Method, apparatus, computer device, and storage medium for determining target index value

Abstract

The present application relates to a method, apparatus, computer device, and storage medium for determining a target index value. The method includes: displaying the sample account distribution curves of a first sample account and a second sample account respectively under a to-be-detected index; in response to a triggered index value recommendation operation, sequentially obtaining the account distribution numbers of the first sample account and the second sample account under each index value of the to-be-detected index according to the sample account distribution curves, and determining the detection effect values for detecting the first sample account corresponding to each index value based on the account distribution numbers; obtaining an effect change amount based on the differences between the detection effect values corresponding to adjacent index values; determining a target index value for detecting a first account according to the effect change amount; and displaying the target index value as a recommended result. Using this method can avoid determining the target index value depending on the preferences of evaluators.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and particularly to a method, apparatus, computer device, and storage medium for determining a target index value. Background Technique

[0002] With the continuous development of Internet technology, the flow and transfer of numerical resources through the network are increasingly popular among users. Therefore, the security and legality of the flow and transfer behavior of numerical resources have attracted extensive attention. In traditional solutions, determining suspicious resource accounts is the current main technical means. For example, for each resource account, by analyzing whether indicators such as the number of resource transfers or the amount of resource transfers corresponding to it meet the corresponding target index value conditions, suspicious resource accounts can be determined, and then it can be judged whether the flow and transfer behavior of numerical resources is safe and legal.

[0003] However, currently, the determination of the target index values of different indicators mainly depends on historical sample data and the preferences of evaluators, resulting in inconsistent identification criteria for suspicious resource accounts, and further affecting the identification effect of the security and legality of the flow and transfer behavior of numerical resources. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, apparatus, computer device, and storage medium for determining a target index value that can improve the identification effect of the security and legality of the flow and transfer behavior of numerical resources.

[0005] A method for determining a target index value, the method comprising:

[0006] Displaying the sample account distribution curves of the first sample account and the second sample account respectively under the index to be measured;

[0007] In response to the triggered index value recommendation operation, sequentially obtaining the account distribution numbers of the first sample account and the second sample account at each index value of the index to be measured according to the sample account distribution curve, and determining the detection effect values corresponding to each index value when detecting the first sample account based on the account distribution numbers;

[0008] Obtaining an effect change amount based on the difference between the detection effect values corresponding to adjacent index values;

[0009] Determining a target index value for detecting the first account according to the effect change amount;

[0010] Displaying the target index value as a recommended result.

[0011] A device for determining a target index value, the device comprising:

[0012] A distribution curve display module for displaying the sample account distribution curves of the first sample account and the second sample account respectively under the to-be-tested indicator;

[0013] An effect value determination module, configured to, in response to a triggered indicator value recommendation operation, sequentially obtain the account distribution numbers of the first sample account and the second sample account under each indicator value of the to-be-tested indicator according to the sample account distribution curve, and determine the detection effect values corresponding to each of the indicator values when detecting the first sample account based on the account distribution numbers;

[0014] A change amount determination module for obtaining an effect change amount based on the differences between the detection effect values corresponding to adjacent indicator values;

[0015] A target indicator value calculation module for determining a target indicator value for detecting the first account according to the effect change amount;

[0016] A result display module for displaying the target indicator value as a recommended result.

[0017] In one embodiment, the effect value determination module is further configured to:

[0018] Calculate a first hit rate corresponding to each of the indicator values when detecting the first sample account according to the account distribution numbers;

[0019] Determine the detection effect values corresponding to each of the indicator values when detecting the first sample account based on the differences between the first hit rates corresponding to adjacent indicator values.

[0020] In one embodiment, the effect value determination module is further configured to:

[0021] Calculate a difference in the first sample hit amounts corresponding to adjacent indicator values when detecting the first sample account according to the account distribution number of the first sample account;

[0022] Calculate a difference in the second sample hit amounts corresponding to adjacent indicator values when detecting the first sample account according to the account distribution number of the second sample account;

[0023] Calculate the detection effect values corresponding to each of the indicator values when detecting the first sample account based on the difference in the first sample hit amounts and the difference in the second sample hit amounts.

[0024] In one embodiment, the result display module is further configured to:

[0025] Determine a first candidate indicator value interval matching the target indicator value;

[0026] Calculate a first target hit rate and a first target coverage rate for detecting the first sample account corresponding to the target metric value based on the number of account distributions of the first sample account and the second sample account within the first candidate metric value range;

[0027] Display the first target hit rate and the first target coverage rate.

[0028] In one embodiment, the sample account distribution curve is displayed in a distribution diagram; the distribution curve display module is further configured to:

[0029] Display the full - volume account distribution curve of all accounts under the metric to be measured in the distribution diagram;

[0030] The effect value determination module is further configured to, in response to a triggered metric value recommendation operation, sequentially obtain the number of full - volume account distributions of all accounts at each metric value of the metric to be measured according to the full - volume account distribution curve;

[0031] The effect value determination module is further configured to determine the detection effect value when detecting the first sample account corresponding to each metric value based on the number of account distributions and the number of full - volume account distributions.

[0032] In one embodiment, the effect value determination module is further configured to:

[0033] Calculate a first hit rate when detecting the first sample account corresponding to each metric value according to the number of account distributions;

[0034] Determine the difference in the full - volume hit quantity corresponding to each metric value according to the number of full - volume account distributions of all accounts at each metric value;

[0035] Calculate the detection effect value when detecting the first sample account corresponding to each metric value based on the difference between the first hit rates corresponding to adjacent metric values and the difference in the full - volume hit quantity.

[0036] In one embodiment, the effect value determination module is further configured to:

[0037] Calculate the difference in the first sample hit quantity when detecting the first sample account corresponding to adjacent metric values according to the number of account distributions of the first sample account;

[0038] Calculate the difference in the second sample hit quantity when detecting the first sample account corresponding to adjacent metric values according to the number of account distributions of the second sample account;

[0039] Determine the difference in the full - volume hit quantity corresponding to each metric value according to the number of full - volume account distributions of all accounts at each metric value of the metric to be measured;

[0040] Based on the first sample hit quantity difference, the second sample hit quantity difference, and the full quantity hit quantity difference, calculate the detection effectiveness value for detecting the first sample account corresponding to each of the index values.

[0041] In one embodiment, the result display module is further configured to:

[0042] Determine a second candidate index value range that matches the target index value;

[0043] Based on the account distribution numbers of the first sample account and the second sample account within the second candidate index value range, calculate the second target hit rate and the second target coverage rate for detecting the first sample account corresponding to the target index value;

[0044] Based on the account distribution number of the full quantity account within the second candidate index value range, calculate the full quantity hit quantity corresponding to the target index value;

[0045] Display the second target hit rate, the second target coverage rate, and the full quantity hit quantity in the distribution diagram.

[0046] In one embodiment, the sample account distribution curve is displayed in the distribution diagram; the apparatus further includes: a real-time acquisition module, a real-time determination module, a real-time calculation module, and a real-time display module, where

[0047] The real-time acquisition module is configured to, in response to a movement operation of the index threshold line in the distribution diagram, acquire the real-time index value that changes in real time during the movement of the index threshold line;

[0048] The real-time determination module is configured to determine a candidate real-time index value that matches the real-time index value;

[0049] The real-time calculation module is configured to, based on the account distribution numbers of the first sample account and the second sample account corresponding to the candidate real-time index value, calculate the second hit rate and the second coverage rate for detecting the first sample account corresponding to the real-time index value;

[0050] The real-time display module is configured to display the second hit rate and the second coverage rate in the distribution diagram.

[0051] In one embodiment, the distribution curve display module is further configured to: display the full quantity account distribution curve of the full quantity account under the index to be measured in the distribution diagram;

[0052] The real-time calculation module is further configured to, based on the account distribution number of the full quantity account corresponding to the candidate real-time index value, calculate the full quantity hit quantity corresponding to the real-time index value;

[0053] The real-time display module is further configured to display the second hit rate, the second coverage rate, and the full-volume hit volume in the distribution diagram.

