding to each abnormal state object in the abnormal state object set. Each target account has interaction information with the corresponding abnormal state object and the object to be processed.

[0012] The similarity estimation unit is used to determine the reference similarity between the object to be processed and each abnormal state object based on the basic interaction information and target interaction information of each target account in the obtained target account set; wherein, the basic interaction information includes the interaction information between the target account and the corresponding abnormal state object, and the target interaction information includes the interaction information between the target account and the object to be processed;

[0013] The object state determination unit is used to determine whether the object state of the object to be processed is abnormal based on the obtained reference similarities.

[0014] In one possible implementation, the similarity estimation unit is specifically used to perform the following operations for each of the abnormal state objects:

[0015] Determine the set of target accounts corresponding to one of the abnormal state objects among the various abnormal state objects;

[0016] Based at least on the basic interaction information of each target account in the determined target account set, determine the basic interaction reference value for the determined target account set; and

[0017] Based at least on the target interaction information of each target account, a target interaction reference value is determined for the determined set of target accounts;

[0018] Based on the basic interaction reference value and the target interaction reference value, the reference similarity between the account to be processed and the abnormal state object is determined.

[0019] In one possible implementation, the similarity estimation unit is specifically used for:

[0020] Determine a first set of accounts corresponding to the one abnormal state object, each first account including accounts that have interaction information with the one abnormal state object and have no interaction information with the account to be processed;

[0021] Based on the basic interaction information of each target account and the basic interaction information of each first account, determine the corresponding sub-basic interaction reference value for each target account; and

[0022] Based on the sub-basic interaction reference values ​​corresponding to each target account, determine the basic interaction reference values ​​for the determined set of target accounts.

[0023] In one possible implementation, the interaction information includes at least one sub-interaction information; the similarity estimation unit is specifically used for:

[0024] Determine the basic reference total value corresponding to each type of sub-interaction information in the at least one type of sub-interaction information; wherein, the basic reference total value corresponding to one type of sub-interaction information in the various types of sub-interaction information is determined based on the one type of sub-interaction information in the basic interaction information of each target account and the one type of sub-interaction information in the basic interaction information of each first account;

[0025] The similarity estimation unit is further configured to perform the following operations for each target account in the target accounts:

[0026] Based on the various sub-interaction information in the basic interaction information of a target account and the basic reference total value corresponding to the various sub-interaction information, the influence value of the target account on the various sub-interaction information is determined respectively.

[0027] Based on the determined impact values, the sub-basic interaction reference values ​​corresponding to the target account are determined.

[0028] In one possible implementation, the similarity estimation unit is specifically used to: perform weighted summation on the obtained influence values ​​according to the first preset weights corresponding to the various sub-interaction information; and determine the sub-basic interaction reference value corresponding to the target account based on the result of the weighted summation.

[0029] In one possible implementation, the similarity estimation unit is specifically used for:

[0030] The result of the weighted summation process is determined as the sub-basic interaction reference value corresponding to the target account; or the ratio of the result of the weighted summation process to the sum of the weights corresponding to each sub-interaction information is determined as the sub-basic interaction reference value corresponding to the target account.

[0031] In one possible implementation, the similarity estimation unit is specifically used for:

[0032] Determine a second set of accounts corresponding to the one abnormal state object, each second account including an account that has interaction information with the object to be processed, but has no interaction information with the one abnormal object;

[0033] Based on the basic interaction information of each target account, a first information value is determined;

[0034] The second information value is determined based on the target interaction information of each target account and the target interaction information of each second account;

[0035] Based on the first information value and the second information value, a target interaction reference value is determined for the determined target account set.

[0036] In one possible implementation, the interaction information includes at least one sub-interaction information; the similarity estimation unit is specifically used for:

[0037] Each of the at least one sub-interaction information is determined to have a first similarity reference value corresponding to each type of sub-interaction information; wherein, the first similarity reference value corresponding to one type of sub-interaction information among the various types of sub-interaction information is determined based on the type of sub-interaction information in the basic interaction information of each target account;

[0038] The first information value is determined based on the determined first similarity reference values;

[0039] Determine a second similarity reference value corresponding to each of the various sub-interaction information; wherein, the second similarity reference value corresponding to one of the various sub-interaction information is determined based on the one of the sub-interaction information in the target interaction information of each target account and the one of the sub-interaction information in the target interaction information of each second account;

[0040] The second information value is determined based on the determined second similarity reference values.

[0041] In one possible implementation, the similarity estimation unit is specifically used for:

[0042] Based on the second preset weights corresponding to the various sub-interaction information, the obtained first similarity reference values ​​are subjected to a second weighted summation process to obtain the first information value.

[0043] Based on the second preset weights corresponding to the various sub-interaction information, the obtained second similarity reference values ​​are subjected to a third weighted summation process to obtain the second information value.

[0044] In one possible implementation, the interaction information includes at least one of the following sub-interaction information:

[0045] The value of electronic resources transferred during an electronic resource transfer operation;

[0046] Number of operations for electronic resource transfer.

[0047] In one possible implementation, the object state determination unit is specifically used to: determine a state evaluation value for the object state of the object to be processed as an abnormal state based on the obtained reference similarities; if the state evaluation value is determined to be greater than a first state evaluation value threshold, then the object state of the object to be processed is determined to be abnormal.

[0048] In one possible implementation, after determining that the object state of the object to be processed is abnormal, the object state determination unit is further configured to: if the state evaluation value is determined to be greater than a second state evaluation value threshold, then determine the object to be processed as an abnormal state object, wherein the second state evaluation value threshold is not less than the first state evaluation value threshold; and add the object to be processed to the abnormal state object set.

[0049] A third aspect of this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the first aspect.

[0050] In a fourth aspect, this application provides a computer program product comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method provided in the first aspect.

[0051] In a fifth aspect, this application provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the method described in the first aspect.

[0052] Since the embodiments of this application adopt the above-described technical solution, they have at least the following technical effects:

[0053] In this embodiment, a target account with interaction information with both the abnormal state objects and the objects to be processed is used to evaluate the similarity (i.e., reference similarity) between the objects to be processed and each abnormal state object based on the interaction information between the two. Then, based on the similarity between the objects to be processed and each abnormal state, it is determined whether the object state of the object to be processed is abnormal. Thus, based on the interaction information between the account and the abnormal state objects, objects with abnormal states in the set of objects to be processed can be mined, thereby improving the accuracy of identifying whether the state of an object is abnormal. Attached Figure Description

[0054] Figure 1 A schematic diagram illustrating an application scenario for determining the object state of an object, as provided in an embodiment of this application;

[0055] Figure 2 A schematic diagram illustrating the process of manipulating an abnormal state object provided in an embodiment of this application;

[0056] Figure 3 A flowchart illustrating a method for determining the state of an object as provided in an embodiment of this application;

[0057] Figure 4 A schematic diagram illustrating a target account set provided in an embodiment of this application;

[0058] Figure 5 This application provides an example of an identification result diagram for determining whether an object to be processed is involved in telecommunications fraud.

[0059] Figure 6 This application provides a schematic diagram illustrating the interaction information between an object and an account, as illustrated in an embodiment of the present application.

[0060] Figure 7 A schematic diagram of the structure of an object state determination device provided in an embodiment of this application;

[0061] Figure 8 This is a structural diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0062] To better understand the technical solutions provided in the embodiments of this application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods; to facilitate a better understanding of the technical solutions of this application by those skilled in the art, some concepts involved in this application will be explained below.

[0063] 1) Objects, exception state objects, and objects to be processed

[0064] In the embodiments of this application, the object may be, but is not limited to, the identity identifier of a target on the Internet that has certain operational permissions. The aforementioned operations may be, but are not limited to, electronic resource transfer operations. That is, the object in the embodiments of this application may be, but is not limited to, a target that can perform electronic resource transfer operations. The aforementioned target may be, but is not limited to, a merchant, enterprise, government department, social welfare organization, or personal account, etc.

[0065] Exceptional state objects may include, but are not limited to, objects whose state is abnormal; objects to be processed include objects whose state needs to be identified as abnormal. The contents of object state and exception state will be described in detail below.

[0066] 2) Accounts, Target Account, First Account and Second Account

[0067] Generally, an account is a representation of a target's identity on the Internet. This target can be, but is not limited to, individuals, merchants, social groups, or government departments.

