CN115147116A

CN115147116A - Object state determination method, device, equipment and readable storage medium

Info

Publication number: CN115147116A
Application number: CN202110334456.1A
Authority: CN
Inventors: 吴杰
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-03-29
Filing date: 2021-03-29
Publication date: 2022-10-04

Abstract

The application provides a method, a device and equipment for determining the state of an object and a readable storage medium, which relate to the technical field of artificial intelligence and are used for improving the accuracy of determining whether the state of the object is abnormal or not. The method comprises the following steps: determining a target account set corresponding to each abnormal state object; each target account has interaction information with the corresponding abnormal state object and the object to be processed; determining reference similarity of the object to be processed and each abnormal state object based on the basic interaction information and the target interaction information of each target account in each target account set; the basic interaction information comprises interaction information between a target account and a corresponding abnormal state object, and the target interaction information comprises interaction information between the target account and an object to be processed; and determining whether the object state of the object to be processed is abnormal or not based on the reference similarity. The method is used for analyzing based on the interactive information of the target account, and can improve the accuracy of determining whether the object state of the object is abnormal or not.

Description

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

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a device, and a readable storage medium for determining an object state.

Background

In the process of checking an object with an abnormal state in a target service, checking is often performed based on object attribute features of the object to be processed, and for example, in the process of checking an object with an abnormal state related to transfer of electronic resources, whether the state of the object to be processed is abnormal is often determined based on electronic resources held by the object to be processed, account attribute features of an account performing interaction, an area interacting with the account, and holding mode object attribute features of the electronic resources.

Disclosure of Invention

The embodiment of the application provides a method, a device and equipment for determining the state of an object and a readable storage medium, which are used for improving the accuracy of determining whether the state of the object is abnormal or not.

In a first aspect of the present application, a method for determining an object state is provided, including:

respectively determining a 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;

respectively determining the reference similarity of the object to be processed and each abnormal state object based on the obtained basic interaction information and target interaction information of each target account in each target account set; the basic interaction information comprises interaction information between a target account and a corresponding abnormal state object, and the target interaction information comprises 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 or not based on the obtained reference similarity.

In a possible implementation manner, the determining, according to a result of the weighted summation processing, a sub-base interaction reference value corresponding to the one target account includes:

determining the result of the weighted summation processing as a sub-basic interaction reference value corresponding to the target account; or determining a ratio of the result of the weighted sum processing to the sum of weights corresponding to the determined sub-interaction information as a sub-basic interaction reference value corresponding to the target account.

In a second aspect of the present application, there is provided an apparatus for determining a state of an object, including:

the target account determining unit is used for respectively determining a 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;

the similarity estimation unit is used for respectively determining the reference similarity of the object to be processed and each abnormal state object based on the obtained basic interaction information and the target interaction information of each target account in each target account set; the basic interaction information comprises interaction information between a target account and a corresponding abnormal state object, and the target interaction information comprises interaction information between the target account and the object to be processed;

and the object state determining unit is used for determining whether the object state of the object to be processed is abnormal or not based on the obtained reference similarity.

In a possible implementation manner, the similarity estimation unit is specifically configured to: the following operations are respectively carried out for each abnormal state object:

determining a target account set corresponding to one abnormal state object in the abnormal state objects;

determining a basic interaction reference value aiming at the determined target account set at least based on basic interaction information of each target account in the determined target account set; and

determining a target interaction reference value for the determined target account set at least based on the target interaction information of each target account;

and determining the reference similarity of the account to be processed and the abnormal state object based on the basic mutual reference value and the target mutual reference value.

In a possible implementation manner, the similarity estimation unit is specifically configured to:

determining a first account set corresponding to the abnormal state object, wherein each first account comprises an account which has interaction information with the abnormal state object and does not have interaction information with the account to be processed;

determining a sub-basic interaction reference value corresponding to each target account according to the basic interaction information of each target account and the basic interaction information of each first account; and

and determining a basic interactive reference value aiming at the determined target account set according to the respective corresponding basic interactive reference value of each target account.

In one possible implementation, the interaction information includes at least one piece of sub-interaction information; the similarity estimation unit is specifically configured to:

determining a basic reference total value corresponding to each sub-interaction information in the at least one piece of sub-interaction information; the basic reference total value corresponding to one piece of sub-interaction information in the various pieces of sub-interaction information is determined based on the one piece of sub-interaction information in the basic interaction information of the target accounts and the one piece of sub-interaction information in the basic interaction information of the first accounts;

the similarity estimation unit is further configured to: for each target account in the target accounts, the following operations are respectively executed:

respectively determining the influence value of one target account on various sub-interaction information based on various sub-interaction information in the basic interaction information of one target account in the target accounts and the basic reference total value corresponding to the various sub-interaction information;

and determining a sub-basic interaction reference value corresponding to the target account based on the determined influence values.

In a possible implementation manner, the similarity estimation unit is specifically configured to: according to the first preset weight corresponding to each sub-interactive information, carrying out weighted summation processing on each obtained influence value; and determining a sub-basic interaction reference value corresponding to the target account according to the result of the weighted summation.

determining the result of the weighted summation processing as a sub-basic interaction reference value corresponding to the target account; or determining the ratio of the result of the weighted sum processing to the sum of the weights corresponding to the determined sub-interactive information as the sub-basic interactive reference value corresponding to the target account.

determining a second account set corresponding to the abnormal state object, wherein each second account comprises an account which has interaction information with the object to be processed and does not have interaction information with the abnormal object;

determining a first information value according to the basic interaction information of each target account;

determining a second information value according to the target interaction information of each target account and the target interaction information of each second account;

determining a target cross-reference value for the determined set of target accounts based on the first information value and the second information value.

respectively determining first similar reference values corresponding to various sub-interactive information in the at least one piece of sub-interactive information; a first similar reference value corresponding to one piece of sub-interaction information in the various pieces of sub-interaction information is determined based on the one piece of sub-interaction information in the basic interaction information of the various target accounts;

determining the first information value based on the determined respective first similar reference values;

determining second similar reference values corresponding to the various sub-interaction information; the second similar reference value corresponding to one piece of sub-interaction information in the various pieces of sub-interaction information is determined based on the one piece of sub-interaction information in the target interaction information of each target account and the one piece of sub-interaction information in the target interaction information of each second account;

determining the second information values based on the determined respective second similar reference values.

performing second weighted summation processing on each obtained first similar reference value based on a second preset weight corresponding to each piece of sub-interaction information to obtain a first information value;

and performing third weighted summation processing on each obtained second similar reference value based on second preset weight corresponding to each piece of sub-interaction information to obtain the second information value.

In a possible implementation manner, the interaction information includes at least one of the following sub-interaction information:

an electronic resource value transferred by the electronic resource transfer operation;

the number of operations of the electronic resource transfer operation.

In a possible implementation manner, the object state determining unit is specifically configured to: determining a state evaluation value that an object state of the object to be processed is an abnormal state based on the obtained respective reference similarities; determining that the object state of the object to be processed is abnormal if it is determined that the state evaluation value is greater than a first state evaluation value threshold.

In a possible implementation manner, 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 larger than a second state evaluation value threshold value, determining the object to be processed as an abnormal state object, wherein the second state evaluation value threshold value is not smaller than the first state evaluation value threshold value; and adding the object to be processed into the abnormal state object set.

In a third aspect of the present application, a computer device is provided, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method of the first aspect.

In a fourth aspect of the present application, a computer program product is provided that includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the first aspect described above.

In a fifth aspect of the present application, there is provided a computer readable storage medium having stored thereon computer instructions which, when run on a computer, cause the computer to perform the method according to the first aspect.