[0054] In one embodiment, the device further includes: a sample determination module, where

[0055] The sample determination module is configured to extract sample accounts from all accounts; obtain interaction data corresponding to the sample accounts under the to-be-detected metrics; and mark the sample accounts based on the interaction data to obtain first sample accounts and second sample accounts.

[0056] In one embodiment, the to-be-detected metrics include at least one of the amount of resource transfer, the number of resource transfer times, and the number of resource transfer objects.

[0057] A computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are implemented:

[0058] Display the sample account distribution curves of the first sample accounts and the second sample accounts respectively under the to-be-detected metrics;

[0059] In response to a triggered metric value recommendation operation, sequentially obtain the account distribution numbers of the first sample accounts and the second sample accounts at each metric value of the to-be-detected metrics according to the sample account distribution curve, and determine the detection effect values corresponding to each metric value for detecting the first sample accounts based on the account distribution numbers;

[0060] Obtain an effect change amount based on the difference between the detection effect values corresponding to adjacent metric values;

[0061] Determine a target metric value for detecting the first account according to the effect change amount;

[0062] Display the target metric value as a recommendation result.

[0063] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0064] Display the sample account distribution curves of the first sample accounts and the second sample accounts respectively under the to-be-detected metrics;

[0065] In response to a triggered metric value recommendation operation, sequentially obtain the account distribution numbers of the first sample accounts and the second sample accounts at each metric value of the to-be-detected metrics according to the sample account distribution curve, and determine the detection effect values corresponding to each metric value for detecting the first sample accounts based on the account distribution numbers;

[0066] Obtain an effect change amount based on the differences between the detection effect values corresponding to adjacent said index values;

[0067] Determine a target index value for detecting a first account according to the effect change amount;

[0068] Display the target index value as a recommended result.

[0069] A computer program, the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium, a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the following steps:

[0070] Display the sample account distribution curves of a first sample account and a second sample account respectively under a to-be-detected index;

[0071] In response to a triggered index value recommendation operation, sequentially obtain the account distribution numbers of the first sample account and the second sample account under each index value of the to-be-detected index according to the sample account distribution curve, and determine the detection effect values corresponding to each index value when detecting the first sample account based on the account distribution numbers;

[0072] Obtain an effect change amount based on the differences between the detection effect values corresponding to adjacent said index values;

[0073] Determine a target index value for detecting a first account according to the effect change amount;

[0074] Display the target index value as a recommended result.

[0075] For the above-mentioned target index value determination method, device, computer device and storage medium, after displaying the sample account distribution curves of a first sample account and a second sample account respectively under a to-be-detected index, in response to a triggered index value recommendation operation, sequentially obtain the account distribution numbers of the first sample account and the second sample account under each index value of the to-be-detected index according to the sample account distribution curve, and determine the detection effect values corresponding to each index value when detecting the first sample account based on the account distribution numbers, obtain an effect change amount based on the differences between the detection effect values corresponding to adjacent index values, and further determine a target index value for detecting a first account according to the determined effect change amount, and display the target index value as a recommended result, so that the evaluator can determine a suspicious resource account based on the target index value, and then can judge whether the numerical resource flow and transfer behavior is safe and legal, avoiding determining the target index value depending on the preferences of the evaluator, ensuring the consistency of the identification criteria for suspicious resource transfer accounts, and further improving the identification effect of the safety and legality of the numerical resource flow and transfer behavior. Brief Description of the Drawings

[0076] Figure 1 FIG. is an application environment diagram of the method for determining the target index value in an embodiment;

[0077] Figure 2 FIG. is a schematic flowchart of the method for determining the target index value in an embodiment;

[0078] Figure 3 FIG.

[0076] is a schematic diagram of the sample account distribution curve in an embodiment;

[0079] Figure 4 FIG. Figure 1 is a schematic diagram of the sample account distribution curve in another embodiment;

[0080] Figure 5 FIG. is a schematic diagram of the distribution diagram in an embodiment;

[0081] Figure 6 FIG.

[0077] is a schematic flowchart of the steps for determining the detection effect value in an embodiment;

[0082] Figure 7 FIG. Figure 2 is a schematic diagram of the distribution diagram in another embodiment;

[0083] Figure 8 FIG. is a schematic diagram of the distribution diagram in another embodiment;

[0084] Figure 9 FIG.

[0078] is a schematic flowchart of the method for determining the target index value in another embodiment;

[0085] Figure 10 FIG. Figure 3 is a structural block diagram of the target index value determination device in an embodiment;

[0086] Figure 11 FIG. is a structural block diagram of the target index value determination device in another embodiment;

[0087] Figure 12 FIG.

[0079] is an internal structural diagram of the computer device in an embodiment;

[0088] Figure 13 FIG. Figure 4 is an internal structural diagram of the computer device in an embodiment. Detailed Description of the Embodiments

[0089] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0090] In the claims, specification and drawings of the present application, terms such as "first", "second", "third", etc. (if any) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0091] The target index value determination method provided by the present application can be implemented based on cloud technology. Among them, cloud technology (Cloud technology) refers to a hosting technology that unifies a series of resources such as hardware, software, and networks within a wide area network or a local area network to achieve data calculation, storage, processing, and sharing. Cloud technology is the general term for network technology, information technology, integration technology, management platform technology, application technology, etc. applied based on the cloud computing business model, and can form a resource pool, which can be used on demand, flexibly and conveniently. Cloud computing technology will become an important support. The background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture websites, and more portal websites. With the high development and application of the Internet industry, in the future, each item may have its own identification mark and needs to be transmitted to the background system for logical processing. Data at different levels will be processed separately, and various types of industry data require a powerful system back-end support, which can only be achieved through cloud computing.

[0092] Cloud computing is a computing model that distributes computing tasks across a resource pool composed of a large number of computing devices, enabling various application systems to obtain computing power, storage space, and information services as needed. The network that provides resources is called the "cloud". The resources in the "cloud" seem to be infinitely expandable to users, and can be obtained at any time, used on demand, expanded at any time, and paid according to usage.

[0093] As a basic capability provider of cloud computing, a cloud computing resource pool (abbreviated as a cloud platform, generally referred to as an IaaS (Infrastructure as a Service) platform) will be established, and various types of virtual resources will be deployed in the resource pool for external customers to choose and use. The cloud computing resource pool mainly includes: computing devices (virtual machines, including operating systems), storage devices, and network devices.

[0094] According to the logical function division, on the IaaS (Infrastructure as a Service) layer, the PaaS (Platform as a Service) layer can be deployed, and on top of the PaaS layer, the SaaS (Software as a Service) layer can be deployed. Or the SaaS can be directly deployed on the IaaS. PaaS is the platform for software operation, such as databases, web containers, etc. SaaS are various business softwares, such as web portals, SMS mass senders, etc. Generally speaking, SaaS and PaaS are the upper layers relative to IaaS.

[0095] Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that combines a large number of different types of storage devices (storage devices are also called storage nodes) in the network through functions such as cluster applications, grid technology, and distributed file systems, and works together through application software or application interfaces to jointly provide data storage and business access functions to the outside world.

[0096] Blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithms. Blockchain, in essence, is a decentralized database, a series of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (anti-counterfeiting) and generate the next block. Blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0097] The underlying blockchain platform may include processing modules such as user management, basic services, smart contracts, and operation monitoring. Among them, the user management module is responsible for the identity information management of all blockchain participants, including maintaining the generation of public and private keys (account management), key management, and the maintenance of the correspondence between the real identity of the user and the blockchain address (permission management). And under authorization, it supervises and audits the transaction situations of certain real identities, and provides the rule configuration for risk control (risk control audit); the basic service module is deployed on all blockchain node devices to verify the validity of business requests, and records the valid requests to the storage after consensus. For a new business request, the basic service first performs interface adaptation parsing and authentication processing (interface adaptation), then encrypts the business information through the consensus algorithm (consensus management), transmits it to the shared ledger completely and consistently after encryption (network communication), and performs record storage; the smart contract module is responsible for the registration and issuance of contracts, contract triggering, and contract execution. Developers can define contract logic through a certain programming language, publish it to the blockchain (contract registration), trigger the execution by calling keys or other events according to the logic of the contract terms, complete the contract logic, and at the same time provide the functions of contract upgrade and cancellation; the operation monitoring module is mainly responsible for the deployment, configuration modification, contract setting, cloud adaptation during the product release process, and the visual output of the real-time state during the product operation, such as: alarm, monitoring network conditions, monitoring the health status of node devices, etc.