[0068] In this embodiment of the application, the target account refers to an account that has interaction information with an abnormal state object and also has interaction information with the object to be processed; the first account and the second account are, in the process of determining the reference similarity between the object to be processed and an abnormal state object, for the aforementioned abnormal state object, that is, for the aforementioned abnormal state object: the first account is an account that has interaction information with the abnormal state object but no interaction information with the object to be processed; the second account is an account that has interaction information with the object to be processed but no interaction information with the abnormal state object;

[0069] For ease of understanding, a specific example is given here. If object A0 is the object to be processed, and the accounts that have interactive information with object A0 include accounts B1 to B5, and object A1 is an abnormal state object, and the accounts that have interactive information with object A1 include accounts B3 to B6, then for objects A0 and A1: the target accounts include accounts B3, B4 and B5, the first account includes B6, and the second account includes B1 and B2.

[0070] The network fraud in this application mainly involves assessing the degree of abnormality of the object's state in the target business related to the transfer of electronic resources, and identifying objects with abnormal object states in the target business.

[0071] This application relates to Artificial Intelligence (AI) and machine learning technologies, and is designed based on computer vision and machine learning (ML) technologies within AI. Artificial intelligence utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to obtain optimal results—theories, methods, technologies, and application systems. In other words, artificial intelligence is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine capable of reacting in a manner similar to human intelligence.

[0072] Artificial intelligence (AI) studies the design principles and implementation methods of various intelligent machines, enabling them to perceive, reason, and make decisions. It mainly includes computer vision technology, natural language processing technology, and machine learning or deep learning. With the research and advancement of AI technology, it is being researched and applied in many fields, such as smart homes, intelligent customer service, virtual assistants, smart speakers, intelligent marketing, autonomous driving, robotics, and smart healthcare. It is believed that with further technological development, AI will be applied in even more fields and play an increasingly important role.

[0073] Machine learning is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory, among others. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, and inductive learning.

[0074] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0075] The design concept of this application will be explained below.

[0076] In the process of investigating objects with abnormal status in target businesses (such as mobile payment or other businesses related to the transfer of electronic resources), the investigation is often based on the attribute characteristics of the objects to be processed. For example, in the process of investigating objects related to electronic resource transactions, the investigation of objects with abnormal status is often based on the value of electronic resources held by the object, the account attribute characteristics of the accounts that conduct electronic resource operations with the object, the transaction area of ​​the electronic resources, and the fund mode of the electronic resources. However, this investigation method has two drawbacks: firstly, the accuracy of identifying the status of objects with unclear attribute characteristics is low; secondly, the accuracy of identifying the status of objects with incomplete attribute information is also low. Therefore, the accuracy of identifying objects with abnormal status is low. Thus, how to improve the accuracy of identifying objects with abnormal status is a problem worth considering.

[0077] In view of this, the inventors designed a method for determining the state of an object to improve the accuracy of determining whether the state of an object is abnormal. In this embodiment, an abnormal state object set is first obtained, which includes abnormal state objects that have been marked as having an abnormal state. In this embodiment, the abnormal state objects are used as black sample seeds. This embodiment involves estimating the reference similarity between the object to be processed and each abnormal state object based on the information of the common interaction accounts between the object to be processed and each abnormal state object. Then, based on the estimated reference similarities, it is determined whether the object state of the object to be processed is abnormal. The common interaction accounts include accounts that have interaction information with the corresponding abnormal state object and accounts that have interaction information with the object to be processed. In the following content of this embodiment, the common interaction accounts are described as target accounts.

[0078] Furthermore, in order to further improve the accuracy of determining whether the object state of the object to be processed is abnormal, in this embodiment of the application, the state evaluation value of the object state of the object to be processed is determined based on the obtained reference similarity values, and then the object state of the object to be processed is determined to be abnormal based on the state evaluation value.

[0079] To better understand the design concept of this application, the following examples illustrate application scenarios in the embodiments of this application; please refer to... Figure 1 This provides an application scenario for determining the object state, which may include a terminal device 110 and a server 120; the terminal device 110 and the server 120 can communicate via a network, wherein:

[0080] The terminal device 110 (such as, but not limited to, 110-1 or 110-2 shown in the figure) may have a target application installed. The target application supports mobile payment functions. The target application may include, but is not limited to, at least one of payment applications, social applications, multimedia applications, and assistance tool applications. This application embodiment does not limit this. In this application embodiment, each object (including the above-mentioned abnormal state objects and pending objects) and each account can log in to the target application and perform corresponding operations. For example, after an object logs in to the target application, it can trigger interactive operations with the account and send various messages to other objects outside the object. After an account logs in to the target application, it can trigger interactive operations with the object and send various messages to other accounts outside the account, etc.

[0081] Terminal device 110 can determine the interaction information between an object and an account based on the interaction operation between the object and the account, and can send the obtained interaction information to server 120 (such as, but not limited to, 120-1, 120-2 or 120-3 shown in the figure); terminal device can also transmit the above interaction operation to server 120, and then server 120 obtains the operation information associated with the interaction operation.

[0082] As one embodiment, the method for determining the state of an object provided in this application can be applied to the terminal device 110 and the server 120 described above.

[0083] In this embodiment of the application, when the method for determining the state of an object is applied to the terminal device 110, the terminal device 110 can obtain a set of abnormal state objects and determine the target account set corresponding to each abnormal state object in the set of abnormal state objects; and based on the basic interaction information and target interaction information of each target account in each target account set, determine the reference similarity between the object to be processed and each abnormal state object; further, based on the obtained reference similarity, determine whether the object state of the object to be processed is abnormal; wherein, the basic interaction information includes the interaction information between the target account and the corresponding abnormal state object, and the target interaction information includes the interaction information between the target account and the object to be processed;

[0084] When the object state determination method provided in this application embodiment is applied to the server 120, the server 120 can obtain the abnormal state object set and determine the target account set corresponding to each abnormal state object in the abnormal state object set; and based on the basic interaction information and target interaction information of each target account in each target account set, determine the reference similarity between the object to be processed and each abnormal state object; further, based on the obtained reference similarity, determine whether the object state of the object to be processed is abnormal.

[0085] The method by which the terminal device 110 and the server 120 obtain the set of abnormal state objects is not limited, and those skilled in the art can set it according to actual needs.

[0086] The terminal device 110 in this application embodiment may be a mobile terminal, a fixed terminal, or a portable terminal, such as a mobile phone, site, unit, device, multimedia computer, multimedia tablet, Internet node, communicator, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, personal communication system (PCS) device, personal navigation device, personal digital assistant (PDA), audio / video player, digital camera or camcorder, positioning device, television receiver, radio broadcast receiver, e-book device, gaming device, or any combination thereof, including accessories and peripherals of these devices or any combination thereof.

[0087] The server 120 in this embodiment can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or multiple cloud servers (such as, but not limited to, servers 120-1, 120-2 or 120-3 shown in the figure) that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The functions of the server 120 can be implemented by one or more cloud servers, or by one or more cloud server clusters, etc.

[0088] In one possible application scenario, cloud storage technology can be used in this application embodiment to save the above-mentioned abnormal state object set and the interaction information of the accounts that interact with each abnormal state object; where cloud storage is a new concept that is extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as storage system) refers to a storage system that uses cluster applications, grid technology and distributed storage file system functions to bring together a large number of storage devices of various types in the network (storage devices are also called storage nodes) through application software or application interfaces to work together to provide data storage and business access functions to the outside world.

[0089] In one possible application scenario, to reduce communication latency, servers 120 can be deployed in various regions. Alternatively, for load balancing, different servers 120 can serve the regions corresponding to each terminal device 110. Blockchain technology is used to store the aforementioned set of abnormal state objects and the interaction information of accounts that interact with each abnormal state object, as well as the object state determination method designed in this embodiment. Multiple servers 120 can share data through the blockchain, forming a data sharing system. For example, terminal device 110 located at location a communicates with server 120, while terminal device 110 located at location b communicates with other servers 120. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0090] Each server 120 in the data sharing system has a node identifier corresponding to that server 120. Each server 120 in the data sharing system can store the node identifiers of other servers 120 in the data sharing system so that the generated blocks can be broadcast to other servers 120 in the data sharing system according to the node identifiers of other servers 120.

[0091] Each server 120 can maintain a node identifier list as shown in the table below, storing the server 120 name and node identifier in the corresponding node identifier list. The node identifier can be an Internet Protocol (IP) address or any other information that can be used to identify the node; Table 1 uses IP addresses as an example only.