Due to the adoption of the technical scheme, the embodiment of the application has at least the following technical effects:

in the embodiment of the application, based on the target accounts with the interaction information between each abnormal state object and the object to be processed, the similarity (namely, the reference similarity) between the object to be processed and each abnormal state object is evaluated according to the interaction information between the target accounts and the object to be processed, and then whether the object state of the object to be processed is abnormal or not is determined according to the similarity between the object to be processed and each abnormal state object, so that the object with the abnormal object state in the object set to be processed can be mined out based on the interaction information between the account and the abnormal state object, and the accuracy of identifying whether the object state is abnormal or not is improved.

Drawings

Fig. 1 is a schematic diagram of an application scenario for determining an object state of an object according to an embodiment of the present application;

fig. 2 is a schematic view of a process of handling an abnormal object according to an embodiment of the present disclosure;

fig. 3 is a flowchart of a method for determining an object status according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a target account set provided by an embodiment of the present application;

FIG. 5 is a diagram showing the identification result of determining whether telecom fraud exists on an object to be processed according to an embodiment of the present application;

FIG. 6 is a schematic diagram illustrating interaction information between an object and an account according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an apparatus for determining an object state according to an embodiment of the present disclosure;

fig. 8 is a block diagram of a computer device according to an embodiment of the present disclosure.

Detailed Description

In order to better understand the technical solutions provided by the embodiments of the present application, the following detailed description is made with reference to the drawings and specific embodiments of the specification; in order to facilitate those skilled in the art to better understand the technical solutions of the present application, some concepts related to the present application will be described below.

1) Object, abnormal state object, object to be processed

The object in this embodiment of the present application may be, but is not limited to, an identification of an object having some operation rights in the internet, where some operations may include, but are not limited to, an electronic resource transfer operation, that is, the object in this embodiment of the present application may include, but is not limited to, an object capable of performing an electronic resource transfer operation, where the object may include, but is not limited to, a business, a government department, a social public institution, or a personal account.

An abnormal state object may include, but is not limited to, an object whose state is an abnormal state; the object to be processed includes an object whose state needs to be identified as abnormal, wherein the contents of the object state and the abnormal state will be described in detail below.

2) Account, target account, first account and second account

An account is generally an identification representation of a target in the internet, which target may be, but is not limited to, an individual, a merchant, a social group, a government department, or the like;

the target account in the embodiment of the application refers to an account which has interactive information with an abnormal state object and has interactive information with an object to be processed; the first account and the second account are for one abnormal state object in the process of determining the reference similarity of the object to be processed and the one abnormal state object, namely for the one abnormal state object: the first account is an account which has interaction information with the abnormal state object and has no interaction information with the object to be processed; the second account is an account which has interaction information with the object to be processed and has no interaction information with the abnormal state object;

here, to facilitate understanding, a specific example is given, if the object A0 is a to-be-processed object, the accounts having the interaction information with the object A0 include accounts B1 to B5, the object A1 is an abnormal state object, and the accounts having the interaction information with the object A1 include accounts B3 to B6, then for the 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.

The network fraud in the embodiment of the application mainly relates to the evaluation of the abnormal degree of the object state of the object in the target business related to the transfer of the electronic resource and the excavation of the object with the abnormal object state in the target business.

The embodiment of the application relates to Artificial Intelligence (AI) and Machine Learning technology, which is designed based on a computer vision technology and Machine Learning (ML) in the AI; artificial intelligence is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence.

Artificial intelligence, namely, the design principle and the realization method of various intelligent machines are researched, so that the machine has the functions of perception, reasoning and decision making; it mainly includes computer vision technique, natural language processing technique, machine learning or deep learning and so on. With the research and progress of artificial intelligence technology, artificial intelligence is researched and applied in a plurality of fields, such as common smart homes, smart customer service, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, robots, smart medical treatment and the like.

Machine learning is a multi-field cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. Specially researching how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer; machine learning is the core of artificial intelligence, is the fundamental approach to make computers have intelligence, and is applied in various fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and the like.

In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The following explains the concept of the present application.

In the process of checking an object with abnormal state in a target service (such as mobile payment or other services related to the transfer of electronic resources), checking is often performed based on attribute characteristics of the object to be processed, and in the process of checking an object with abnormal state for an object to be processed related to the transaction of electronic resources, whether the state of the object to be processed is abnormal is often determined based on an electronic resource value held by the object to be processed, account attribute characteristics of an account performing electronic resource operation with the object to be processed, a transaction area of the electronic resources, and attribute characteristics of a fund mode waiting object of the electronic resources.

In view of this, the inventors have devised a method of determining the state of an object, for improving the accuracy of determining whether the state of the object is abnormal; in the embodiment of the present application, an abnormal state object set is first obtained, where the abnormal state object set includes an abnormal state object whose object state is marked as an abnormal state, and the abnormal state object is used as a black sample seed in the embodiment of the present application, information of a common interaction account between an object to be processed and each abnormal state object is used to estimate reference similarities of the object to be processed and each abnormal state object, and further, based on the estimated reference similarities, it is determined whether the object state of the object to be processed is abnormal, where the common interaction account includes an account having interaction information with a corresponding abnormal state object and having interaction information with the object to be processed, and in the following content of the embodiment of the present application, the common interaction account is described as a target account.

Further, in order to further improve the accuracy of determining whether the object state of the object to be processed is abnormal, in the embodiment of the present application, a state evaluation value, which determines that the object state of the object to be processed is an abnormal state, may be determined based on the obtained respective reference similarities, and further, whether the object state of the object to be processed is abnormal may be determined based on the state evaluation value.

In order to more clearly understand the design idea of the present application, an application scenario in the embodiment of the present application is described as an example below; referring to fig. 1, an application scenario for determining an object state of an object is provided, where the application scenario may include a terminal device 110 and a server 120; communication between terminal device 110 and server 120 may be via a network, wherein:

a target application program may be installed on the terminal device 110 (such as but not limited to include 110-1 or 110-2 illustrated in the figure), where the target application program supports a mobile payment function, and the target application program may include but is not limited to include at least one of a payment type application program, a social type application program, a multimedia type application program, and an assistance tool type application program, which is not limited in this embodiment of the present application; in the embodiment of the application, each object (including each abnormal state object and each object to be processed) and each account can log in the target application program and execute corresponding behaviors or operations; for example, after an object logs in a target application program, interaction with an account can be triggered, and various messages can be sent to other objects except the object; after one account logs in the target application program, interaction with an object can be triggered, and various messages and the like can be sent to other accounts except the account.

Terminal device 110 may determine interaction information between the object and the account based on the interaction behavior between the object and the account, and may send the obtained interaction information to server 120 (such as may include, but is not limited to, 120-1, 120-2, or 120-3 illustrated in the figure); the terminal device may also transmit the interactive behavior to the server 120, and the server 120 obtains behavior information associated with the interactive behavior.

As an embodiment, the method for determining an object state provided in the embodiment of the present application may be applied to the terminal device 110, and may also be applied to the server 120;

when the method for determining the object state provided by the embodiment of the present application is applied to the terminal device 110, the terminal device 110 may obtain an abnormal state object set, and respectively determine a target account set corresponding to each abnormal state object in the abnormal state object set; respectively determining the reference similarity of the object to be processed and each abnormal state object based on the obtained basic interaction information and target interaction information of each target account in each target account set, and further determining whether the object state of the object to be processed is abnormal based on the obtained reference similarities; the basic interaction information comprises interaction information between a target account and a corresponding abnormal state object, and the target interaction information comprises interaction information between the target account and the object to be processed;

when the method for determining an object state provided by the embodiment of the present application is applied to the server 120, the server 120 may obtain the abnormal state object set, and respectively determine a target account set corresponding to each abnormal state object in the abnormal state object set; and respectively determining the reference similarity of the object to be processed and each abnormal state object based on the obtained basic interaction information and the target interaction information of each target account in each target account set, and further determining whether the object state of the object to be processed is abnormal based on the obtained reference similarities.