[0098] The platform product service layer provides the basic capabilities and implementation frameworks of typical applications. Developers can build on these basic capabilities and overlay the characteristics of the business to complete the blockchain implementation of the business logic. The application service layer provides application services based on the blockchain solution for business participants to use.

[0099] The method for determining the target metric value provided in this application can be applied to, for example Figure 1 the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The above method for determining the target metric value can also be applied to the terminal 102 or the server 104, and can also be applied to Figure 1A system including a terminal 102 and a server 104 as shown, and is implemented through the interaction between the terminal 102 and the server 104. Taking the above-mentioned target index value determination method executed on the terminal 102 as an example for illustration, the terminal 102 displays the sample account distribution curves of the first sample account and the second sample account respectively under the index to be measured; in response to the triggered index value recommendation operation, sequentially obtains the account distribution numbers of the first sample account and the second sample account under each index value of the index to be measured based on the sample account distribution curves, and determines the detection effect values when detecting the first sample account corresponding to each index value based on the account distribution numbers; obtains the effect change amount based on the difference between the detection effect values corresponding to each adjacent index value; determines the target index value for detecting the first account according to the effect change amount; and displays the target index value as a recommendation result.

[0100] Among them, the terminal 102 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides 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, CDN, as well as big data and artificial intelligence platforms.

[0101] In one embodiment, as Figure 2 shown, a method for determining a target index value is provided. Taking the application of this method to the Figure 1 computer device (terminal or server) as an example for illustration, it includes the following steps:

[0102] S202, display the sample account distribution curves of the first sample account and the second sample account respectively under the index to be measured.

[0103] Among them, the first sample account refers to a sample account with suspected resource transfer, and can also be called a black sample account. The second sample account is a sample account without suspected resource transfer behavior, and can also be called a white sample account. The suspected resource transfer behavior can be illegal numerical resource flow and transfer behaviors, such as resource transfer behaviors suspected of money laundering. Money laundering refers to covering up and concealing the source and nature of illegal proceeds and the proceeds generated therefrom through various means to make them legal in form. In recent years, e-commerce and its derived third-party online payments have become emerging money laundering tools for criminals. Money launderers use e-commerce trading accounts to conduct frequent false transactions, and at the same time, achieve the purpose of money laundering through online payment platforms to realize the flow and transfer of funds.

[0104] The sample account can be the account corresponding to the sample resource transfer data extracted from the historical resource transfer data, or the account corresponding to the sample resource transfer data extracted from the resource transfer data to be detected. It should be noted that the resource transfer behavior involved in this application includes the resource transfer behavior generated when transactions occur between resource transfer accounts.

[0105] The index to be detected is an index used to determine the attribute of an account. The attributes of an account include a suspicious account and a non-suspicious account. The index includes at least one of the number of resource transfers involved in the resource transfer data, the amount of resource transfer, and the number of resource transfer objects. The number of resource transfers is the number of resource transfer behaviors generated by the resource transfer account; the amount of resource transfer is the amount transferred by each resource transfer behavior generated by the resource transfer account, or the cumulative amount of all resource transfers generated by the resource transfer account; the number of resource transfer objects is the number of other accounts that conduct resource transfers with the resource transfer account.

[0106] The sample account distribution curve refers to a curve determined with different index values as the abscissa and the frequency of occurrence of sample accounts at each index value as the ordinate under the index to be detected, including the first sample account distribution curve corresponding to the first sample account and the account distribution curve corresponding to the second sample account.

[0107] In one embodiment, the computer device extracts sample accounts, obtains the resource transfer data corresponding to each sample account, determines the first sample account and the second sample account in the sample accounts based on the obtained resource transfer data, and determines, based on the resource transfer data corresponding to each first sample account under different indexes to be detected, different sample account distribution curves corresponding to all the first sample accounts under different indexes to be detected, that is, the first sample account distribution curve; and determines, based on the resource transfer data corresponding to each second sample account under different indexes to be detected, different sample account curves corresponding to all the second sample accounts under different indexes to be detected, that is, the second sample account distribution curve.

[0108] Among them, the obtained resource transfer data includes resource transfer data under different indexes, such as the statistical data of the resource transfer amount of each sample account corresponding to the resource transfer amount index, the statistical data of the number of resource transfers of each sample account corresponding to the number of resource transfers index, and the statistical data of the resource transfer objects of each sample account corresponding to the number of resource transfer objects index.

[0109] Specifically, the computer device can determine the first sample account distribution curve corresponding to the resource transfer amount index of the first sample account and the second sample account distribution curve corresponding to the resource transfer amount index of the second sample account based on the statistical data of the resource transfer amounts of each sample account corresponding to the resource transfer amount index; the computer device can determine the first sample account distribution curve corresponding to the resource transfer times index of the first sample account and the second sample account distribution curve corresponding to the resource transfer times index of the second sample account based on the statistical data of the resource transfer times of each sample account corresponding to the resource transfer times index; the computer device can determine the first sample account distribution curve corresponding to the resource transfer object number index of the first sample account and the second sample account distribution curve corresponding to the resource transfer object number index of the second sample account based on the statistical data of the resource transfer object numbers of each sample account corresponding to the resource transfer amount index.

[0110] As Figure 3 shown, it is the sample account distribution curve in an embodiment, where the curve corresponding to the dots is the second sample account distribution curve, and the curve corresponding to the squares is the first sample account distribution curve. The first sample account distribution curve and the second sample account distribution curve are the sample account distribution curves under the resource transfer object number index. Figure 3 In the figure, the abscissa is the quantity of the resource transfer object number, and the ordinate is the quantity of the accounts, which characterizes the distribution of the first sample account and the second sample account in the dimension of the resource transfer object number index.

[0111] In one embodiment, after the computer device obtains the resource transfer data of the sample account under the to-be-detected index, it determines the corresponding index value interval based on the resource transfer data corresponding to the to-be-detected index, divides the determined index value interval into multiple index value sub-intervals, determines the number of the first sample accounts and the number of the second sample accounts corresponding to each index value sub-interval, and then generates the first sample account distribution curve and the second sample account curve based on the number of the sample accounts with different attributes corresponding to each sub-index value sub-interval, and displays the generated first sample account curve and the second sample account curve.

[0112] For example, if the index to be detected is the resource transfer amount index, after the computer device obtains the statistical data of the resource transfer amount of the sample account, and determines that the maximum resource transfer amount of a single sample account is 1000 yuan and the minimum resource transfer amount is 100 yuan, then the index value range corresponding to the resource transfer amount index can be determined as [100, 1000]. Furthermore, this index value range is divided into ten index value sub-ranges: "[100, 200), [200, 300),... [800, 900), [900, 1000]". Then, the number of first sample accounts corresponding to each index value sub-range is determined, thereby generating a first sample account distribution curve, the number of second sample accounts corresponding to each index value sub-range is determined, thereby generating a second sample account distribution curve, and the generated first sample account curve and second sample account curve are displayed.

[0113] S204, in response to the triggered index value recommendation operation, sequentially obtain the account distribution numbers of the first sample account and the second sample account at each index value of the index to be detected according to the sample account distribution curve, and determine the detection effect values corresponding to each index value when detecting the first sample account based on the account distribution numbers.