[0092] Table 1

[0093] Node 1 119.115.151.174 Node 2 118.116.189.145 … … Node N 119.124.789.258

[0094] It is understood that in the specific implementation of this application, data related to the operation of objects and accounts is involved. When the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0095] The method for determining the object state in the embodiments of this application will be described in detail below. It should be noted that the above application scenarios are only shown for the purpose of understanding the spirit and principle of this application, and the implementation of this application is not limited in any way.

[0096] First, the object states, abnormal state objects, and abnormal state object sets involved in the embodiments of this application will be further explained:

[0097] As an example, the object state in this application embodiment may refer to the state of the object on the Internet. The object state in this application embodiment may include, but is not limited to, at least one of normal state and abnormal state. The normal state can indicate that the operation of the object on the Internet conforms to the corresponding operation specifications; the abnormal state can indicate that the operation of the object on the Internet does not conform to the corresponding operation specifications.

[0098] As one embodiment, the object state determination method provided in this application is used to determine whether the object to be processed is in an abnormal state on the Internet. The abnormal state object may include the object whose object state is abnormal.

[0099] As one embodiment, the object state determination method provided in this application can also be used to determine whether the object state of the object to be processed is abnormal in the target business. In this case, in order to improve the accuracy of determining whether the object state is abnormal, the object state of the object in this application embodiment can also be the state of the object in the target business; thus, the above-mentioned abnormal object state can include objects whose object state in the target business is abnormal.

[0100] The aforementioned target businesses may include, but are not limited to, transactions that need to be processed in mobile payments, as well as business related to transactions, dating, job information, rebates (i.e., businesses related to returning benefits), financial credit, gambling, betting, money laundering, and other related activities.

[0101] It should be noted that the object status of the object to be processed in the target business obtained in this application embodiment is for positive channels, such as anti-gambling, anti-money laundering, and anti-fraud.

[0102] As one embodiment, the object state determination method provided in this application is used to determine whether the object state of the object to be processed in the target business is abnormal. The normal state of the object state can be understood, but is not limited to, that the operation of the object in the target business meets the operation convention information associated with the target business, and the abnormal state can be understood, but is not limited to, that the operation of the object in the target business does not meet the operation convention information associated with the target business. For example, if an object has a fraudulent operation in the target business, it can be considered that the business operation of the object in the target business does not meet the operation convention information associated with the target business. When an object has an abnormal resource aggregation operation in the target business, it can also be considered that the object does not meet the operation determination information associated with the target business.

[0103] The aforementioned abnormal resource aggregation operations can include, but are not limited to, operations that aggregate large amounts of electronic resources in a short period of time, such as the money laundering operations mentioned above. For ease of understanding, an example is given here, using online gambling as the target business. In the set of abnormal state objects associated with the online gambling business, the abnormal state object can be an abnormal behind-the-scenes bookmaker. This abnormal behind-the-scenes bookmaker can use a code-sharing method, that is, control a large number of payment codes on various platforms through various illegal channels. When an account repeatedly transfers electronic resources (e.g., purchasing chips) to this abnormal behind-the-scenes bookmaker, the bookmaker's app will randomly assign the transactions to different payment codes, thereby creating the illusion that the account is making payments to various virtual merchants in an attempt to evade conventional risk control identification strategies. Abstractly speaking, the various accounts of the aforementioned abnormal behind-the-scenes bookmaker will transfer electronic resources to different virtual merchants through different payment codes, and ultimately, the aforementioned abnormal behind-the-scenes bookmaker will receive electronic resources transferred from accounts of different virtual merchants (e.g., gambling accounts).

[0104] Please see Figure 2This document provides a schematic diagram illustrating the manipulation by an anomalous behind-the-scenes manipulator. This manipulator controls multiple virtual merchants C1, C2, ..., Cn (n being a positive integer) and their associated payment codes D1, D2, ..., Dn. These virtual merchants may be disguised as legitimate businesses, such as breakfast shops, snack bars, bookstores, clothing stores, and cafes. Accounts B1, B2, ..., Bm (m being a positive integer) wish to participate in online gambling, for example, by purchasing chips and / or making direct payments. Account B1 may participate in online gambling through virtual merchant C1 and transfer electronic resources via virtual merchant C1's payment code D1 (e.g., at least one interaction such as purchasing chips or making direct payments to participate in gambling); accounts B2 and B3 may participate in online gambling through virtual merchant C2 and transfer electronic resources via virtual merchant C2's payment code D2; accounts Bm, etc., may participate in online gambling through virtual merchant Cn and transfer electronic resources via virtual merchant Cn's payment code Dn.

[0105] It should be noted that in the above embodiments, the interactive operation of obtaining abnormal state objects is used for positive channels, such as anti-gambling, anti-money laundering, and anti-fraud.

[0106] As one embodiment, the set of abnormal state objects in this application embodiment can be a set consisting of at least one abnormal state object.

[0107] As one embodiment, the object state determination method provided in this application can also be used to determine whether the object state of the object to be processed is abnormal in different target services. In this case, in order to improve the accuracy of determining whether the object state of the object to be processed is abnormal in different target services, this application embodiment may, but is not limited to, setting up a set of abnormal state objects associated with different target services. The set of abnormal state objects associated with the target services includes abnormal state objects whose object state is abnormal in the aforementioned target services.

[0108] Secondly, the interactive information and interactive operations involved in the embodiments of this application are explained: the interactive information between the account and the object in the embodiments of this application may be, but is not limited to, information (or data) triggered or associated by the interactive operation between the account and the object; the interactive operations involved in the embodiments of this application may be, but are not limited to, electronic resource transfer operations, multimedia information transfer operations (video, audio or text and images, etc.) or game resources, etc.

[0109] As one embodiment, the interactive operation involved in this application embodiment may include a first operation triggered by and executed by an account, such as the first operation may include, but is not limited to, the operation of the account actively transferring electronic resources to the object; the interactive operation may also include a second operation triggered by the object and executed by the account, such as the second operation may be the object showing a payment code or other payment information to the account, and then the account transferring electronic resources to the object based on the payment code or other payment information; the interactive information may also include a third operation triggered by the object and executed by the object, such as the third operation may be the object actively transferring electronic resources to the account, etc.

[0110] The electronic resource transfer operation in this application embodiment may include the operation of transferring electronic resources, which can also be called mobile payment. Mobile payment represents the operation of an account making a payment through a mobile network. Among them, the electronic resources involved in this application embodiment can be at least one of funds and information resources. The funds mentioned above can include at least fiat currency, electronic money, etc. Fiat currency refers to a currency that is legally mandated to circulate and be used. Electronic money refers to currency stored in electronic form in the electronic wallet held by the account (such as wallets in mobile payment applications, but not limited to them). The information resources mentioned above can include, but are not limited to, game resources (such as game equipment), multimedia resources (such as video, audio, etc.), and electronic coupons (such as electronic group-buying coupons, electronic discount coupons, etc.).

[0111] The aforementioned interactive information may include, but is not limited to, the trigger time of the interactive operation, operation description information, or the number of times the interactive operation is performed; when the interactive operation includes an electronic resource transfer operation, the interactive information in this application embodiment may include, but is not limited to, at least one of the following sub-interactive information: the electronic resource value transferred by the aforementioned electronic resource transfer operation and the number of times the aforementioned electronic resource transfer operation is performed.

[0112] For ease of understanding, a specific example of an interactive operation and interactive information is given here. The interactive operation can be a first electronic resource transfer operation in which an account actively transfers electronic resources to an object. The interactive information can include at least one of the following: the electronic resource value associated with the first electronic resource transfer operation of the account to the object, and the number of times the account performed the first electronic resource transfer operation to the object. For example, please refer to the contents of Table 2 below.

[0113] Table 2:

[0114]

[0115] As one embodiment, when an interactive operation is a second electronic resource transfer operation in which an object transfers electronic resources to an account, the interactive information may include at least one of the following: the electronic resource value associated with the object's second electronic resource transfer operation to the account, and the number of times the object performs the second electronic resource transfer operation to the account, as can be seen in Table 3 below.