The manner of acquiring the abnormal state object set by the terminal device 110 and the server 120 is not limited, and those skilled in the art may set the abnormal state object set according to actual requirements.

The terminal device 110 in the embodiments of the present application may be a mobile terminal, a fixed terminal, or a portable terminal, such as a mobile handset, a station, a unit, a device, a multimedia computer, a multimedia tablet, an internet node, a communicator, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a Personal Communication System (PCS) device, a personal navigation device, a Personal Digital Assistant (PDA), an audio/video player, a digital camera or camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination thereof, including accessories and peripherals of these devices, or any combination thereof.

The server 120 in this embodiment of the application may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a plurality of cloud servers (such as but not limited to a server 120-1, a server 120-2, or a server 120-3 illustrated in the figure) that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDNs, and big data and artificial intelligence platforms in a cloud service technology; the functions of the server 120 may be implemented by one or more cloud servers, one or more cloud server clusters, and the like.

In a possible application scenario, in the embodiment of the application, a cloud storage technology may be adopted to store the abnormal state object set and the interaction information of the account having an interaction behavior with each abnormal state object; the distributed Cloud Storage system (hereinafter referred to as a Storage system) refers to a Storage system which integrates a large number of Storage devices (Storage devices are also referred to as Storage nodes) of various types in a network through application software or application interfaces to cooperatively work through functions such as cluster application, grid technology and distributed Storage file system, and provides data Storage and service access functions to the outside.

In a possible application scenario, in order to reduce communication delay, the server 120 may be deployed in each region, or in order to balance load, different servers 120 may respectively serve the regions corresponding to each terminal device 110, store the abnormal state object set and the interaction information of the account having an interaction behavior with each abnormal state object by using a blockchain technique, and implement the method for determining the object state designed in the embodiment of the present application. The plurality of servers 120 enable sharing of data by a blockchain, and the plurality of servers 120 correspond to a data sharing system formed by the plurality of servers 120. For example, terminal device 110 is located at location a and communicatively coupled to server 120, and terminal device 110 is located at location b and communicatively coupled to other servers 120. The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer.

Each server 120 in the data sharing system has a node identifier corresponding to the server 120, and each server 120 in the data sharing system may store node identifiers of other servers 120 in the data sharing system, so that the generated block is broadcast to other servers 120 in the data sharing system according to the node identifiers of other servers 120.

Each server 120 may maintain a node identifier list as shown in the following table, and store the name of the server 120 and the node identifier in the node identifier list. The node identifier may be an Internet Protocol (IP) address or any other information that can be used to identify the node, and table 1 only illustrates the IP address as an example.

TABLE 1

Server name	Node identification
		Node 1	119.115.151.174
Node 2	118.116.189.145
		…	…
Node N	119.124.789.258

The following describes a method for determining the object state in the embodiment of the present application in detail. It should be noted that the above application scenarios are only presented to facilitate understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect.

First, the object state, the abnormal state object, and the abnormal state object set related in the embodiment of the present application are further explained:

as an embodiment, the object state in the embodiment of the present application may refer to, but is not limited to, a state of an object in the internet, and the object state in the embodiment of the present application may include, but is not limited to, at least one of a normal state and an abnormal state, where the normal state may represent that a behavior of the object in the internet meets a corresponding behavior specification; the abnormal state can represent that the behavior of the object in the internet does not conform to the corresponding behavior specification.

As an embodiment, an object state determining method provided by the embodiment of the present application is used for determining whether an object state of an object to be processed in the internet is abnormal, where an abnormal state object may include an object whose object state is an abnormal state.

As an embodiment, the object state determining method provided in the embodiment of the present application may be further configured to determine whether an object state of an object to be processed in a target service is abnormal, and in this case, in order to improve accuracy of determining whether the object state of the object is abnormal, the object state of the object in the embodiment of the present application may also be a state of the object in the target service; further, the abnormal object state may include an object whose object state in the target service is an abnormal state.

The target service may include, but is not limited to, transactions to be processed in mobile payment, and the target service may include, but is not limited to, transaction services, friend-making services, services related to work information, rebate services (i.e., services related to rebate), services related to financial credit, gambling, betting, money laundering and the like.

As an embodiment, the object state determining method provided in the embodiment of the present application is configured to determine whether an object state of an object to be processed in a target service is abnormal, where a normal state in the object state may be, but is not limited to, understanding that a behavior of the object in the target service satisfies behavior contract information associated with the target service, and an abnormal state may be, but is not limited to, understanding that a behavior of the object in the target service does not satisfy the behavior contract information associated with the target service; for example, if an object has a fraudulent behavior in a target service, it may be considered that the service behavior of the object in the target service does not satisfy behavior engagement information associated with the target service; when an object has an abnormal resource aggregation behavior in a target service, the object can also be considered not to meet behavior determination information associated with the target service;

the above abnormal resource aggregation behavior may include, but is not limited to, behavior of aggregating a large amount of electronic resources in a short time, such as the money laundering behavior described above in general; for the sake of understanding, it is exemplified here that the network gambling service is taken as an example of a target service, then in the set of abnormal state objects associated with the network gambling service, the abnormal state object may be an abnormal behind-the-scenes dealer, which may be a dealer using a round-robin method, that is, a large number of payouts for various platforms are controlled and operated through various illegal channels, and when an account transfers electronic resources (for example, purchases chips) to the abnormal behind-the-scenes dealer for many times, the APP of the abnormal behind-the-scenes dealer randomly allocates transactions to different payouts, thereby forging the account to have data artifacts of consumption payments by various virtual merchants, in an attempt to avoid the conventional wind-based recognition strategy. In abstract terms, each account of the abnormal background dealer transfers electronic resources to different virtual merchants through different cash codes, and finally the abnormal background dealer receives the transferred electronic resources from the accounts of different virtual merchants (e.g., gambling accounts).

Please refer to fig. 2, which provides a schematic diagram of the dealer operating at the back of the abnormal background; the dealer behind the abnormal scenes controls a plurality of virtual commercial businesses C1, C2, \8230;, cn (n is a positive integer) and the associated cash register codes D1, D2, \8230; \, dn respectively. These virtual merchants may be disguised as merchants of various normal businesses, such as breakfast shops, snack bars, bookstores, clothing stores, coffee shops, and the like; accounts B1, B2, \8230;, bm (m is a positive integer) want to, for example, purchase chips and/or pay directly to participate in network gambling. The account B1 may participate in network gambling at the virtual merchant C1 and transfer of electronic resources (e.g., at least one interactive action of purchasing chips or directly paying to participate in gambling, etc.) through the payee code D1 of the virtual merchant C1; the accounts B2 and B3 can participate in network gambling at the virtual merchant C2, and electronic resource transfer is carried out through the payment receiving code D2 of the virtual merchant C2; the account Bm and the like may participate in network gambling at the virtual merchant Cn, and transfer of electronic resources and the like is performed through the payment code Dn of the virtual merchant Cn.

As an embodiment, the abnormal state object set in the embodiment of the present application may be a set composed of at least one abnormal state object.

As an embodiment, the object state determining method provided in the embodiment of the present application may be further configured to determine, for different target services, whether an object state of the object to be processed in different target services is abnormal, and in this case, in order to improve accuracy of determining whether the object state of the object to be processed in different target services is abnormal, in the embodiment of the present application, but not limited to setting, for different target services, abnormal state object sets associated with the target services respectively, where the abnormal state object set associated with the target services includes an abnormal state object whose object state is an abnormal state in the target services.