[0114] Among them, index value recommendation refers to recommending the optimal index value for account identification based on the distribution of sample accounts, so as to perform the first account detection using the recommended index value. Performing the first account detection using the recommended index value can specifically be to perform the first account detection according to the preset detection rules and the recommended index value. For example, when the detection rule is to detect accounts not less than the recommended index value, then during detection, the accounts in the resource transfer data not less than the recommended index value are determined as the first account; when the detection rule is to detect accounts less than the recommended index value, then during detection, the accounts in the resource transfer data less than the recommended index value are determined as the first account. The first account involved in this application is an account of the same account type as the first sample account, and the second account is an account of the same account type as the second sample account. That is to say, the first account refers to an account with a suspected resource transfer behavior, and the second account is an account without a suspected resource transfer behavior.

[0115] For example, if the preset detection rule is to detect an account not less than the recommended metric value, then when using this metric value to detect the first account, the accounts not less than this metric value in the resource transfer data will be determined as the first account. The detected first accounts include the true first account and the true second account that are hit, while the true first account in the resource transfer data that is less than this metric value cannot be hit. Based on this, the hit rate can be used to represent the ratio of the true first account in the detected first accounts, and the coverage rate can be used to represent the ratio of the detected first accounts in all true first accounts. That is to say, the hit rate is the ratio of the true first account in the first accounts determined based on the metric value, and the coverage rate is the ratio of the true first accounts that can be determined based on the metric value in all true first accounts. It can be understood that when performing actual detection, the first accounts determined based on the metric value include the true first account and the true second account. Therefore, the hit rate can be calculated using formula (1); when performing actual detection, based on the metric value, not all true first accounts can be detected, only some of the true first accounts can be detected. Therefore, the coverage rate can be calculated using formula (2), where formula (1) and formula (2) are as follows:

[0116]

[0117]

[0118] Among them, S 判.黑(黑) refers to the true first account in the first accounts determined based on the metric value, and S 判.黑(白+黑) refers to the first accounts determined based on the metric value, specifically including the true first account and the true second account, and S 判.黑(白) refers to the true second account in the first accounts determined based on the metric value. S 全.真.黑 refers to all existing true first accounts, including the true first account in the first accounts determined based on the metric value and the true first account that is not determined as the first account.

[0119] It can be understood that when using the recommended metric value to detect the first account, the best detection effect can be achieved. The best detection effect refers to comprehensively considering the hit rate and coverage rate of the first account, and avoiding the situation where the hit rate is high while the coverage rate is low, or the coverage rate is low while the hit rate is high.

[0120] The account distribution number refers to the number of accounts corresponding to each indicator value. The indicator value can be a specific numerical value or an indicator value sub-interval. When the indicator value is an indicator value sub-interval, the account distribution number is the number of accounts corresponding to the distribution of the indicator value sub-interval. It can be understood that the account distribution number of the first sample accounts is the number of the first sample accounts corresponding to each indicator value, and the account distribution number of the second sample accounts is the number of the second sample accounts corresponding to each indicator value.

[0121] The detection effect value is used to numerically represent the detection effect on the first sample accounts when detecting the first sample accounts using the corresponding indicator value. It can be understood that when using the recommended indicator value for the first account detection, the detection effect value of the recommended indicator value represents the detection effect that can be achieved when detecting the first account.

[0122] Specifically, in response to an indicator recommendation operation triggered for the displayed sample account distribution curve, the computer device respectively obtains the account distribution numbers of the first sample accounts corresponding to each indicator value according to the first sample account distribution curve, and respectively obtains the account distribution numbers of the second sample accounts corresponding to each indicator value based on the second sample account distribution curve. Then, based on the account distribution numbers of the first sample accounts under each indicator value and the account distribution numbers of the second sample accounts under each indicator value, it determines the detection effect values that can be achieved when each indicator value is used to detect the first sample accounts.

[0123] In one embodiment, the process by which the computer device determines the detection effect values corresponding to each indicator value when detecting the first sample accounts based on the account distribution numbers specifically includes: calculating the first hit rate corresponding to each indicator value when detecting the first sample accounts according to the account distribution numbers; and determining the detection effect values corresponding to each indicator value when detecting the first sample accounts based on the differences between the first hit rates corresponding to adjacent indicator values.

[0124] Specifically, the steps for the computer device to calculate the first hit rate corresponding to each indicator value when detecting the first sample accounts according to the account distribution numbers include: for any indicator value, determining the first sample hit volume and the second sample hit volume that match the indicator value according to the account distribution numbers, and calculating the first hit rate corresponding to the indicator value when detecting the first sample accounts based on the first sample hit volume and the second sample hit volume.

[0125] Among them, the hit volume of the first sample accounts is the number of true first sample accounts in the first sample accounts detected based on the metric value, and the hit volume of the second sample accounts is the number of true second sample accounts in the first sample accounts detected based on the metric value. For example, if the preset detection rule is to detect accounts with a metric value not less than a certain value, then for each metric value, the sample accounts in the resource transfer data that are not less than this metric value are determined as the first sample accounts. Specifically, the account distribution numbers of the first sample accounts corresponding to each other metric value not less than this metric value can be accumulated to obtain the first sample hit volume of the true first sample accounts that are hit, and the account distribution numbers of the second sample corresponding to each other metric value not less than this metric value are accumulated to obtain the second sample hit volume of the true second sample accounts that are hit.

[0126] In one embodiment, the process by which the computer device calculates the first hit rate when detecting the first sample accounts corresponding to this metric value based on the first sample hit volume and the second sample hit volume can be as follows: for any metric value under the metric to be detected, the first sample hit volume and the second sample hit volume corresponding to this metric value are input into formula (3) to calculate the first hit rate of this metric value:

[0127]

[0128] Among them, m i is the first hit rate corresponding to the i-th metric value, S i(命.白) is the second sample hit volume corresponding to the i-th metric value, S i(命.黑) is the first sample hit volume corresponding to the i-th metric value.

[0129] In one embodiment, after the computer device calculates the first hit rate corresponding to each metric value, it inputs the first hit rates of any two adjacent metric values into formula (4) to calculate the difference between the first hit rates corresponding to this adjacent metric value:

[0130] Δm i =m i -m i+1 (4)

[0131] Among them, Δm i is the difference in the first hit rate corresponding to the i-th metric value, m i is the first hit rate corresponding to the i-th metric value, m i+1 is the first hit rate corresponding to the i + 1-th metric value.

[0132] As an example to illustrate the above embodiment, refer to Figure 4 , Figure 4The abscissa corresponding to the intersection point of the dotted line 402 and the first sample distribution curve is the i-th index value, and the ordinate corresponding to the intersection point of the dotted line 402 and the first sample distribution curve is the account distribution number of the first sample account corresponding to the i-th index value. The ordinate corresponding to the intersection point of the dotted line 402 and the second sample distribution curve is the account distribution number of the second sample account corresponding to the i-th index value. If the preset detection rule is to detect accounts with index values not less than, then for the i-th index value, the corresponding first sample hit count is, Figure 4 the accumulation of the account distribution numbers of the first sample accounts corresponding to each index value on the right side of the dotted line 402, and the corresponding second sample hit count is Figure 4 the accumulation of the account distribution numbers of the second sample accounts corresponding to each index value on the right side of the dotted line 402; Figure 4 The abscissa corresponding to the intersection point of the dotted line 404 and the first sample distribution curve is the (i + 1)-th index value, and the ordinate corresponding to the intersection point of the dotted line 404 and the first sample distribution curve is the account distribution number of the first sample account corresponding to the (i + 1)-th index value. The ordinate corresponding to the intersection point of the dotted line 404 and the second sample distribution curve is the account distribution number of the second sample account corresponding to the (i + 1)-th index value. If the preset detection rule is to detect accounts with index values not less than, then for the (i + 1)-th index value, the corresponding first sample hit count is, Figure 4 the accumulation of the account distribution numbers of the first sample accounts corresponding to each index value on the right side of the dotted line 404, and the corresponding second sample hit count is Figure 4 the accumulation of the account distribution numbers of the second sample accounts corresponding to each index value on the right side of the dotted line 404. After the computer device calculates the first hit rates of each index value based on the first sample hit counts and second sample hit counts corresponding to each index value, for the i-th index value, it calculates the difference between its first hit rate and the first hit rate of the adjacent (i + 1)-th index value to obtain the first hit rate difference corresponding to the i-th index value.