[0116] Table 3:

[0117]

[0118] based on Figure 1 The following describes an example of a method for determining the state of an object in an embodiment of this application. Please refer to the following examples. Figure 3 This flowchart illustrates a method for determining the state of an object according to an embodiment of this application. It can be applied, but is not limited to, the aforementioned terminal device 110 or server 120, and specifically includes the following steps:

[0119] Step S301: Determine the target account set corresponding to each abnormal state object in the abnormal state object set, wherein each target account has interaction information with the corresponding abnormal state object and the above-mentioned object to be processed.

[0120] As one embodiment, in step S301, the set of abnormal state objects can be determined first. The specific method of determining the set of abnormal state objects is not limited. Those skilled in the art can set it according to actual needs. For example, the set of abnormal state objects uploaded by the reviewer can be determined as the set of abnormal state objects, or the set of abnormal state objects updated in real time can be obtained directly from the blockchain or cloud service.

[0121] As one embodiment, when the object state determination method provided in this application is used to determine whether the object state of the object to be processed is abnormal in the target business, the abnormal state object set in step S301 can be the abnormal state object set associated with the target business, so as to improve the accuracy of identifying objects with abnormal object states in the target business.

[0122] As one embodiment, regarding the aforementioned abnormal state objects, in the process of determining whether the object state of the object to be processed is abnormal, each of the aforementioned abnormal state objects corresponds to a target account set. For different abnormal state objects, the number of target accounts in their corresponding target account sets is determined according to the actual situation; that is, the number of target accounts in a target account set may be 0, 1, 2, or more than 2, etc. A specific example is provided here for illustration; please refer to [link / reference]. Figure 4If object A0 is the object to be processed, and objects A1, A2, and A3 are all abnormal state objects, and the accounts that have interaction information with object A0 include accounts B1 to B5, the accounts that have interaction information with object A1 include accounts B3 to B6, the accounts that have interaction information with object A2 include accounts B5 to B7, and the accounts that have interaction information with object A3 include accounts B6 to B8; then the target account set 1 corresponding to object A1 is {account B3, account B4, account B5}, the target account set 2 corresponding to object A2 is {account B5}, and the target account set 3 corresponding to object A3 is empty; for the abnormal state objects corresponding to the empty target account set, the following step S302 can be skipped directly.

[0123] Step S302: Based on the basic interaction information and target interaction information of each target account in the obtained target account set, determine the reference similarity between the above-mentioned object to be processed and each abnormal state object; wherein, the above-mentioned basic interaction information includes the interaction information between the target account and the corresponding abnormal state object, and the above-mentioned target interaction information includes the interaction information between the target account and the above-mentioned object to be processed.

[0124] As one embodiment, step S302 can be performed on a non-empty target account set. For an empty target account set, the reference similarity between the object to be processed and the abnormal state object corresponding to the empty target account set can be directly set to a preset reference similarity to improve the efficiency of determining the reference similarity between the object to be processed and each abnormal state object. In order to improve the efficiency of subsequent processing based on the determined reference similarity, the preset reference similarity can be set to 0 in this embodiment, but is not limited to it.

[0125] As one embodiment, in step S302, the following operations can be performed on each of the above-mentioned abnormal state objects: determining the target account set corresponding to one of the above-mentioned abnormal state objects; determining a basic interaction reference value for the above-mentioned determined target account set based at least on the basic interaction information of each target account in the determined target account set; and determining a target interaction reference value for the above-mentioned determined target account set based at least on the target interaction information of each target account; and determining a reference similarity between the account to be processed and the above-mentioned abnormal state object based on the basic interaction reference value and the target interaction reference value; wherein, the specific method for determining the reference similarity between the account to be processed and the above-mentioned abnormal state object will be further explained below.

[0126] Step S303: Based on the obtained reference similarities, determine whether the object state of the above-mentioned object to be processed is abnormal.

[0127] As one embodiment, in order to improve the accuracy of determining whether the object state of the object to be processed is abnormal, in this embodiment of the application, the state evaluation value of the object state of the object to be processed is determined based on the obtained reference similarity values, but not limited to; then, the object state of the object to be processed is determined to be abnormal based on the state evaluation value; if the state evaluation value is determined to be greater than the first state evaluation value threshold, the object state of the object to be processed is determined to be abnormal; otherwise, the object state of the object to be processed is determined to be normal; wherein, the first state evaluation value threshold is not limited, and those skilled in the art can set it according to actual needs.

[0128] As one embodiment, in order to improve the accuracy of determining whether the object state of the object to be processed is abnormal, this embodiment of the application can be based on the principle of the following formula (1a), where the sum of the obtained reference similarities is determined as the state evaluation value corresponding to the object to be processed, or based on the principle of the following formula (1b), where the obtained reference similarities and the abnormal weights corresponding to the abnormal object states are weighted and summed, and the result is determined as the state evaluation value corresponding to the object to be processed; wherein, the above-mentioned abnormal weights can characterize the degree to which the object state of the abnormal object state is an abnormal state, such as, but not limited to, determining the abnormality level of the abnormal object state as the abnormal weight corresponding to the abnormal state object, etc.; those skilled in the art can also process the obtained reference similarities in other ways to obtain the state evaluation value corresponding to the object to be processed.

[0129]

[0130]

[0131] In formulas (1a) and (1b), U is the state evaluation value corresponding to the object to be processed; j is the identifier of the abnormal state object; J is the total number of abnormal state objects in the abnormal state object set; T i It is the abnormal weight corresponding to the abnormal state object identified as j.

[0132] As an embodiment, to further improve the accuracy of identifying objects in an abnormal state, in step S303 of this embodiment, it can be further determined whether the object to be processed can be used as an abnormal state object for estimating whether the object state of other objects is abnormal. Specifically, after determining that the object state of the object to be processed is abnormal in step S303, the state evaluation value corresponding to the object to be processed is compared with the second state evaluation value threshold. If it is determined that the state evaluation value is greater than the second state evaluation value threshold, the object to be processed can be identified as an abnormal state object and added to the abnormal state object set to participate in the subsequent object state determination process. The second state evaluation value threshold is not less than the first state evaluation value threshold. The specific value of the second state evaluation value threshold is not limited, and those skilled in the art can set it according to business experience or other influencing factors.

[0133] As one embodiment, after determining the state evaluation value corresponding to the object to be processed in step S303, the state evaluation value can also be used as an evaluation feature. Based on this evaluation feature and other evaluation features corresponding to the object to be processed, it can be determined whether the object to be processed has a target fraud operation. The target fraud operation is not limited; those skilled in the art can set it according to actual needs, such as, but not limited to, dating fraud, rebate fraud, telecommunications fraud, or part-time job fraud. For ease of understanding, please refer to [link to relevant documentation]. Figure 5 Here is a diagram showing the identification results of whether the target object is involved in telecommunications fraud. The diagram shows the 16 dimensions of evaluation features of the target object analyzed during the identification process (i.e., the detection risk points in the diagram). The identification results of the target object are displayed in the identification result display area 501 of the diagram. It can be seen from the diagram that the target object has engaged in telecommunications fraud.

[0134] The following content of this application embodiment will describe in detail the specific method of determining the reference similarity between the account to be processed and each abnormal state object in step S302 above. The following only takes one abnormal state object among the abnormal state objects as an example to explain the determination of the reference similarity between the account to be processed and that one abnormal state object.

[0135] As one embodiment, in this application embodiment, the sum of the above-mentioned basic interaction reference value and the target interaction reference value can be determined as the reference similarity between the account to be processed and the above-mentioned abnormal state object based on the following formula (2a); or the product of the above-mentioned basic interaction reference value and the target interaction reference value can be determined as the reference similarity between the account to be processed and the above-mentioned abnormal state object based on the following formula (2b).

[0136] A j =R j+COM j Formula (2a)

[0137] A j =R j ×COM j Formula (2b)

[0138] In formulas (2a) and (2b), j is the identifier of the abnormal state object, and A j R is the reference similarity between the object to be processed and the abnormal state object identified as j. j It is the base interaction reference value for the set of target accounts corresponding to the abnormal state object identified as j, COM j It is the target interaction reference value for the set of target accounts corresponding to the abnormal state object identified as j.

[0139] As one embodiment, to further improve the accuracy of the determined basic interaction reference values, in step S302, the basic interaction reference values ​​for the determined target account set can be determined in the following ways, but are not limited to: determining the first account set corresponding to the above-mentioned abnormal state object; determining the sub-basic interaction reference values ​​corresponding to each of the above-mentioned target accounts based on the basic interaction information of each of the above-mentioned target accounts and the basic interaction information of each of the above-mentioned first accounts; and determining the basic interaction reference values ​​for the determined target account set based on the sub-basic interaction reference values ​​corresponding to each of the above-mentioned target accounts; wherein, each first account in the first account set includes an account that has interaction information with the above-mentioned abnormal state object but has no interaction information with the above-mentioned account to be processed.