Next, the interactive information and interactive operation related in the embodiment of the present application will be described: in the embodiment of the present application, the interaction information between the account and the object may be, but is not limited to, information (or data) triggered or associated by an interaction behavior between the account and the object; wherein a general case of behavior may refer to operations; the interactive operation involved in the embodiment of the present application may include, but is not limited to, an electronic resource transfer operation, a multimedia information transfer operation (video, audio, or graphics, etc.), or a game resource, etc.;

as an example, the interactive behavior referred to in the embodiments of the present application may include a first operation triggered by the account and performed by the account, such as, but not limited to, an operation that includes the account actively transferring the electronic resource to the object; the interactive operation may also include a second operation triggered by the object and executed by the account, for example, the second operation may be an operation in which the object displays a payment code or other payment information to the account, and the account transfers the electronic resource to the object based on the payment code or other first payment information; the interaction information may also include a third operation triggered by the object and performed by the object, such as the third operation may be an operation in which the object actively transfers the electronic resource to the account.

The electronic resource transfer operation in the embodiment of the application may include an operation of transferring electronic resources, the electronic resource transfer operation may also be referred to as mobile payment, and the mobile payment represents a behavior of an account performing a payment operation through a mobile network; the electronic resource related in the embodiment of the application can be at least one of fund and information resource; the funds may include at least french currency, electronic money, and the like; the legal currency is a currency which is given to the legal currency for forced circulation, such as RMB, USD and the like; by electronic money is meant money stored in electronic form in an electronic wallet held by an account (such as a wallet in mobile payment type applications, etc.), which may include, but is not limited to, electronic tickets, digital money (an unregulated, digitized currency, game pieces, etc.); the information resource can be, but is not limited to, a game resource (such as game equipment and the like), a multimedia resource (such as video, audio and the like), and an electronic ticket (such as an electronic group purchase ticket, an electronic discount ticket and the like).

The above interaction information may include, but is not limited to, trigger time of the interaction behavior, behavior description information, or operation times of the interaction behavior; when the interaction behavior includes an electronic resource transfer operation, the interaction information in this embodiment may include, but is not limited to, at least one piece of sub-interaction information in an electronic resource value transferred by the electronic resource transfer operation and an operation frequency of the electronic resource transfer operation.

To facilitate understanding, a specific example of an interactive behavior and interactive information is given here, the interactive behavior may be a first electronic resource transfer operation in which an account actively transfers an electronic resource to an object, and the interactive information may include at least one of an electronic resource value associated with the account for the first electronic resource transfer operation of the object and a number of operations of the account for the first electronic resource transfer operation of the object, as may be referred to in table 2 below.

Table 2:

as an embodiment, when the interaction behavior is a second electronic resource transfer operation of transferring the electronic resource to an account by an object, the interaction information may include at least one of an electronic resource value associated with the second electronic resource transfer operation of the account by the object and the operation number of the second electronic resource transfer operation of the account by the object, as may refer to the contents in table 3 below.

Table 3:

based on the application scenario in fig. 1, a method for determining an object state in the embodiment of the present application is described below by way of example, please refer to fig. 3, which is a flowchart illustrating a method for determining an object state designed in the embodiment of the present application, and the method can be applied to, but is not limited to, the terminal device 110 or the server 120, and specifically includes the following steps:

step S301, respectively determining a 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.

As an embodiment, in step S301, an abnormal state object set may be determined first, where a specific manner of determining the abnormal state object set is not limited, and a person skilled in the art may set according to actual requirements, for example, a set including an abnormal state object uploaded by an auditor may be determined as the abnormal state object set, or an abnormal state object set updated in real time may be obtained directly from a block chain or a cloud service.

As an embodiment, when the object state determining method provided in this embodiment of the present application is used to determine whether an object state of an object to be processed in a target service is abnormal, the abnormal state object set in step S301 may be an abnormal state object set associated with the target service, so as to improve accuracy of identifying an object with an abnormal object state in the target service.

As an embodiment, for each abnormal state object, in the process of determining whether the object state of the object to be processed is abnormal, each abnormal state object corresponds to one target account set, and for different abnormal state objects, the number of target accounts in the corresponding target account set is determined according to an actual situation, that is, the number of target accounts in one target account set may be 0, 1, 2, or more than 2, and so on; to illustrate by taking a specific example, please refer to fig. 4, if the object A0 is a to-be-processed object, the object A1, the object A2, and the object A3 are all abnormal state objects, the account having the interaction information with the object A0 includes accounts B1 to B5, the account having the interaction information with the object A1 includes accounts B3 to B6, the account having the interaction information with the object A2 includes accounts B5 to B7, and the account having the interaction information with the object A3 includes accounts B6 to B8; then the target account set 1 corresponding to the object A1 is { account B3, account B4, account B5}, the target account set 2 corresponding to the object A2 is { account B5}, and the target account set 3 corresponding to the object A3 is empty; for the abnormal state object corresponding to the empty target account set, the following process of step S302 may be directly skipped.

Step S302, respectively determining the reference similarity of the object to be processed and each abnormal state object based on the obtained basic interaction information and target interaction information of each target account in each target account set; the basic interaction information comprises interaction information between a target account and a corresponding abnormal state object, and the target interaction information comprises interaction information between the target account and the object to be processed.

As an embodiment, the operation of step S302 may be executed for a target account set that is not empty, and for an empty target account set, the reference similarity of the object to be processed and the abnormal-state object corresponding to the empty target account set may be directly set as a preset reference similarity, so as to improve the efficiency of determining the reference similarities of the object to be processed and each abnormal-state object; in order to improve the efficiency of performing subsequent processing based on the determined reference similarity, the preset reference similarity may be set to 0 in this embodiment of the application, but is not limited thereto.

As an example, in step S302, the following operations may be performed for each abnormal state object: determining a target account set corresponding to one abnormal state object in the abnormal state objects; determining a basic interaction reference value aiming at the determined target account set at least based on the basic interaction information of each target account in the determined target account set; determining a target interaction reference value aiming at the determined target account set at least based on the target interaction information of each target account; determining the reference similarity between the account to be processed and the abnormal state object based on the basic cross reference value and the target cross reference value; the specific method for determining the reference similarity between the account to be processed and the above-mentioned one abnormal state object will be further described below.

Step S303, determining whether the object state of the object to be processed is abnormal based on the obtained respective reference similarities.

As an embodiment, in order to improve the accuracy of determining whether the object state of the object to be processed is abnormal, in the embodiment of the present application, it is possible, but not limited to, determining a state evaluation value that the object state of the object to be processed is an abnormal state based on the obtained respective reference similarities; determining whether the object state of the object to be processed is abnormal or not based on the state evaluation value; if the state evaluation value is determined to be larger than a first state evaluation value threshold value, determining that the object state of the object to be processed is abnormal, otherwise, determining that the object state of the object to be processed is normal; the threshold of the first state evaluation value is not limited, and may be set by a person skilled in the art according to actual requirements.

As an embodiment, in order to improve the accuracy of determining whether the object state of the object to be processed is abnormal, in the embodiment of the present application, the sum of the obtained reference similarities may be determined as the state evaluation value corresponding to the object to be processed based on the principle of the following formula (1 a), or the obtained reference similarities and the abnormality weights corresponding to the abnormal object states may be subjected to weighted summation processing based on the principle of the following formula (1 b), and the obtained result is determined as the state evaluation value corresponding to the object to be processed; the abnormal weight may represent a degree that a target state of the abnormal target state is an abnormal state, such as but not limited to determining an abnormal level of the abnormal target state as an abnormal weight corresponding to the abnormal target state; those skilled in the art may also process the obtained reference similarities in other ways to obtain a state evaluation value corresponding to the object to be processed.

In the formula (1 a) and the formula (1 b), U is a state evaluation value corresponding to the object to be processed; j is the identification of the abnormal state object; j is the total number of abnormal state objects in the set of abnormal state objects; t is _i Is the anomaly weight corresponding to the anomaly status object identified as j.