[0133] In one embodiment, after the computer device calculates the differences between the first hit rates corresponding to each adjacent index value, it directly determines the first hit rate differences corresponding to each index value as the detection effect values when detecting the first sample accounts corresponding to the respective index values.

[0134] Specifically, after the computer device obtains the first hit rate differences corresponding to each index value, it inputs the first hit rate differences into formula (5) to obtain the detection effect values when detecting the first sample accounts corresponding to each index value:

[0135] P i =Δm i (5)

[0136] where Pi is the detection effect value corresponding to the i-th index value, Δm i is the first hit rate difference corresponding to the i-th index value.

[0137] In the above embodiment, the computer device calculates the first hit rate when detecting the first sample account corresponding to each index value according to the account distribution number, and determines the detection effect value when detecting the first sample account corresponding to each index value based on the difference between the first hit rates corresponding to adjacent index values, so that the index value of the first account detection with the best detection effect can be determined based on the detection effect value, avoiding relying on the preferences of the evaluators to determine the target index value and ensuring the consistency of the identification criteria for suspicious resource transfer accounts.

[0138] In another embodiment, the process of the computer device determining the detection effect value when detecting the first sample account corresponding to each index value based on the account distribution number specifically includes: calculating the difference in the first sample hit quantity when detecting the first sample account corresponding to adjacent index values according to the account distribution number of the first sample account; calculating the difference in the second sample hit quantity when detecting the first sample account corresponding to adjacent index values according to the account distribution number of the second sample account; calculating the detection effect value when detecting the first sample account corresponding to each index value based on the difference in the first sample hit quantity and the difference in the second sample hit quantity.

[0139] Specifically, after the computer device obtains the account distribution numbers of the first sample account under each index value and the account distribution numbers of the second sample account under each index value, according to the preset detection rules, it determines the first sample hit quantity and the second sample hit quantity corresponding to each index value, calculates the difference in the first sample hit quantity and the difference in the second sample hit quantity corresponding to adjacent index values, and calculates the detection effect value when detecting the first sample account corresponding to each index value based on the difference in the first sample hit quantity and the difference in the second sample hit quantity.

[0140] In one embodiment, after the computer device determines the first sample hit quantity corresponding to each index value, it inputs the first sample hit quantities of any two adjacent index values into formula (6) to calculate the difference in the first sample hit quantity corresponding to the adjacent index values:

[0141] ΔS i(命.黑) = S i(命.黑) - S i+1(命.黑) (6)

[0142] where, ΔS i(命.黑) is the difference in the first sample hit quantity corresponding to the i-th index value, S i(命.黑)i is the first sample hit quantity corresponding to the i-th index value, S i+1(命.黑) is the first sample hit quantity corresponding to the i+1-th index value.

[0143] In one embodiment, after the computer device determines the second sample hit count corresponding to each metric value, it inputs the second sample hit counts of any two adjacent metric values into formula (7) to calculate the difference in the second sample hit counts corresponding to the adjacent metric values:

[0144] ΔS i(命.白) =S i(命.白) -S i+1(命.白) (7)

[0145] where ΔS i(命.白) is the difference in the second sample hit counts corresponding to the i-th metric value, S i(命.白) is the second sample hit count corresponding to the i-th metric value, and S i+1(命.白) is the second sample hit count corresponding to the (i + 1)-th metric value.

[0146] In one embodiment, after the computer device calculates the differences in the first sample hit counts and the differences in the second sample hit counts corresponding to adjacent metric values, it inputs the calculated differences in the first sample hit counts and the differences in the second sample hit counts into formula (8) to calculate the detection effect values corresponding to each metric value:

[0147]

[0148] where P i is the detection effect value corresponding to the i-th metric value, ΔS i(命.白) is the difference in the second sample hit counts corresponding to the i-th metric value, and ΔS i(命.黑) is the difference in the first sample hit counts corresponding to the i-th metric value.

[0149] As an example to illustrate the above embodiment, referring to Figure 4 , if the preset detection rule is to detect accounts with metric values not less than, then for the i-th metric value, the first sample hit count corresponding to it is the sum of the account distribution numbers of the first sample accounts corresponding to each metric value on the right side of the dotted line 402 in Figure 4 , and the second sample hit count corresponding to it is Figure 4 the sum of the account distribution numbers of the second sample accounts corresponding to each metric value on the right side of the dotted line 402 in Figure 4 ; then for the (i + 1)-th metric value, the first sample hit count corresponding to it is the sum of the account distribution numbers of the first sample accounts corresponding to each metric value on the right side of the dotted line 404 in Figure 4 , and the second sample hit count corresponding to it is i, the account distribution number of the corresponding second sample account is c i , then the difference in the first sample hit volume between the i-th index value and the i+1-th index value is b i , the difference in the second sample hit volume is c i , then the detection effect value corresponding to the i-th index value can be calculated by formula (9):

[0150]

[0151] Among them, P i is the detection effect value corresponding to the i-th index value, b i is the account distribution number of the first sample account corresponding to the i-th index value, c i is the account distribution number of the second sample account corresponding to the i-th index value.

[0152] In the above embodiment, the computer device calculates the difference in the first sample hit volume and the difference in the second sample hit volume when detecting the first sample account corresponding to each adjacent index value according to the account distribution number, and calculates the detection effect value when detecting the first sample account corresponding to each index value based on the difference in the first sample hit volume and the difference in the second sample hit volume, so that the index value of the first account detection with the best detection effect can be determined based on the detection effect value, avoiding determining the target index value depending on the preference of the evaluator and ensuring the consistency of the identification criteria for suspicious resource transfer accounts.

[0153] S206, obtaining the effect change amount based on the difference between the detection effect values corresponding to each adjacent index value.

[0154] Among them, the effect change amount is used to characterize the change situation of the detection effect of any index value relative to its adjacent index value.

[0155] Specifically, after the computer device calculates the detection effect values corresponding to each index value, for any one index value, it calculates the difference between the detection effect value of this index value and the detection effect value of the adjacent index value, and determines the calculated difference as the effect change amount of this index value.

[0156] In one embodiment, after the computer device obtains the detection effect values corresponding to each index value, it inputs the obtained detection effect values into formula (10) to obtain the effect change amount corresponding to each index value:

[0157] ΔP i =P i -P i-1 (10)

[0158] Among them, ΔP i is the effect change amount corresponding to the i-th index value, Pi is the detection effect value corresponding to the i-th index value, P i-1 is the detection effect value corresponding to the (i - 1)-th index value.

[0159] S208. Determine the target index value for detecting the first account according to the change in effect.

[0160] In one embodiment, after calculating the change in effect corresponding to each index value, the computer device screens out the index value with the smallest change in effect from each index value, and determines the index value with the smallest change in effect as the target index value for detecting the first account.

[0161] Specifically, the computer device screens out the index values with a negative change in effect from each index value, then screens out the index value with the smallest value of the change in effect from the index values with a negative change in effect, and determines the index value with the smallest change in effect as the target index value for detecting the first account.

[0162] In one embodiment, after calculating the change in effect corresponding to each index value, the computer device calculates the change rate of effect for each index value based on the change in effect, and determines the target index value for detecting the first account according to the change rate of effect.

[0163] Specifically, after calculating the change rate of effect for each index value, the computer device screens out the index value with the smallest change rate of effect from each index value, and determines the index value with the smallest change rate of effect as the target index value for detecting the first account. For example, the computer device screens out the index values with a negative change rate of effect from each index value, then screens out the index value with the smallest value of the change rate of effect from the index values with a negative change rate of effect, and determines the index value with the smallest change rate of effect as the target index value for detecting the first account.