[0140] Specifically, in the process of determining the basic interaction reference value for the determined target account set based on the sub-basic interaction reference values ​​corresponding to each of the target accounts, the sum of the sub-basic interaction reference values ​​corresponding to each of the target accounts can be used as the basic interaction reference value for the determined target account set based on the principle of the following formula (3a); or the average value of the sub-basic interaction reference values ​​corresponding to each of the target accounts can be used as the basic interaction reference value for the determined target account set based on the principle of the following formula (3b).

[0141]

[0142]

[0143] In formulas (3a) and (3b) above, j is the identifier of the abnormal state object, and R jis the base interaction reference value for the set of target accounts corresponding to the abnormal state object identified as j; n is the identifier of the target account in the set of target accounts corresponding to the abnormal state object identified as j; N is the number of target accounts in the set of target accounts corresponding to the abnormal state object identified as j; R n It is the sub-basic interaction reference value corresponding to the target account marked n in the target account set corresponding to the abnormal state object marked j.

[0144] As one embodiment, the interaction information in this application embodiment may include at least one sub-interaction information, that is, the interaction information may include one sub-interaction information or multiple sub-interaction information. Then, in step S302, in the process of determining the sub-basic interaction reference value corresponding to each of the target accounts based on the basic interaction information of each target account and the basic interaction information of each first account, the basic reference total value corresponding to each of the at least one sub-interaction information can be determined. Further, for each of the target accounts, the following operations are performed respectively: based on the various sub-interaction information in the basic interaction information of a target account and the basic reference total value corresponding to each of the various sub-interaction information, the influence value of the target account on the various sub-interaction information is determined respectively, and based on the determined influence values, the sub-basic interaction reference value corresponding to the target account is determined.

[0145] As one embodiment, the basic reference total value corresponding to one of the various sub-interaction information is determined based on the aforementioned sub-interaction information in the basic interaction information of each target account and the aforementioned sub-interaction information in the basic interaction information of each first account; for example, the basic reference total value corresponding to the various sub-interaction information can be obtained based on the principle of the following formula (4a) or formula (4b), wherein

[0146]

[0147]

[0148] In formulas (4a) and (4b) above, i is the identifier of one type of sub-interaction information among the various sub-interaction information; R 总_i i is the base reference total value corresponding to a sub-interaction information identified as i; e is the account identifier of the account in the target account and the first account mentioned above; E is the total number of accounts in the target account and the first account mentioned above; iATM e It is the value of a sub-interaction information identified as i within the basic interaction information of the account identified as e.

[0149] As one embodiment, when determining the basic reference total value corresponding to a sub-interaction information based on the above formula (4a) in this application embodiment, the influence value of the above target account on the above various sub-interaction information can be determined based on the principle of the following formula (5a), but is not limited to it; when determining the basic reference total value corresponding to a sub-interaction information based on the above formula (4b), the influence value of the above target account on the above various sub-interaction information can be determined based on the principle of the following formula (5b), but is not limited to it.

[0150]

[0151] Y_i=|R 总_i -iATM n |Formula (5b)

[0152] In formulas (5a) and (5b) above, i is the identifier of one type of sub-interaction information among the various sub-interaction information; R 总_i i is the base reference total value corresponding to a sub-interaction information identified as i; n is the identifier of the target account mentioned above; iATM n Y_i is the value of a sub-interaction information identified as i in the basic interaction information of the target account identified as n; Y_i is the influence value of the target account identified as n on the sub-interaction information identified as i.

[0153] As an example, in the process of determining the sub-basic interaction reference value corresponding to a target account based on the determined influence values, it is possible, but not limited to, to determine the sum of the influence values ​​of a target account for various sub-interaction information as the sub-basic interaction reference value corresponding to a target account based on the principle of the following formula (6).

[0154]

[0155] In formula (6) above, n is the identifier of the target account; R n Y_i is the sub-basic interaction reference value corresponding to the target account identified as n; i is the identifier of one of the various sub-interaction information mentioned above; Y_i is the influence value of the target account identified as n on the sub-interaction information identified as i.

[0156] Furthermore, in the process of determining the sub-basic interaction reference value corresponding to the aforementioned target account based on the determined various influence values, the obtained influence values ​​can be weighted and summed according to the first preset weights corresponding to the various sub-interaction information; and the sub-basic interaction reference value corresponding to the aforementioned target account can be determined according to the result of the weighted summation.

[0157] If possible, but not limited to, based on the principle of the following formula (7a), the result of the above weighted summation process can be determined as the sub-basic interaction reference value corresponding to the above target account; or based on the principle of the following formula (7b), the ratio of the result of the above weighted summation process to the sum of the weights corresponding to the above sub-interaction information can be determined as the sub-basic interaction reference value corresponding to the above target account.

[0158]

[0159]

[0160] In formulas (7a) and (7b) above, n is the identifier of the target account; R n Y_i is the sub-basic interaction reference value corresponding to the target account identified as n; i is the identifier of one of the various sub-interaction information mentioned above; Y_i is the influence value of the target account identified as n on the sub-interaction information identified as i; K i It is the first preset weight corresponding to a type of sub-interaction information identified as i, where I is the total number of types of sub-interaction information.

[0161] In this embodiment, when the interaction information includes two types of interaction information, the above formulas (7a) and (7b) can be transformed into the following formulas (7c) and (7d); when the interaction information includes three types of interaction information, the above formulas (7a) and (7b) can be transformed into the following formulas (7e) and (7f). When the types of sub-interaction information included in the interaction information are other numbers, the same logic can be applied, and will not be repeated here.

[0162] R n =K1×Y_1+K2×Y_2 (Formula 7c)

[0163]

[0164] R n =K1×Y_1+K2×Y_2+K3×Y_3 (Formula 7e)

[0165]

[0166] As one embodiment, in step S302, during the process of determining the target interaction reference value for the determined set of target accounts based at least on the target interaction information of each of the target accounts, the target interaction parameter value can be determined based on the interaction information of all accounts that have interactive operations with the object to be processed, and the interaction information between the target accounts and the corresponding abnormal state objects in each set of target accounts. Specifically, it can be, but is not limited to, determining the second set of accounts corresponding to the abnormal state object; determining a first information value based on the basic interaction information of each of the target accounts, and determining a second information value based on the target interaction information of each of the target accounts and the target interaction information of each second account; further determining the target interaction reference value for the determined set of target accounts based on the first information value and the second information value; wherein each second account includes an account that has interaction information with the object to be processed but has no interaction information with the abnormal object.

[0167] Furthermore, the interaction information in this application embodiment may include at least one sub-interaction information. That is, the interaction information in this application embodiment may include one type of sub-interaction information or multiple types of sub-interaction information. In order to improve the accuracy of the determined target interaction reference value, this application embodiment may, but is not limited to, determine the first similarity reference value corresponding to each type of sub-interaction information in the above-mentioned at least one type of sub-interaction information, and determine the above-mentioned first information value based on each determined first similarity reference value; wherein, the first similarity reference value corresponding to one type of sub-interaction information in the above-mentioned various types of sub-interaction information is determined based on the above-mentioned one type of sub-interaction information in the basic interaction information of each target account.

[0168] As one embodiment, the first similarity reference value corresponding to various sub-interaction information can be determined based on the principles of the following formula (8a) or formula (8b), but is not limited to this embodiment.

[0169]

[0170]

[0171] In formulas (8a) and (8b) above, i is the identifier of one type of sub-interaction information among the various sub-interaction information; Q1 总_i The first information value mentioned above; n is the account identifier of the target account mentioned above; N is the total number of target accounts in the determined target account set mentioned above; iATM n It is the value of a sub-interaction information identified as i in the basic interaction information of the target account identified as n; It is the first similarity reference value corresponding to a type of sub-interaction information identified as i.