As an embodiment, in order to further improve the accuracy of identifying an object whose object state is an abnormal state, in step S303 in this embodiment of the application, it may further be determined whether the object to be processed can be used as an abnormal state object for estimating whether the object state of another object is abnormal; specifically, after determining that the object state of the object to be processed is abnormal in the step S303, comparing the state evaluation value corresponding to the object to be processed with the second state evaluation value threshold, and if determining that the state evaluation value is greater than the second state evaluation value threshold, determining the object to be processed as an abnormal object, adding the object to be processed to an abnormal object set, and participating in the determination process of the object state after the determination; the second state evaluation value threshold is not less than the first state evaluation value threshold, and the specific value of the second state evaluation value threshold is not limited, and may be set by a person skilled in the art according to business experience or other influencing factors.

As an embodiment, after determining the state evaluation value corresponding to the object to be processed in step S303, it may also be determined whether there is target fraud in the object to be processed based on the state evaluation value as an evaluation feature and based on the evaluation feature and other evaluation features corresponding to the object to be processed; the above target fraud is not limited, and those skilled in the art can set the fraud according to actual requirements, such as but not limited to friend-making fraud, rebate fraud, telecom fraud or part-time fraud; for easy understanding, please refer to fig. 5, which shows a recognition result display diagram for determining whether the object to be processed has telecommunication fraud, wherein 16-dimensional evaluation features (i.e. detection risk points in the diagram) of the object to be processed are analyzed in the recognition process, and the recognition result of the object to be processed is shown in a recognition result display area 501, and the behavior of the object to be processed having telecommunication fraud can be seen from the diagram.

The following of the embodiment of the present application describes in detail a specific method for determining the reference similarity between the account to be processed and each abnormal state object in the above step S302, and only one abnormal state object in each abnormal state object is taken as an example to describe the reference similarity between the account to be processed and the one abnormal state object.

As an embodiment, in the embodiment of the present application, the sum of the basic cross reference value and the target cross reference value may be determined as a reference similarity between the account to be processed and the one abnormal state object based on, but not limited to, the following formula (2 a); the product of the basic cross reference value and the target cross reference value can also be determined as the reference similarity of the account to be processed and the abnormal state object based on the following formula (2 b).

A _j ＝R _j +COM _j Formula (2 a)

A _j ＝R _j ×COM _j Formula (2 b)

Wherein, in formula (2 a) and formula (2 b), j is the identification of the abnormal state object, A _j Is the reference similarity of the object to be processed and the abnormal state object identified as j, R _j Is the base interaction reference value, COM, of the set of target accounts corresponding to the abnormal state object identified as j _j And j is the target interaction reference value of the target account set corresponding to the abnormal state object identified as j.

As an embodiment, to further improve the accuracy of the determined basic cross reference value, in step S302, the basic cross reference value for the determined target account set may be determined, but is not limited to be determined, by the following means: determining a first account set corresponding to the abnormal state object; determining a sub-basic interaction reference value corresponding to each target account according to the basic interaction information of each target account and the basic interaction information of each first account; determining a basic interactive reference value aiming at the determined target account set according to the corresponding basic interactive reference value of each target account; each first account in the first account set comprises an account which has interactive information with the abnormal state object and has no interactive information with the account to be processed.

Specifically, in the process of determining the basic mutual reference value for the determined target account set according to the sub-basic mutual reference value corresponding to each target account, the sum of the sub-basic mutual reference values corresponding to each target account may be determined as the basic mutual reference value for the determined target account set based on the principle of the following formula (3 a); the average value of the base mutual reference values corresponding to the respective target accounts may be determined as the base mutual reference value for the determined target account set based on the principle of the following formula (3 b).

Wherein, in the above formula (3 a) and formula (3 b), j is the identifier of the abnormal state object, R _j Is the basic interaction reference value of the target account set corresponding to the abnormal state object identified as j; n is the mark of the target account in the target account set corresponding to the abnormal state object marked as j; n is the number of target accounts in the target account set corresponding to the abnormal state object with the mark j; r _n And the sub-base interaction reference value is the sub-base 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.

As an embodiment, the interaction information in the embodiment of the present application may include at least one piece of sub-interaction information, that is, the interaction information may include one piece of sub-interaction information, and may also include multiple pieces of sub-interaction information, and in the process of determining the sub-base interaction reference value corresponding to each target account according to the base interaction information of each target account and the base interaction information of each first account in step S302, the base reference total value corresponding to each piece of sub-interaction information in the at least one piece of sub-interaction information may be determined; further, for each of the target accounts, the following operations are respectively executed: based on various sub-interaction information in the basic interaction information of one target account in the target accounts and the basic reference total value corresponding to the various sub-interaction information, respectively determining the influence value of the target account on the various sub-interaction information, and based on the determined influence values, determining a sub-basic interaction reference value corresponding to the target account.

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

Wherein, in the above formula (4 a) and formula (4 b), i is an identifier of one piece of sub-interaction information in the above various pieces of sub-interaction information; r _{Total _ i} Is a basic reference total value corresponding to a piece of sub-interactive information marked as i; e is the account identification of the target account and the account in the first account; e is the total number of accounts in the target account and the first account; iATM _e The value of the seed interactive information marked as i in the basic interactive information of the account marked as e.

As an embodiment, when determining a base reference total value corresponding to a piece of sub-interaction information based on the above formula (4 a), the influence value of the above one target account on the above various pieces of sub-interaction information may be, but is not limited to, determined based on the principle of the following formula (5 a); when the basic reference total value corresponding to one piece of sub-interaction information is determined based on the above formula (4 b), the influence value of the above one target account on the above various pieces of sub-interaction information may be determined based on, but not limited to, the principle of the following formula (5 b).

Y_i＝|R _{Total _ i} -iATM _n Equation (5 b)

Wherein, in the formula (5 a) and the formula (5 b), i is an identifier of one piece of sub-interaction information in the various pieces of sub-interaction information; r _{Total _ i} Is a basic reference total value corresponding to a piece of sub-interactive information marked as i; n is the identification of the target account; iATM _n The value of a piece of sub-interactive information marked as i in the basic interactive information of the target account marked as n; y _ i is the impact value of the target account identified as n on one piece of sub-interaction information identified as i.

As an embodiment, in the process of determining the sub-base mutual reference value corresponding to the above one target account based on the determined respective influence values, the sum of the influence values of the one target account with respect to the various sub-mutual information may be determined as the sub-base mutual reference value corresponding to the one target account based on, but not limited to, the following principle of formula (6).

Wherein, in the formula (6), n is the identifier of the target account; r _n The target account is a sub-base interaction reference value corresponding to the target account marked as n; i is the identifier of one piece of sub-interaction information in the various pieces of sub-interaction information; y _ i is the impact value of the target account identified as n on one piece of sub-interaction information identified as i.

Further, in the process of determining the sub-basic interaction reference value corresponding to the one target account based on the determined influence values, the obtained influence values may be subjected to weighted summation processing according to the first preset weight corresponding to the various sub-interaction information; and determining a sub-basic interactive reference value corresponding to the target account according to the result of the weighted summation processing.

If the result of the weighted summation processing can be determined as the sub-basic mutual reference value corresponding to the one target account based on the principle of the following formula (7 a); or based on the principle of the following formula (7 b), determining the ratio of the result of the weighted summation processing and the sum of the weights corresponding to the determined sub-interactive information as the sub-basic interactive reference value corresponding to the target account.

Wherein, in the above formulas (7 a) and (7 b), n is the identifier of the target account; r _n The target account is a sub-base interaction reference value corresponding to the target account marked as n; i is the identifier of one piece of sub-interaction information in the various pieces of sub-interaction information; y _ i is an influence value of the target account marked as n on the seed interactive information marked as i; k _i Is a first preset weight corresponding to a piece of sub-interactive information identified as I, I is the number of total categories of sub-interactive information of various sub-interactive information.