[0164] In one embodiment, the computer device inputs the change in effect corresponding to each obtained index value into formula (11) to calculate the change rate of effect for each index value:

[0165]

[0166] where, D i is the change rate of effect corresponding to the i-th index value, ΔP i is the change in effect corresponding to the i-th index value, P i is the detection effect value corresponding to the i-th index value, P i-1 is the detection effect value corresponding to the (i - 1)-th index value.

[0167] S210. Display the target index value as a recommended result.

[0168] Specifically, after the computer device determines the target metric value for detecting the first account, it determines the target metric value as the recommended result corresponding to the metric value recommendation operation and displays the recommended result.

[0169] Among them, the display of the target metric value can be directly displayed in numerical form at a specified position, or can be marked and displayed at the abscissa corresponding to the target metric value. For example Figure 3 in, the computer device responds to the trigger operation of the "recommended metric value" button, determines the target metric value for detecting the first account, and displays the target metric value as the recommended result above the horizontal line on the right side of the "selected metric value".

[0170] For the above target metric value determination method, after the computer device displays the sample account distribution curves of the first sample account and the second sample account under the to-be-detected metric respectively, in response to the triggered metric value recommendation operation, it sequentially obtains the account distribution numbers of the first sample account and the second sample account at each metric value of the to-be-detected metric based on the sample account distribution curve, and determines the detection effect value of the first sample account when it is at each metric value based on the account distribution number. Based on the difference between the detection effect values corresponding to each adjacent metric value, the effect change amount is obtained. Furthermore, according to the determined effect change amount, the target metric value for detecting the first account is further determined, and the target metric value is displayed as the recommended result, so that the evaluation personnel can determine the suspicious resource accounts based on the target metric value, and then can judge whether the numerical resource flow and transfer behavior is safe and legal, avoiding relying on the preferences of the evaluation personnel to determine the target metric value, ensuring the consistency of the identification criteria for suspicious resource transfer accounts, and thus improving the identification effect of the safety and legality of the numerical resource flow and transfer behavior.

[0171] In one embodiment, after the computer device determines the target metric value for detecting the first account, it can also display the first target hit rate and the first target coverage rate corresponding to the target metric value, which specifically includes the following steps: determining the first candidate metric value interval matching the target metric value; calculating the first target hit rate and the first target coverage rate for detecting the first sample account corresponding to the target metric value based on the account distribution numbers of the first sample account and the second sample account within the first candidate metric value interval; displaying the first target hit rate and the first target coverage rate.

[0172] Among them, the first candidate index value range is the index value range hit when using the target index value to detect the first sample account. It can be understood that the first candidate index value range is the index value range determined based on the target index value and the preset detection rule. For example, if the preset detection rule is to detect accounts with index values not less than a certain value, then the range from not less than the target index value and less than or equal to the maximum index value of the index to be detected is determined as the first candidate index value range.

[0173] Specifically, after the computer device determines the first candidate index value range that matches the target index value, it accumulates the account distribution numbers of the first sample accounts corresponding to each index value in the first candidate index value range to obtain the first target first sample hit quantity of the first sample accounts, accumulates the account distribution numbers of the second sample accounts corresponding to each index value in the first candidate index value range to obtain the first target second sample hit quantity of the second sample accounts, and calculates the first target hit rate corresponding to the target index value based on the first target first sample hit quantity and the first target second sample hit quantity; in addition, the computer device obtains the account distribution numbers of the first sample accounts corresponding to each index value in the index value range corresponding to the sample distribution curve, accumulates the obtained account distribution numbers of the first sample accounts to obtain the total quantity of the first sample accounts, and calculates the first target coverage rate corresponding to the target index value based on the first target first sample hit quantity and the total quantity of the first sample accounts.

[0174] Among them, the first target hit rate can be obtained by inputting the first target first sample hit quantity and the first target second sample hit quantity into formula (1) for calculation, and the first target coverage rate can be obtained by inputting the first target first sample hit quantity and the total quantity of the first sample accounts into formula (2) for calculation.

[0175] In the above embodiment, the computer device determines the first candidate index value range that matches the target index value, calculates and displays the first target hit rate and the first target coverage rate for detecting the first sample accounts corresponding to the target index value based on the account distribution numbers of the first sample accounts and the second sample accounts within the first candidate index value range, enabling the evaluator to intuitively see the detection effect that can be achieved by the target index value, so that the evaluator can determine suspicious resource accounts based on the target index value, and further can judge whether the numerical resource flow and transfer behavior is safe and legal.

[0176] In one embodiment, the computer device displays the sample distribution curve in the distribution map, and the above method for determining the target index value further includes the following steps: displaying the full - quantity account distribution curve of the full - quantity accounts under the index to be detected in the distribution map; in response to the triggered index value recommendation operation, sequentially obtaining the full - quantity account distribution numbers of the full - quantity accounts at each index value of the index to be detected according to the full - quantity account distribution curve.

[0177] Among them, the full - volume accounts can be the historical accounts corresponding to the historical resource transfer data or the to - be - detected accounts corresponding to the to - be - detected resource transfer data. The full - volume account distribution curve refers to the curve determined by taking different index values as the abscissa and the frequencies of the full - volume accounts appearing at each index value as the ordinate under the to - be - detected index.

[0178] In one embodiment, the computer device obtains the full - volume accounts corresponding to the historical resource transfer data or the to - be - detected resource transfer data, and based on the resource transfer data corresponding to each full - volume account under different to - be - detected indexes, determines the different full - volume account distribution curves of all the full - volume accounts under different to - be - detected indexes.

[0179] Among them, the resource transfer data includes the resource transfer data under different indexes, such as the statistical data of the resource transfer amounts of each sample account corresponding to the resource transfer amount index, the statistical data of the resource transfer times of each sample account corresponding to the resource transfer times index, and the statistical data of the resource transfer objects of each sample account corresponding to the resource transfer object number index.

[0180] Figure 5 It is a schematic diagram of the distribution map in an embodiment. The sample account distribution curve and the full - volume account distribution curve are shown in the figure. Among them, the curve corresponding to the dots is the second sample account distribution curve, the curve corresponding to the squares is the first sample account distribution curve, and the curve with only lines is the full - volume account distribution curve. Each distribution curve shown in this distribution map is the sample account distribution curve under the resource transfer object number index. Figure 5 In it, the abscissa is the quantity of the resource transfer object number, and the ordinate is the quantity of the accounts, which characterizes the distribution of the first sample account, the second sample account, and the full - volume account respectively in the dimension of the resource transfer object number index.

[0181] In one embodiment, in response to the index value recommendation operation triggered in the distribution map, the computer device sequentially obtains the full - volume account distribution numbers of the full - volume accounts at each index value of the to - be - detected index according to the full - volume account distribution curve, and based on the account distribution numbers of the first sample account and the second sample account and the full - volume account distribution numbers, determines the detection effect values when detecting the first sample account corresponding to each index value.

[0182] Specifically, in response to an indicator recommendation operation triggered for the displayed distribution map, the computer device respectively obtains the account distribution numbers of the first sample accounts corresponding to each indicator value according to the first sample account distribution curve, respectively obtains the account distribution numbers of the second sample accounts corresponding to each indicator value based on the second sample account distribution curve, and sequentially obtains the full - volume account distribution numbers of the full - volume accounts at each indicator value of the to - be - measured indicator according to the full - volume account distribution curve. Then, based on the account distribution numbers of the first sample accounts, the second sample accounts, and the full - volume account distribution numbers, it determines the detection effect values when detecting the first sample accounts corresponding to each indicator value.

[0183] In the above - mentioned embodiment, the computer device displays the full - volume account distribution curve of the full - volume accounts under the to - be - measured indicator in the distribution map, so as to, in response to the triggered indicator value recommendation operation, obtain the full - volume account distribution numbers of the full - volume accounts, and further, based on the account distribution numbers of the first sample accounts, the second sample accounts, and the full - volume account distribution numbers, determine the detection effect values when detecting the first sample accounts corresponding to each indicator value, further improving the accuracy of the detection effect values corresponding to each indicator value. Thus, it can determine the indicator value with the detection effect closest to the actual detection situation based on the detection effect value, improving the accuracy of determining the target indicator value.