[0172] As an example, in order to further improve the accuracy of the determined target interaction reference value, this application embodiment may, but is not limited to, determine the second similarity reference value corresponding to the various sub-interaction information, and determine the second information value based on the determined second similarity reference value; wherein, the second similarity reference value corresponding to one of the various sub-interaction information is determined based on the sub-interaction information in the target interaction information of each target account and the sub-interaction information in the target interaction information of each second account; specifically, this application embodiment may, but is not limited to, determine the second similarity reference value corresponding to various sub-interaction information based on the principle of the following formula (9a) or formula (9b).

[0173]

[0174]

[0175] In formulas (9a) and (9b) above, i is the identifier of one type of sub-interaction information among the various sub-interaction information; Q2 总_i The second information value mentioned above; m is the account identifier of the account in the target account and the second account mentioned above; M is the total number of accounts in the target account and the second account mentioned above; iATM m It is the value of a sub-interaction information identified as i within the basic interaction information of the account identified as m; It is the second similarity reference value corresponding to a type of sub-interaction information identified as i.

[0176] As an embodiment, to further improve the accuracy of the finally determined target interaction reference value, this embodiment of the application may also perform a second weighted summation process on the obtained first similar reference values ​​based on the second preset weights corresponding to the various sub-interaction information to obtain the first information value; and perform a third weighted summation process on the obtained second similar reference values ​​based on the second preset weights corresponding to the various sub-interaction information to obtain the second information value; specifically, the first information value may be obtained based on, but is not limited to, the principles of the following formula (10a) or formula (10b); for example, the second information value may be obtained based on, but is not limited to, the principles of the following formula (11a) or formula (11b).

[0177]

[0178]

[0179] In formulas (10a) and (10b) above, i is the identifier of one type of sub-interaction information among the various sub-interaction information; Q1 总_iThe first information value mentioned above; n is the account identifier of the target account mentioned above; N is the total number of target accounts in the determined target account set mentioned above; iATM n It is the value of a sub-interaction information identified as i in the basic interaction information of the target account identified as n; It is the first similarity reference value corresponding to a sub-interaction information identified as i; W i It is the second preset weight corresponding to a type of sub-interaction information identified as i.

[0180]

[0181]

[0182] In formulas (11a) and (11b) above, i is the identifier of one type of sub-interaction information among the various sub-interaction information; Q2 总_i The second information value mentioned above; m is the account identifier of the account in the target account and the second account mentioned above; M is the total number of accounts in the target account and the second account mentioned above; iATM m It is the value of a sub-interaction information identified as i within the basic interaction information of the account identified as m; It is the second similarity reference value corresponding to a sub-interaction information identified as i; W i It is the second preset weight corresponding to a type of sub-interaction information identified as i.

[0183] As one embodiment, in the process of determining the target interaction reference value for the determined target account set based on the first information value and the second information value, the difference between the first information value and the second information value can be used as the target interaction reference value, or the ratio of the first information value and the second information value can be used as the target interaction parameter value. Those skilled in the art can use this information according to actual needs. To facilitate understanding of obtaining the target interaction reference value, a specific example is given here. If the interaction information in the embodiment of this application includes two types of interaction information, the target interaction reference value can be obtained by the principle of the following formula (12a) or formula (12b), but is not limited to this.

[0184]

[0185]

[0186] In formulas (12a) and (12b) above, i is the identifier of one type of sub-interaction information among the various sub-interaction information; Q1 总_i The first information value mentioned above; n is the account identifier of the target account mentioned above; N is the total number of target accounts in the determined target account set mentioned above; iATM nIt is the value of a sub-interaction information identified as i within the basic interaction information of the target account identified as n; Q2 总_i The second information value mentioned above; m is the account identifier of the account in the target account and the second account mentioned above; M is the total number of accounts in the target account and the second account mentioned above; iATM m W is the value of a sub-interaction information identified as i within the basic interaction information of the account identified as m; i It is the second preset weight corresponding to a type of sub-interaction information identified as i; j is the identifier of the abnormal state object, COM j It is the target interaction reference value for the set of target accounts corresponding to the abnormal state object identified as j.

[0187] That is, based on the principles of formulas (2a) to (12b) in the embodiments of this application, the embodiments of this application can, but are not limited to, obtain the reference similarity between the object to be processed and each abnormal state object based on any one of the following formulas (13a) to (13b).

[0188]

[0189]

[0190]

[0191]

[0192]

[0193] In formulas (13a) to (13c) above, j is the identifier of the abnormal state object, A j R is the reference similarity between the object to be processed and the abnormal state object identified as j; n is the identifier of the target account in the target account set corresponding to the abnormal state object identified as j; N is the total number of target accounts in the target account set corresponding to the abnormal state object identified as j; n The identifier is the sub-basic interaction reference value corresponding to the target account identified as n; i is the identifier of one of the various sub-interaction information mentioned above; iATM n It is the value of a sub-interaction information identified as i in the basic interaction information of the target account identified as n; m is the account identifier of the account in the target account and the second account; M is the total number of accounts in the target account and the second account; iATM m W is the value of a sub-interaction information identified as i within the basic interaction information of the account identified as m; i It is the second preset weight corresponding to a type of sub-interaction information identified as i.

[0194] It should be noted that obtaining the reference similarity between the object to be processed and each abnormal state object based on any one of the above formulas (13a) to (13b) is only an exemplary explanation. Those skilled in the art can also flexibly obtain other ways to determine the above reference similarity based on the principles of the above formulas (2a) to (12b).

[0195] The following is a specific example of the object state determination method provided in the embodiments of this application; in this example, the interaction information includes sub-interaction information X1 and sub-interaction information X2, and the sub-basic interaction reference value corresponding to the target account can be determined based on the following formula (14); the reference similarity between the object to be processed and each abnormal state object is determined based on the following formula (15).

[0196]

[0197]

[0198] In formulas (14) and (15), i is the identifier of one type of sub-interaction information among the various sub-interaction information mentioned above; A j is the reference similarity between the object to be processed and the abnormal state object identified as j; e is the identifier of the account (including the target account and the first account) that has interaction information with the abnormal state object identified as j; E is the total number of accounts that have interaction information with the abnormal state object identified as j; m is the identifier of the account (including the target account and the second account) that has interaction information with the object to be processed; M is the total number of accounts that have interaction information with the object to be processed; 1_ATM e The value of sub-interaction information X1 in the basic interaction information of the account identified as e is 1; 2_ATM e is the value of sub-interaction information X2 in the basic interaction information of the account identified as e, which is 1; n is the identifier of the target account in the target account set corresponding to the abnormal state object identified as j; N is the total number of target accounts in the target account set corresponding to the abnormal state object identified as j; R n It is the sub-basic interaction reference value corresponding to the target account marked as n in the target account set corresponding to the abnormal state object marked as j; K1 and K2 are the first preset weights of sub-interaction information X1 and X2 respectively, and W1 and W2 are the second preset weights of sub-interaction information X1 and X2 respectively.

[0199] As an example, when the basic interaction information and target interaction information of each target account are not available, this embodiment of the application may also use the sub-basic interaction reference value R corresponding to each target account. n Determined as (E is the total number of target accounts in the target account set). If the amount transferred from different accounts to the same target is considered the same, and the number of transfers from different accounts to the same target is considered the same, then the above formula (15) can be transformed into the following formula (15a):

[0200]

[0201] In formula (15a), j is the identifier of the abnormal state object; A j G1 is the reference similarity between the object to be processed and the abnormal state object identified as j; G2 is the total number of target accounts in the target account set corresponding to the abnormal state object identified as j; G3 is the total number of accounts (including target accounts and first accounts) that have interactive information with the abnormal state object identified as j; G4 is the total number of accounts (including target accounts and second accounts) that have interactive information with the object to be processed.

[0202] In this example, the information associated with the first electronic resource transfer operation (e.g., the amount transferred from the account to the object) is used as the interaction information. Specifically, the value of the electronic resources transferred in the first e.g., the amount transferred from the account to the object is used as the sub-interaction information X1, and the number of the first e.g., the number of transfers from the account to the object is used as the sub-interaction information X2. Object A0 is the object to be processed, and object A1 is the object in an abnormal state. Accounts that have interaction information with object A0 include accounts B2 to B5, and accounts that have interaction information with object A1 include accounts B1 to B4 (see [link to relevant documentation]). Figure 6 Let's take an example to illustrate:

[0203] Scenario 1: See Figure 6 In (a), assuming that the amounts transferred from accounts B1 to B4 to object A1 are 1, 2, 3 and 4 respectively, and the amounts transferred from accounts B2 to B5 to object A0 are 5, 6, 7 and 8 respectively, then K1 and K2 in formula (14) are set to 1 and 0 respectively, and W1 and W2 in formula (15) are set to 1 and 0 respectively; then the target account set corresponding to the abnormal state object can be determined as {account B2, account B3, account B4}. Based on formula (14), the sub-basic interaction reference values ​​corresponding to accounts B2 to B4 can be determined as follows. Furthermore, based on the principle of formula (15), it can be determined that The reference similarity A1 between object A0 and object A1 can be determined to be 0.312.