When the interactive information in the embodiment of the present application includes 2 seed interactive information, the above formulas (7 a) and (7 b) may be transformed into the following formulas (7 c) and (7 d); when the interactive information in the embodiment of the present application includes 3 pieces of seed interactive information, the above formulas (7 a) and (7 b) may be modified into the following formulas (7 e) and (7 f), and when the types of the sub interactive information included in the interactive information are other numbers, the analogy may be performed, and the description is not repeated here.

R _n ＝K ₁ ×Y_1+K ₂ XY _2 equation (7 c)

R _n ＝K ₁ ×Y_1+K ₂ ×Y_2+K ₃ XY-3 formula (7 e)

As an embodiment, in the step S302, in the process of determining the target interaction reference value for the determined target account set at least based on the target interaction information of each target account, the target interaction parameter value may be determined based on the interaction information of all accounts having an interaction behavior with the object to be processed and the interaction information between the target account in each target account set and the corresponding abnormal state object; specifically, the second account set corresponding to the above one abnormal state object may be, but is not limited to be, determined; determining a first information value according to the basic interaction information of each target account, determining a second information value according to the target interaction information of each target account and the target interaction information of each second account, and further determining a target interaction reference value aiming at the determined target account set based on the first information value and the second information value; and each second account comprises an account which has interactive information with the object to be processed and has no interactive information with the abnormal object.

Further, the interaction information in the embodiment of the present application may include at least one piece of sub-interaction information, that is, the interaction information in the embodiment of the present application may include one piece of sub-interaction information, and may also include a plurality of pieces of sub-interaction information, and in order to improve accuracy of the determined target interaction reference value, in the embodiment of the present application, but not limited to, respectively determining first similar reference values corresponding to various pieces of sub-interaction information in the at least one piece of sub-interaction information, and determining the first information value based on each determined first similar reference value; the first similar reference value corresponding to one piece of sub-interaction information in the various pieces of sub-interaction information is determined based on the one piece of sub-interaction information in the basic interaction information of the various target accounts.

As an embodiment, the first similar reference values corresponding to various sub-interaction information may be determined based on, but not limited to, the following principle of formula (8 a) or formula (8 b) in the embodiment of the present application.

Wherein, in the above formula (8 a) and formula (8 b), i is an identifier of one piece of sub-interaction information in the above various pieces of sub-interaction information; q1 _{Total _ i} Is the first information value; n is the account identification of the target account; n is the total number of the target accounts in the determined target account set; iATM _n The value of a piece of sub-interactive information marked as i in the basic interactive information of the target account marked as n;

is a first similar reference value corresponding to a piece of sub-interactive information identified as i.

As an embodiment, in order to further improve the accuracy of the determined target interaction reference value, in this embodiment of the application, but not limited to, determining second similar reference values corresponding to the various sub-interaction information, and determining the second information value based on the determined second similar reference values; a second similarity reference value corresponding to one piece of sub-interaction information in the various pieces of sub-interaction information is determined based on the one piece of sub-interaction information in the target interaction information of each target account and the one piece of sub-interaction information in the target interaction information of each second account; specifically, in the embodiment of the present application, the second similar reference values corresponding to various sub-interaction information may be determined based on, but not limited to, the following principle of formula (9 a) or formula (9 b).

Wherein, in the above formula (9 a) and formula (9 b), i is an identifier of one piece of sub-interaction information in the above various pieces of sub-interaction information; q2 _{Total _ i} Is the second information value; m is the account identification 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 The value of the sub-interactive information marked as i in the basic interactive information of the account marked as m;

is a second similar reference value corresponding to a piece of sub-interactive information identified as i.

As an embodiment, in order to further improve the accuracy of the finally determined target interaction reference value, in the embodiment of the present application, second weighting and summing processing may be performed on each obtained first similar reference value based on a second preset weight corresponding to each piece of sub-interaction information, so as to obtain the first information value; performing third weighted summation processing on each obtained second similar reference value based on a second preset weight corresponding to each piece of sub-interaction information to obtain a second information value; specifically, the above-described first information value may be, but is not limited to, based on the principle of the following formula (10 a) or formula (10 b); as may be based on, but not limited to, the principle of the following equation (11 a) or equation (11 b) to the above-described second information value; .

Wherein, in the above formula (10 a) and formula (10 b), i is an identifier of one piece of sub-interaction information in the above various pieces of sub-interaction information; q1 _{Total _ i} Is the first information value; n is the account identification of the target account; n is the total number of the target accounts in the determined target account set; iATM _n The value of the sub-interactive information marked as i in the basic interactive information marked as n of the target account;

is a first similar reference value corresponding to a piece of sub-interactive information marked as i; w _i Is a second preset weight corresponding to a piece of sub-interactive information identified as i.

Wherein, in the formula (11 a) and the formula (11 b), i is an identifier of one piece of sub-interaction information in the various pieces of sub-interaction information; q2 _{Total _ i} Is the second information value; m is the account identification 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 The value of a piece of sub-interactive information marked as i in the basic interactive information of the account marked as m;

is a second similar reference value corresponding to a piece of sub-interactive information identified as i; w _i Is a second preset weight corresponding to a piece of sub-interactive information identified as i.

As an embodiment, in the process of determining the target interaction reference value for the determined target account set by using the first information value and the second information value, a difference value between the first information value and the second information value may be, but is not limited to, determined as the target interaction reference value, or a ratio of the first information value and the second information value may be determined as the target interaction parameter value, and a person skilled in the art may use the method to determine the target interaction reference value according to an actual demand society; for the convenience of understanding to obtain the target cross-reference value, a specific example is given here, and when the interaction information in the embodiment of the present application includes 2 seed interaction information, the target cross-reference value may be obtained by, but is not limited to, the following principle of formula (12 a) or formula (12 b).

In the above formula (12 a) and formula (12 b), i is an identifier of one piece of sub-interaction information in the above various pieces of sub-interaction information; q1 _{Total _ i} Is the first information value; n is the account identification of the target account; n is the total number of the target accounts in the determined target account set; iATM _n The value of a piece of sub-interactive information marked as i in the basic interactive information of the target account marked as n; q2 _{Total _ i} Is the second information value; m is the account identification 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 The value of a piece of sub-interactive information marked as i in the basic interactive information of the account marked as m; w _i A second preset weight corresponding to a piece of sub-interactive information marked as i; j is the identification of an abnormal state object, COM _j Is the target interaction reference value of the target account set corresponding to the abnormal state object identified as j.

That is, the principle of the above formula (2 a) to the above formula (12 b) in the embodiment of the present application, the reference similarity of the object to be processed and each abnormal-state object may be obtained based on any one of the following formula (13 a) to formula (13 b), but is not limited thereto in the embodiment of the present application.

Wherein, in the above formulas (13 a) to (13 c), j is the identification of the abnormal state object, a _j Is the reference similarity of the object to be processed and the abnormal state object identified as j; n is the identification of the target account in the target account set corresponding to the abnormal state object with the identification of j; n is the total number of target accounts in the target account set corresponding to the abnormal state object marked as j; r _n The identification is a sub-base interaction reference value corresponding to the target account with the identification being n; i is the identifier of one piece of sub-interaction information in the various pieces of sub-interaction information; iATM _n The value of a piece of sub-interactive information marked as i in the basic interactive information of the target account marked as n; m is the account identification 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 The value of a piece of sub-interactive information marked as i in the basic interactive information of the account marked as m; w _i Is a second preset weight corresponding to a piece of sub-interactive information identified as i.