[0184] In one embodiment, as Figure 6 shown, the process by which the computer device determines the detection effect values when detecting the first sample accounts corresponding to each indicator value based on the account distribution numbers of the first sample accounts, the second sample accounts, and the full - volume account distribution numbers includes the following steps:

[0185] S602, calculate the first hit rate when detecting the first sample accounts corresponding to each indicator value according to the account distribution numbers of the first sample accounts and the second sample accounts.

[0186] Specifically, for any indicator value, the computer device determines the first sample hit quantity matching the indicator value according to the account distribution number of the first sample accounts, determines the second sample hit quantity matching the indicator value according to the account distribution number of the second sample accounts, and calculates the first hit rate when detecting the first sample accounts corresponding to each indicator value according to the first sample hit quantity and the second sample hit quantity.

[0187] Among them, the process by which the computer device calculates the first hit rate when detecting the first sample accounts corresponding to the indicator value according to the first sample hit quantity and the second sample hit quantity can be that, for any indicator value under the to - be - detected indicator, the first sample hit quantity and the second sample hit quantity corresponding to the indicator value are input into formula (3) to calculate the detection effect value of the indicator value.

[0188] S604. Determine the difference in the total number of hits corresponding to each metric value based on the distribution of the total number of accounts at each metric value.

[0189] Among them, the difference in the total number of hits refers to the difference between the total number of hits corresponding to two adjacent metric values. The total number of hits is the number of total accounts determined to be the first type of account when detecting the total number of accounts based on the metric value. For example, if the preset detection rule is to detect accounts not less than the metric value, then for each metric value, the total accounts in the resource transfer data that are not less than the target metric value are determined as the first type of account. Specifically, it can be to accumulate the distribution numbers of the total accounts corresponding to each metric value not less than this metric value to obtain the total number of hits of the first type of accounts that are hit.

[0190] Specifically, after the computer device calculates the total number of hits corresponding to each metric value, it inputs the total number of hits of any two adjacent metric values into formula (12) to calculate the difference in the total number of hits corresponding to the adjacent metric values:

[0191] Δn i = n i - n i+1 (12)

[0192] Among them, Δn i is the difference in the total number of hits corresponding to the i-th metric value, n i is the total number of hits corresponding to the i-th metric value, n i+1 is the total number of hits corresponding to the (i + 1)-th metric value.

[0193] S606. Calculate the detection effectiveness value when detecting the first sample accounts corresponding to each metric value based on the difference between the first hit rates corresponding to adjacent metric values and the difference in the total number of hits.

[0194] In one embodiment, after the computer device calculates the first hit rate corresponding to each metric value, it uses formula (4) to calculate the difference between the first hit rates corresponding to adjacent metric values, that is, calculates the difference in the first hit rate corresponding to each metric value, and calculates the detection effectiveness value when detecting the first sample accounts corresponding to each metric value based on the difference in the first hit rate corresponding to each metric value and the difference in the total number of hits.

[0195] Specifically, after the computer device obtains the difference in the first hit rate and the difference in the total number of hits corresponding to each metric value, it inputs the difference in the first hit rate and the difference in the total number of hits into formula (13) to obtain the detection effectiveness value when detecting the first sample accounts corresponding to each metric value:

[0196]

[0197] where P i is the detection effect value corresponding to the i-th index value, and Δm i is the first hit rate difference corresponding to the i-th index value, and Δn i is the total hit volume difference corresponding to the i-th index value.

[0198] In the above embodiments, the computer device calculates the first hit rate and the total hit volume difference when detecting the first sample account corresponding to each index value according to the account distribution numbers of the first sample account and the second sample account, and the total account distribution number, and calculates the detection effect value when detecting the first sample account corresponding to each index value based on the difference between the first hit rates corresponding to adjacent index values and the total hit volume difference, further improving the accuracy of the detection effect value corresponding to each index value, so that the index value with the detection effect closest to the actual detection situation can be determined based on the detection effect value, improving the accuracy of determining the target index value.

[0199] In one embodiment, the process by which the computer device determines the detection effect value when detecting the first sample account corresponding to each index value based on the account distribution numbers of the first sample account and the second sample account, and the total account distribution number includes the following steps: calculating the first sample hit volume difference when detecting the first sample account corresponding to adjacent index values according to the account distribution number of the first sample account; calculating the second sample hit volume difference when detecting the first sample account corresponding to adjacent index values according to the account distribution number of the second sample account; determining the total hit volume difference corresponding to each index value according to the total account distribution number of the total accounts under each index value of the index to be measured; calculating the detection effect value when detecting the first sample account corresponding to each index value based on the first sample hit volume difference, the second sample hit volume difference, and the total hit volume difference.

[0200] Specifically, after the computer device obtains the first sample hit volume difference, the second sample hit volume difference, and the total hit volume difference corresponding to each index value, it inputs the first sample hit volume difference, the second sample hit volume difference, and the total hit volume difference into formula (14) to calculate the detection effect value corresponding to each index value:

[0201]

[0202] where P i is the detection effect value corresponding to the i-th index value, ΔS i(命.白) is the second sample hit volume difference corresponding to the i-th index value, ΔS i(命.黑) is the first sample hit volume difference corresponding to the i-th index value, and Δn i is the total hit volume difference corresponding to the i-th index value.

[0203] As an example, the above embodiments are described with reference to 7. Figure 7 The abscissa corresponding to the intersection point of the dotted line 702 and the first sample distribution curve is the i-th index value, and the ordinate corresponding to the intersection point of the dotted line 702 and the first sample distribution curve is the account distribution number of the first sample account corresponding to the i-th index value. The ordinate corresponding to the intersection point of the dotted line 702 and the second sample distribution curve is the account distribution number of the second sample account corresponding to the i-th index value. The ordinate corresponding to the intersection point of the dotted line 702 and the full-scale account distribution curve is the account distribution number of the full-scale account corresponding to the i-th index value. Figure 7 The abscissa corresponding to the intersection point of the dotted line 704 and the first sample distribution curve is the (i + 1)-th index value. The ordinate corresponding to the intersection point of the dotted line 404 and the first sample distribution curve is the account distribution number of the first sample account corresponding to the (i + 1)-th index value. The ordinate corresponding to the intersection point of the dotted line 404 and the second sample distribution curve is the account distribution number of the second sample account corresponding to the (i + 1)-th index value. The ordinate corresponding to the intersection point of the dotted line 704 and the full-scale account distribution curve is the account distribution number of the full-scale account corresponding to the (i + 1)-th index value. If the preset detection rule is to detect accounts with index values not less than, then for the i-th index value, the corresponding first sample hit volume is the sum of the account distribution numbers of the first sample accounts corresponding to each index value on the right side of the dotted line 702. The corresponding second sample hit volume is the sum of the account distribution numbers of the second sample accounts corresponding to each index value on the right side of the dotted line 702. The corresponding full-scale hit volume is the sum of the account distribution numbers of the full-scale accounts corresponding to each index value on the right side of the dotted line 702. Then for the (i + 1)-th index value, the corresponding first sample hit volume is the sum of the account distribution numbers of the first sample accounts corresponding to each index value on the right side of the dotted line 704 in the middle. The corresponding second sample hit volume is the sum of the account distribution numbers of the second sample accounts corresponding to each index value on the right side of the dotted line 704. The corresponding full-scale hit volume is the sum of the account distribution numbers of the full-scale accounts corresponding to each index value on the right side of the dotted line 704. Thus, it can be seen that if the account distribution number of the first sample account corresponding to the i-th index value is b i and the account distribution number of the second sample account corresponding to it is c i and the account distribution number of the full-scale account corresponding to it is a i then the difference in the first sample hit volume between the i-th index value and the (i + 1)-th index value is b i the difference in the second sample hit volume is c i and the difference in the full-scale hit volume is a i then the detection effect value corresponding to the i-th index value can be calculated by formula (15):

[0204]

[0205] Among them, P i is the detection effect value corresponding to the i-th index value, b i is the account distribution number of the first sample account corresponding to the i-th index value, c i is the account distribution number of the second sample account corresponding to the i-th index value, a i is the account distribution number of the full amount of accounts corresponding to the i-th index value.