[0204] Scenario 2: See Figure 6In (b), assume that the amounts transferred from accounts B1 to B4 to object A1 are 1, 2, 3 and 4 respectively, the number of transfers from accounts B1 to B4 to object A1 are 1, 1, 2 and 2 respectively, the amounts transferred from accounts B2 to B5 to object A0 are 5, 6, 7 and 8 respectively, and the amounts transferred from accounts B2 to B5 to object A0 are 2, 2, 3 and 4 respectively; at this time, K1 and K2 in formula (14) are set to 1 and 1 respectively, and W1 and W2 in formula (15) are set to 1 and 1 respectively;

[0205] Then the target account set corresponding to the abnormal state object can be determined as {account B2, account B3, account B4}. Based on formula (14), the sub-basic interaction reference values ​​corresponding to accounts B2 to B4 can be determined as follows: Furthermore, based on the principle of formula (15), it can be determined that The reference similarity between object A0 and object A1 can be determined to be 0.328.

[0206] The method provided in this application embodiment identifies abnormal objects (i.e., objects whose state is abnormal and await processing objects) based on the interaction information of the target account. It can identify abnormal bookmakers who engage in abnormal fundraising in gambling, abnormal merchants or individuals who engage in credit card cash-out, and abnormal merchants who engage in order-brushing operations. It can significantly improve the accuracy of identifying abnormal state objects and improve the accuracy of identifying whether the state of an object is abnormal.

[0207] Please refer to Figure 7 Based on the same inventive concept, embodiments of this application provide an object state determination device 700, comprising:

[0208] The target account determination unit 7001 is used to determine the target account set corresponding to each abnormal state object in the abnormal state object set, wherein each target account has interaction information with the corresponding abnormal state object and the above-mentioned object to be processed;

[0209] The similarity estimation unit 7002 is used to determine the reference similarity between the above-mentioned object to be processed and each abnormal state object based on the basic interaction information and target interaction information of each target account in the obtained target account set; wherein, the above-mentioned basic interaction information includes the interaction information between the target account and the corresponding abnormal state object, and the above-mentioned target interaction information includes the interaction information between the target account and the above-mentioned object to be processed;

[0210] The object state determination unit 7003 is used to determine whether the object state of the above-mentioned object to be processed is abnormal based on the obtained reference similarity.

[0211] As one embodiment, the similarity estimation unit 7002 is specifically used to perform the following operations for each of the above-mentioned abnormal state objects:

[0212] Determine the set of target accounts corresponding to one of the above abnormal state objects;

[0213] Based at least on the basic interaction information of each target account in the determined target account set, determine the basic interaction reference values ​​for the determined target account set; and

[0214] Based at least on the target interaction information of each of the above target accounts, determine the target interaction reference value for the set of target accounts identified above.

[0215] Based on the aforementioned basic interaction reference value and the aforementioned target interaction reference value, the reference similarity between the aforementioned account to be processed and the aforementioned abnormal state object is determined.

[0216] As one embodiment, the similarity estimation unit 7002 is specifically used for:

[0217] Determine the first set of accounts corresponding to the above-mentioned abnormal state object, each first account including accounts that have interaction information with the above-mentioned abnormal state object and have no interaction information with the above-mentioned account to be processed;

[0218] Based on the basic interaction information of each target account and each first account, determine the corresponding sub-basic interaction reference value for each target account; and

[0219] Based on the sub-basic interaction reference values ​​corresponding to each of the above target accounts, determine the basic interaction reference values ​​for the set of target accounts identified above.

[0220] As one embodiment, the above-mentioned interaction information includes at least one sub-interaction information; the above-mentioned similarity estimation unit 7002 is specifically used to: determine the basic reference total value corresponding to each type of sub-interaction information in the above-mentioned at least one type of sub-interaction information; wherein, the basic reference total value corresponding to one type of sub-interaction information in the above-mentioned various types of sub-interaction information is determined based on the above-mentioned one type of sub-interaction information in the basic interaction information of each target account and the above-mentioned one type of sub-interaction information in the basic interaction information of each first account;

[0221] The similarity estimation unit 7002 is further configured to: perform the following operations for each target account among the target accounts: based on the various sub-interaction information in the basic interaction information of a target account and the basic reference total value corresponding to the various sub-interaction information, determine the influence value of the target account on the various sub-interaction information; and based on the determined influence values, determine the sub-basic interaction reference value corresponding to the target account.

[0222] As one embodiment, the similarity estimation unit 7002 is specifically used to: perform weighted summation on the obtained influence values ​​according to the first preset weights corresponding to the various sub-interaction information; and determine the sub-basic interaction reference value corresponding to the target account based on the result of the weighted summation.

[0223] As one embodiment, the similarity estimation unit 7002 is specifically used to: determine the result of the above weighted summation process as the sub-basic interaction reference value corresponding to the target account; or, determine the ratio of the result of the above weighted summation process to the sum of the weights corresponding to each of the above sub-interaction information as the sub-basic interaction reference value corresponding to the target account.

[0224] As one embodiment, the similarity estimation unit 7002 is specifically used for:

[0225] Determine the set of second accounts corresponding to the above-mentioned abnormal state object, each second account including an account that has interaction information with the above-mentioned object to be processed, but has no interaction information with the above-mentioned abnormal object;

[0226] Based on the basic interaction information of each target account, determine the first information value;

[0227] Based on the target interaction information of each target account and the target interaction information of each second account, the second information value is determined;

[0228] Based on the first information value and the second information value mentioned above, a target interaction reference value is determined for the target account set identified above.

[0229] As one embodiment, the above-mentioned interaction information includes at least one sub-interaction information; the above-mentioned similarity estimation unit 7002 is specifically used for:

[0230] Each of the above-mentioned at least one sub-interaction information is determined to have a first similarity reference value corresponding to each type of sub-interaction information; wherein, the first similarity reference value corresponding to one type of sub-interaction information among the above-mentioned various sub-interaction information is determined based on the one type of sub-interaction information in the basic interaction information of each of the above-mentioned target accounts.

[0231] Based on the determined first similarity reference values, the aforementioned first information value is determined;

[0232] Determine the second similarity reference value corresponding to each of the above-mentioned sub-interaction information; wherein, the second similarity reference value corresponding to one of the above-mentioned sub-interaction information is determined based on the above-mentioned sub-interaction information in the target interaction information of each of the above-mentioned target accounts and the above-mentioned sub-interaction information in the target interaction information of each of the above-mentioned second accounts.

[0233] The aforementioned second information value is determined based on the determined second similarity reference values.

[0234] As one embodiment, the similarity estimation unit 7002 is specifically used to: perform a second weighted summation process on each of the obtained first similarity reference values ​​based on the second preset weights corresponding to the various sub-interaction information to obtain the first information value; and perform a third weighted summation process on each of the obtained second similarity reference values ​​based on the second preset weights corresponding to the various sub-interaction information to obtain the second information value.

[0235] As one embodiment, the above-mentioned interactive information includes at least one of the following sub-interactive information: the electronic resource value transferred by the electronic resource transfer operation; and the number of times the electronic resource transfer operation is performed.

[0236] As one embodiment, the object state determination unit 7003 is specifically used to: determine the state evaluation value of the object state of the object to be processed as an abnormal state based on the obtained reference similarities; if the state evaluation value is determined to be greater than the first state evaluation value threshold, then the object state of the object to be processed is determined to be abnormal.

[0237] As one embodiment, after determining that the object state of the object to be processed is abnormal, the object state determination unit 7003 is further configured to: if the state evaluation value is determined to be greater than the second state evaluation value threshold, then determine the object to be processed as an abnormal state object, wherein the second state evaluation value threshold is not less than the first state evaluation value threshold; and add the object to be processed to the abnormal state object set.

[0238] As one example, Figure 7 The device described above can be used to implement any of the methods for determining the state of an object discussed earlier.