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

A specific example of the object state determination method provided in the embodiment of the present application is given below; in this example, the interaction information includes sub-interaction information X1 and sub-interaction information X2, and then a sub-basic interaction reference value corresponding to the token account may be determined based on the following formula (14); the reference similarity of the object to be processed and each abnormal-state object is determined based on the following formula (15).

In the formula (14) and the formula (15), i is an identifier of one piece of sub-interaction information in the above-mentioned various pieces of sub-interaction information; a. The _j Is the reference similarity of the object to be processed and the abnormal state object identified as j; e is the identification of the account (including the target account and the first account) with which the interaction information exists between the abnormal state object identified as j, and E is the total number of accounts with which the interaction information exists between the abnormal state object identified as j; m is the identification of the accounts (including the target account and the second account) with which the interaction information exists between the objects to be processed, and M is the total number of the accounts with which the interaction information exists between the objects to be processed; 1 xu ATM _e Is the value 1 of the sub-interaction information X1 in the basic interaction information of the account marked as e; 2 u ATM _e Is the value 1 of the sub-interaction information X2 in the basic interaction information of the account identified as e; n is the identifier of the target account in the target account set corresponding to the abnormal state object with the identifier j, and N is the total number of the target accounts in the target account set corresponding to the abnormal state object with the identifier j; r _n Is in the set of target accounts corresponding to the abnormal state object identified as j,a sub-base interaction reference value corresponding to the target account marked as n; k ₁ And K ₂ First preset weights, W, of the sub-mutual information X1 and X2, respectively ₁ And W ₂ The second preset weights of the sub interaction information X1 and X2, respectively.

As an embodiment, when the basic interaction information and the target interaction information of each target account cannot be obtained, in the embodiment of the present application, the sub-basic interaction reference value R corresponding to each target account may also be used _n Is determined as

(E is the total number of target accounts in the set of target accounts), the amount of money transferred by different accounts for the same object is considered to be the same, and the number of strokes transferred by different accounts for the same object is considered to be the same, then in this case, the above formula (15) can be transformed into the following formula (15 a):

in equation (15 a), j is the identification of the abnormal state object; a. The _j Is the reference similarity of the object to be processed and the abnormal state object identified as j; g1 is the total number of target accounts in the target account set corresponding to the abnormal state object marked as j; g2 is the total number of accounts (including the target account and the first account) for which there is interaction information with the abnormal state object identified as j; g3 is the total number of accounts (including the target account and the second account) with which the interaction information exists with the object to be processed.

In this example, information associated with a first electronic resource transfer operation for transferring an electronic resource to an object by an account is taken as interaction information, in this example, an electronic resource value transferred by the first electronic resource transfer operation (i.e., an amount of money transferred from the account to the object) is taken as the sub-interaction information X1, a number of times of the first electronic resource transfer operation (i.e., a number of strokes transferred from the account to the object) is taken as the sub-interaction information X2, an object A0 is an object to be processed, an object A1 is an abnormal state object, accounts having interaction information with the object A0 include accounts B2 to B5, and accounts having interaction information with the object A1 include accounts B1 to B4 (see fig. 6) for example, the following description is made:

scene 1: referring to (a) in fig. 6, assuming that the amounts transferred to the object A1 by the accounts B1 to B4 are 1, 2, 3 and 4, respectively, and the amounts transferred to the object A0 by the accounts B2 to B5 are 5, 6, 7 and 8, respectively, K in formula (14) is applied ₁ And K ₂ Set to 1 and 0, respectively, and W in equation (15) ₁ And W ₂ Set to 1 and 0, respectively; then the target account set corresponding to the abnormal state object may be determined as { account B2, account B3, account B4}, and based on the formula (14), the sub-base mutual reference values corresponding to accounts B2 to B4 may be determined to be respectively account B2 to account B4

Further, based on the principle of the formula (15), it can be determined

The reference similarity A of the object A0 and the object A1 can be determined ₁ Is 0.312.

Scene 2: referring to fig. 6 (B), it is assumed that the amounts transferred to the object A1 by the accounts B1 to B4 are 1, 2, 3 and 4, respectively, the numbers of strokes transferred to the object A1 by the accounts B1 to B4 are 1, 2 and 2, respectively, the amounts transferred to the object A0 by the accounts B2 to B5 are 5, 6, 7 and 8, respectively, and the amounts transferred to the object A0 by the accounts B2 to B5 are 2, 3 and 4, respectively; at this time, K in the formula (14) ₁ And K ₂ Set to 1 and 1, respectively, and W in equation (15) ₁ And W ₂ Set to 1 and 1, respectively;

then the target account set corresponding to the abnormal status object may be determined as { account B2, account B3, account B4}, and based on formula (14), the sub-base cross-reference values corresponding to accounts B2 to B4 may be determined to be respectively

Further, based on the principle of the formula (15), it can be determined

The reference similarity of the object A0 and the object A1 can be determined to be 0.328.

According to the method provided by the embodiment of the application, the risk object (namely the object to be processed with the abnormal state) with similar behavior with the abnormal state object is identified based on the interactive information of the target account, and scenes such as a risk banker with abnormal funding in gambling, an abnormal merchant or an individual with credit card cash register, an abnormal merchant with single line swiping and the like can be identified, so that the accuracy of identifying the abnormal state object can be obviously improved, and the accuracy of identifying whether the state of the object is abnormal or not is improved.

Referring to fig. 7, based on the same inventive concept, an embodiment of the present application provides an apparatus 700 for determining a state of an object, including:

a destination account determining unit 7001, configured to determine a destination account set corresponding to each abnormal state object in the abnormal state object set, where there is interaction information between each destination account and the corresponding abnormal state object and the object to be processed;

a similarity estimation unit 7002, configured to determine reference similarities of the to-be-processed object and each abnormal-state object respectively based on the obtained basic interaction information and target interaction information of each target account in each target account set; the basic interaction information comprises interaction information between a target account and a corresponding abnormal state object, and the target interaction information comprises interaction information between the target account and the object to be processed;

an object state determination unit 7003, configured to determine whether the object state of the above-described object to be processed is abnormal based on the obtained respective reference similarities.

As an example, the similarity estimation unit 7002 is specifically configured to: the following operations are respectively carried out for each abnormal state object:

determining a basic interaction reference value aiming at the determined target account set at least based on the basic interaction information of each target account in the determined target account set; and

determining a target interaction reference value aiming at the determined target account set at least based on the target interaction information of each target account;

and determining the reference similarity between the account to be processed and the abnormal state object based on the basic cross reference value and the target cross reference value.

As an example, the similarity estimation unit 7002 is specifically configured to:

and determining a basic interactive reference value aiming at the determined target account set according to the corresponding basic interactive reference value of each target account.

As an embodiment, the interactive information includes at least one piece of sub-interactive information; the similarity estimation unit 7002 is specifically configured to: determining a basic reference total value corresponding to each sub-interaction information in the at least one piece of sub-interaction information; the basic reference total value corresponding to one piece of sub-interaction information in the various pieces of sub-interaction information is determined based on the one piece of sub-interaction information in the basic interaction information of each target account and the one piece of sub-interaction information in the basic interaction information of each first account;

the similarity estimation unit 7002 described above is further configured to: for each target account in the target accounts, the following operations are respectively executed: respectively determining the influence value of one target account on various sub-interaction information based on various sub-interaction information in the basic interaction information of one target account in the target accounts and the basic reference total value corresponding to the various sub-interaction information; and determining a sub-basic mutual reference value corresponding to the target account based on the determined influence values.

As an example, the similarity estimation unit 7002 is specifically configured to: according to the first preset weight corresponding to the various sub-interactive information, carrying out weighted summation processing on the obtained various influence values; and determining a sub-basic interactive reference value corresponding to the target account according to the result of the weighted summation processing.

As an example, the similarity estimation unit 7002 is specifically configured to: determining the result of the weighted summation processing as a sub-basic interactive reference value corresponding to the target account; or, determining a ratio of the result of the weighted sum processing to the sum of weights corresponding to each piece of sub-interaction information as a sub-basic interaction reference value corresponding to the one target account.

determining a second account set corresponding to the abnormal state object, wherein each second account comprises an account which has interactive information with the object to be processed and does not have interactive information with the abnormal object;

and determining a target cross reference value aiming at the determined target account set based on the first information value and the second information value.

As an embodiment, the interactive information includes at least one piece of sub-interactive information; the similarity estimation unit 7002 is specifically configured to:

determining second similar reference values corresponding to the various sub-interaction information; a second similarity reference value corresponding to one piece of sub-interaction information in the various pieces of sub-interaction information is determined based on the one piece of sub-interaction information in the target interaction information of each target account and the one piece of sub-interaction information in the target interaction information of each second account;

the second information values are determined based on the determined respective second similarity reference values.

As an example, the similarity estimation unit 7002 is specifically configured to: performing second weighted summation processing on each obtained first similar reference value based on a second preset weight corresponding to each piece of sub-interaction information to obtain the first information value; and performing third weighted summation processing on each obtained second similar reference value based on second preset weight corresponding to each piece of sub-interaction information to obtain the second information value.

As an embodiment, the interaction information includes at least one of the following sub-interaction information: an electronic resource value transferred by the electronic resource transfer operation; the number of operations of the electronic resource transfer operation.

As an embodiment, the object state determination unit 7003 is specifically configured to: determining a state evaluation value that the object state of the object to be processed is an abnormal state based on the obtained respective reference similarities; if it is determined that the state evaluation value is larger than the first state evaluation value threshold, it is determined that the object state of the object to be processed is abnormal.

As an embodiment, after determining that the object status of the above-mentioned object to be processed is abnormal, the object status determination unit 7003 is further configured to: if the state evaluation value is determined to be larger than a second state evaluation value threshold value, determining the object to be processed as an abnormal state object, wherein the second state evaluation value threshold value is not smaller than the first state evaluation value threshold value; and adding the object to be processed into the abnormal state object set.

As an example, the apparatus in fig. 7 may be used to implement any one of the methods for determining the state of an object discussed above.

The method embodiment is based on the same inventive concept, and the embodiment of the application also provides computer equipment. The computer device may be used for push content based data processing. In one embodiment, the computer device may be a server, such as server 120 shown in FIG. 1. In this embodiment, the structure of the computer device can be as shown in fig. 8, including a memory 801, a communication module 803, and one or more processors 802.

A memory 801 for storing computer programs executed by the processor 802. The memory 801 may mainly include a program storage area and a data storage area, where the program storage area may store an operating system, programs required for running an instant messaging function, and the like; the storage data area can store various instant messaging information, operation instruction sets and the like.

The Memory 801 may be a Volatile Memory (Volatile Memory), such as a Random-Access Memory (RAM); the Memory 801 may also be a Non-Volatile Memory (Non-Volatile Memory), such as a read-only Memory (rom), a Flash Memory (Flash Memory), a Hard Disk Drive (HDD) or a Solid-State Drive (SSD); or memory 801 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. Memory 801 may be a combination of the above.

The processor 802 may include one or more Central Processing Units (CPUs), or be a digital Processing Unit, etc. The processor 802 is configured to implement the above-mentioned object state determination method when calling the computer program stored in the memory 801.

The communication module 803 is used for communicating with the terminal device and other servers.

The embodiment of the present application does not limit the specific connection medium among the memory 801, the communication module 803, and the processor 802. In the embodiment of the present application, the memory 801 and the processor 802 are connected by a bus 804 in fig. 8, the bus 804 is represented by a thick line in fig. 8, and the connection manner between other components is merely illustrative and is not limited. The bus 804 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 8, but this is not intended to represent only one bus or type of bus.

The memory 801 stores a computer storage medium, and the computer storage medium stores computer-executable instructions for implementing the account feature extraction method according to the embodiment of the present application. The processor 802 is configured to perform the above-mentioned determination method of the object status.

Those of ordinary skill in the art will understand that: all or part of the steps of implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer-readable storage medium, and when executed, executes the steps including the method embodiments; and the aforementioned storage medium includes: various media capable of storing program codes, such as a removable Memory device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Alternatively, the integrated unit of the invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the above methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.

Based on the same technical concept, the embodiment of the present application also provides a computer-readable storage medium storing computer instructions, which, when executed on a computer, cause the computer to execute the determination method for object status as discussed above.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may 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, and the like) having computer-usable program code embodied therein.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A method for determining a state of an object, comprising:

respectively determining a target account set corresponding to each abnormal state object in the abnormal state object set, wherein each target account, the corresponding abnormal state object and the object to be processed have interaction information;

2. The method according to claim 1, wherein the determining the reference similarity of the object to be processed and each abnormal-state object respectively based on the obtained basic interaction information and target interaction information of each target account in each target account set comprises:

respectively carrying out the following operations on each abnormal state object:

3. The method of claim 2, wherein determining a base interaction reference value for the determined set of target accounts based at least on the base interaction information for each of the determined set of target accounts comprises:

4. The method of claim 3, wherein the interaction information comprises at least one piece of sub-interaction information; determining a sub-basic interaction reference value corresponding to each target account according to the basic interaction information of each target account and the basic interaction information of each first account, including:

further, for each of the target accounts, the following operations are respectively performed:

5. The method of claim 4, wherein determining the sub-base mutual reference value corresponding to the one target account based on the determined respective impact values comprises:

according to the first preset weight corresponding to each sub-interactive information, carrying out weighted summation processing on each obtained influence value;

and determining a sub-basic interaction reference value corresponding to the target account according to the result of the weighted summation processing.

6. The method of claim 2, wherein determining the target interaction reference value for the determined set of target accounts based at least on the target interaction information for the respective target account comprises:

7. The method of claim 6, wherein the interaction information comprises at least one piece of sub-interaction information; determining a first information value according to the basic interaction information of each target account, including:

determining a second information value according to the target interaction information of each target account and the target interaction information of each second account, including:

determining second similar reference values corresponding to the various sub-interaction information; the second similarity reference value corresponding to one piece of sub-interaction information in the various pieces of sub-interaction information is determined based on the one piece of sub-interaction information in the target interaction information of each target account and the one piece of sub-interaction information in the target interaction information of each second account;

8. The method of claim 7, wherein said determining the first information value based on the determined respective first similar reference values comprises:

said determining said second information values based on the determined respective second similar reference values comprises:

9. The method of any one of claims 1-8, wherein the interaction information comprises at least one of the following sub-interaction information:

the number of operations of the electronic resource transfer operation.

10. The method according to any one of claims 1 to 8, wherein the determining whether the object state of the object to be processed is abnormal based on the obtained respective reference similarities comprises:

determining a state evaluation value that an object state of the object to be processed is an abnormal state based on the obtained respective reference similarities;

determining that the object state of the object to be processed is abnormal if it is determined that the state evaluation value is greater than a first state evaluation value threshold.

11. The method of claim 10, wherein after determining that the object state of the object to be processed is abnormal, further comprising:

if the state evaluation value is determined to be larger than a second state evaluation value threshold value, determining the object to be processed as an abnormal state object, wherein the second state evaluation value threshold value is not smaller than the first state evaluation value threshold value; and

and adding the object to be processed into the abnormal state object set.

12. An apparatus for determining a state of an object, comprising:

13. A computer program product, comprising computer instructions stored in a computer-readable storage medium, the computer instructions being read from the computer-readable storage medium by a processor of the computer device, the processor executing the computer instructions to cause the computer device to perform the method of any one of claims 1-11.

14. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1-11 when executing the program.

15. A computer-readable storage medium having stored thereon computer instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1-11.