[0239] Based on the same inventive concept as the above-described method embodiments, this application also provides a computer device. This computer device can be used for data processing based on pushed content. In one embodiment, the computer device can be a server, such as... Figure 1 The server 120 is shown. In this embodiment, the structure of the computer device can be as follows: Figure 8As shown, it includes a memory 801, a communication module 803, and one or more processors 802.

[0240] The memory 801 is used to store computer programs executed by the processor 802. The memory 801 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0241] Memory 801 may be volatile memory, such as random-access memory (RAM); memory 801 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 801 may be any other medium capable of carrying or storing desired program code having the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 801 may be a combination of the above-described memories.

[0242] Processor 802 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 802 is used to implement the above-mentioned method for determining the state of an object when calling a computer program stored in memory 801.

[0243] The communication module 803 is used to communicate with terminal devices and other servers.

[0244] This application embodiment does not limit the specific connection medium between the memory 801, communication module 803, and processor 802 described above. This application embodiment... Figure 8 The memory 801 and the processor 802 are connected via a bus 804, and the bus 804 is in Figure 8 The connections between other components are indicated by thick lines and are for illustrative purposes only, not as limiting information. The 804 bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0245] The memory 801 stores a computer storage medium containing computer-executable instructions for implementing the account feature extraction method of this application embodiment. The processor 802 is used to execute the above-described object state determination method.

[0246] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0247] Alternatively, if the integrated unit described above is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0248] Based on the same technical concept, embodiments of this application also provide a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the method for determining the state of an object as described above.

[0249] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0250] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for determining the state of an object, characterized in that, include: Each abnormal state object in the abnormal state object set is respectively determined to correspond to a target account set, a first account set, and a second account set. Each target account has interaction information with its corresponding abnormal state object and the object to be processed. Each first account has interaction information with its corresponding abnormal state object but no interaction information with the object to be processed. Each second account has interaction information with the object to be processed but no interaction information with its corresponding abnormal state object. The interaction information is operation information associated with the electronic resource transfer operation. For each abnormal state object, based on the basic interaction information of each target account corresponding to the abnormal state object and the basic interaction information of each first account, a sub-basic interaction reference value corresponding to each target account is determined, and based on the sub-basic interaction reference values ​​corresponding to each target account, a basic interaction reference value for the set of target accounts corresponding to the abnormal state object is determined; and based on the basic interaction information and target interaction information of each target account, combined with the target interaction information of each second account corresponding to the abnormal state object, a target interaction reference value for the set of target accounts corresponding to the abnormal state object is determined; based on the basic interaction reference value and the target interaction reference value, a reference similarity between the object to be processed and the abnormal state object is obtained; wherein, the basic interaction information includes the interaction information between the target account or the first account and the corresponding abnormal state object, and the target interaction information includes the interaction information between the target account or the second account and the object to be processed; Based on the obtained reference similarities, it is determined whether the object state of the object to be processed is abnormal.

2. The method as described in claim 1, characterized in that, The interaction information includes at least one sub-interaction information; determining the sub-basic interaction reference value corresponding to each target account based on the basic interaction information of each target account corresponding to the abnormal state object and the basic interaction information of each first account includes: Determine the basic reference total value corresponding to each type of sub-interaction information in the at least one type of sub-interaction information; wherein, the basic reference total value corresponding to one type of sub-interaction information in the various types of sub-interaction information is determined based on the one type of sub-interaction information in the basic interaction information of each target account and the one type of sub-interaction information in the basic interaction information of each first account; Further, for each target account within the aforementioned target accounts, the following operations are performed: Based on the various sub-interaction information in the basic interaction information of a target account and the basic reference total value corresponding to the various sub-interaction information, the influence value of the target account on the various sub-interaction information is determined respectively. Based on the determined impact values, the sub-basic interaction reference values ​​corresponding to the target account are determined.

3. The method as described in claim 2, characterized in that, The determination of the sub-basic interaction reference value corresponding to the target account based on the determined influence values ​​includes: According to the first preset weights corresponding to the various sub-interaction information, the obtained influence values ​​are weighted and summed. Based on the result of the weighted summation process, the sub-basic interaction reference value corresponding to the target account is determined.

4. The method as described in claim 1, characterized in that, The step of determining the target interaction reference value for the set of target accounts corresponding to the abnormal state object based on the basic interaction information and target interaction information of each target account, combined with the target interaction information of each second account corresponding to the abnormal state object, includes: The first information value is determined based on the basic interaction information of each target account. The second information value is determined based on the target interaction information of each target account and the target interaction information of each second account. Based on the first information value and the second information value, a target interaction reference value is determined for the target account set corresponding to the abnormal state object.

5. The method as described in claim 4, characterized in that, The interaction information includes at least one sub-interaction information; determining the first information value based on the basic interaction information of each target account includes: Each of the at least one sub-interaction information is determined to have a first similarity reference value corresponding to each type of sub-interaction information; wherein, the first similarity reference value corresponding to one type of sub-interaction information among the various types of sub-interaction information is determined based on the type of sub-interaction information in the basic interaction information of each target account. The first information value is determined based on the determined first similarity reference values; The step of determining the second information value based on the target interaction information of each target account and the target interaction information of each second account includes: Determine a second similarity reference value corresponding to each of the various sub-interaction information; wherein, the second similarity reference value corresponding to one of the various sub-interaction information is determined based on the one of the sub-interaction information in the target interaction information of each target account and the one of the sub-interaction information in the target interaction information of each second account; The second information value is determined based on the determined second similarity reference values.

6. The method as described in claim 5, characterized in that, Determining the first information value based on the determined first similarity reference values ​​includes: Based on the second preset weights corresponding to the various sub-interaction information, the obtained first similarity reference values ​​are subjected to a second weighted summation process to obtain the first information value. Determining the second information value based on the determined second similarity reference values ​​includes: Based on the second preset weights corresponding to the various sub-interaction information, the obtained second similarity reference values ​​are subjected to a third weighted summation process to obtain the second information value.

7. The method according to any one of claims 1-6, characterized in that, The interaction information includes at least one of the following sub-interaction information: The value of electronic resources transferred during an electronic resource transfer operation; Number of operations for electronic resource transfer.

8. The method according to any one of claims 1-6, characterized in that, The step of determining whether the object state of the object to be processed is abnormal based on the obtained reference similarities includes: Based on the obtained reference similarities, the state evaluation value of the object to be processed is determined to be an abnormal state. If the state evaluation value is determined to be greater than the first state evaluation value threshold, then the object state of the object to be processed is determined to be abnormal.

9. The method as described in claim 8, characterized in that, After determining that the object state of the object to be processed is abnormal, the process further includes: If the state evaluation value is determined to be greater than the second state evaluation value threshold, then the object to be processed is determined to be an abnormal state object, and the second state evaluation value threshold is not less than the first state evaluation value threshold; and Add the object to be processed to the collection of abnormal state objects.

10. A device for determining the state of an object, characterized in that, include: The target account determination unit is used to determine the target account set, the first account set, and the second account set corresponding to each abnormal state object in the abnormal state object set. Each target account has interaction information with the corresponding abnormal state object and the object to be processed. Each first account has interaction information with the corresponding abnormal state object but no interaction information with the object to be processed. Each second account has interaction information with the object to be processed but no interaction information with the corresponding abnormal state object. The interaction information is operation information associated with the electronic resource transfer operation. A similarity estimation unit is configured to, for each abnormal state object, determine a sub-basic interaction reference value corresponding to each target account based on the basic interaction information of each target account corresponding to the abnormal state object and the basic interaction information of each first account, and determine a basic interaction reference value for the set of target accounts corresponding to the abnormal state object based on the sub-basic interaction reference values ​​of each target account; and determine a target interaction reference value for the set of target accounts corresponding to the abnormal state object based on the basic interaction information and target interaction information of each target account, combined with the target interaction information of each second account corresponding to the abnormal state object; and obtain a reference similarity between the object to be processed and the abnormal state object based on the basic interaction reference value and the target interaction reference value; wherein, the basic interaction information includes the interaction information between the target account or the first account and the corresponding abnormal state object, and the target interaction information includes the interaction information between the target account or the second account and the object to be processed; The object state determination unit is used to determine whether the object state of the object to be processed is abnormal based on the obtained reference similarities.

11. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, wherein a processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions to cause the computer device to perform the method of any one of claims 1-9.

12. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method of any one of claims 1-9.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-9.

Images