[0206] In the above embodiment, the computer device calculates the difference in the number of hits of the first sample, the difference in the number of hits of the second sample, and the difference in the number of full - amount hits of each index value according to the account distribution numbers of the first sample account and the second sample account, and the full - amount account distribution number. And based on the difference in the number of hits of the first sample, the difference in the number of hits of the second sample, and the difference in the number of full - amount hits, it calculates the detection effect value when detecting the first sample account corresponding to each index value, further improving the accuracy of the detection effect value corresponding to each index value. Thus, it can determine the index value with the detection effect closest to the actual detection situation based on the detection effect value, improving the accuracy of determining the target index value.

[0207] In one embodiment, after the computer device determines the target index value for detecting the first account, it can also display the second target hit rate, the second target coverage rate, and the full - amount hit number corresponding to the target index value. The specific steps are as follows: determining a second candidate index value interval that matches the target index value; calculating the second target hit rate and the second target coverage rate for detecting the first sample account corresponding to the target index value based on the account distribution numbers of the first sample account and the second sample account within the second candidate index value interval; calculating the full - amount hit number corresponding to the target index value based on the account distribution number of the full - amount account within the second candidate index value interval; and displaying the second target hit rate, the second target coverage rate, and the full - amount hit number in the distribution diagram.

[0208] Among them, the second candidate index value interval is the index value interval hit when using the target index value to detect the first sample account. It can be understood that the second candidate index value interval is the index value interval determined based on the target index value and the preset detection rule. For example, if the preset detection rule is to detect accounts with index values not less than, then the interval range that is not less than the target index value and less than or equal to the maximum index value of the index to be detected is determined as the second candidate index value interval.

[0209] Specifically, after the computer device determines the second candidate index value interval that matches the target index value, it accumulates the account distribution numbers of the first sample accounts corresponding to each index value in the second candidate index value interval to obtain the second target first sample hit volume of the first sample accounts, accumulates the account distribution numbers of the second sample accounts corresponding to each index value in the second candidate index value interval to obtain the second target second sample hit volume of the second sample accounts, accumulates the full account distribution numbers of the full accounts corresponding to each index value in the second candidate index value interval to obtain the full hit volume of the full accounts, and calculates the second target hit rate corresponding to the target index value based on the second target first sample hit volume and the second target second sample hit volume; in addition, the computer device obtains the account distribution numbers of the first sample accounts corresponding to each index value in the index value interval corresponding to the sample distribution curve, accumulates the obtained account distribution numbers of the first sample accounts to obtain the total volume of the first sample accounts, and calculates the second target coverage rate corresponding to the target index value based on the second target first sample hit volume and the total volume of the first sample accounts.

[0210] Among them, the second target hit rate can be obtained by inputting the second target first sample hit volume and the second target second sample hit volume into formula (1) for calculation, and the second target coverage rate can be obtained by inputting the second target first sample hit volume and the total volume of the first sample accounts into formula (2) for calculation.

[0211] In the above embodiment, the computer device determines the second candidate index value interval that matches the target index value, and calculates and displays the second target hit rate, the second target coverage rate, and the full hit volume for detecting the first sample accounts corresponding to the target index value based on the account distribution numbers of the first sample accounts and the second sample accounts within the second candidate index value interval, and the full account distribution numbers of the full accounts within the second candidate index value interval, so that the evaluator can intuitively see the detection effect that can be achieved by the target index value, so that the evaluator can determine the suspicious resource accounts based on the target index value, and further can judge whether the numerical resource flow and transfer behavior is safe and legal.

[0212] In one embodiment, when the computer device displays the sample account distribution curve in the distribution map, it also displays a draggable index threshold line. When the displayed index threshold line is dragged, the computer device responds to the movement operation of the index threshold line triggered in the distribution map, and obtains the real-time index value that changes in real time during the movement of the index threshold line; determines the candidate real-time index value that matches the real-time index value; calculates the second hit rate and the second coverage rate for detecting the first sample accounts corresponding to the real-time index value based on the account distribution numbers of the first sample accounts and the second sample accounts corresponding to the candidate real-time index value; and displays the second hit rate and the second coverage rate in the distribution map.

[0213] Among them, the index threshold line is used to mark the corresponding index value at present, that is, the real-time index value. The candidate real-time index value refers to each index value in the index value range hit when detecting based on the real-time index value and the preset detection rules. For example, if the preset detection rule is to detect accounts with index values not less than a certain value, then each index value within the index value range that is not less than the target index value and less than or equal to the maximum index value of the index to be detected is determined as the candidate real-time index value.

[0214] Specifically, after the computer device determines the candidate real-time index value that matches the real-time index value, it accumulates the account distribution numbers of the first sample accounts corresponding to the candidate real-time index value to obtain the real-time first sample hit volume of the first sample accounts, accumulates the account distribution numbers of the second sample accounts corresponding to the candidate real-time index value to obtain the real-time second sample hit volume of the second sample accounts, and calculates the second hit rate corresponding to the real-time index value based on the real-time first sample hit volume and the real-time second sample hit volume; in addition, the computer device obtains the account distribution numbers of the first sample accounts corresponding to each index value in the index value range corresponding to the sample distribution curve, accumulates the obtained account distribution numbers of the first sample accounts to obtain the total amount of the first sample accounts, and calculates the second coverage rate corresponding to the real-time index value based on the real-time first sample hit volume and the total amount of the first sample accounts.

[0215] Among them, the second hit rate can be obtained by inputting the real-time first sample hit volume and the real-time second sample hit volume into formula (1) for calculation, and the second coverage rate can be obtained by inputting the real-time first sample hit volume and the total amount of the first sample accounts into formula (2) for calculation.

[0216] In the above embodiment, the computer device obtains the real-time index value that changes in real time during the movement of the index threshold line in the distribution diagram by responding to the movement operation of the index threshold line in the distribution diagram, determines the candidate real-time index value that matches the real-time index value, and calculates and displays the second hit rate and the second coverage rate for detecting the first sample accounts corresponding to the real-time index value based on the account distribution numbers of the first sample accounts and the second sample accounts corresponding to the candidate real-time index value, so that the evaluator can intuitively see the detection effects that can be achieved by each index value, so that the evaluator can independently select appropriate index values to identify network money laundering behaviors based on the detection effects that can be achieved by each index value.

[0217] In one embodiment, the computer device also displays the full amount account distribution curve of the full amount accounts under the index to be detected in the distribution diagram; and after determining the candidate real-time index value, calculates the full amount hit volume corresponding to the real-time index value based on the account distribution numbers of the full amount accounts corresponding to the candidate real-time index value; and displays the second hit rate, the second coverage rate and the full amount hit volume in the distribution diagram.

[0218] Specifically, after the computer device determines the candidate real-time metric values that match the real-time metric value, it accumulates the account distribution numbers of the first sample accounts corresponding to the candidate real-time metric values to obtain the real-time first sample hit volume of the first sample accounts, accumulates the account distribution numbers of the second sample accounts corresponding to the candidate real-time metric values to obtain the real-time second sample hit volume of the second sample accounts, and accumulates the full account distribution numbers of the full amount of accounts corresponding to the candidate real-time metric values to obtain the full amount hit volume of the full amount of accounts; and calculates the second hit rate corresponding to the real-time metric value based on the real-time first sample hit volume and the real-time second sample hit volume; in addition, the computer device obtains the account distribution numbers of the first sample accounts corresponding to each metric value in the metric value interval corresponding to the sample distribution curve, and accumulates the obtained account distribution numbers of the first sample accounts to obtain the total amount of the first sample accounts, and calculates the second coverage rate corresponding to the real-time metric value based on the real-time first sample hit volume and the total amount of the first sample accounts, and then displays the calculated second hit rate, second coverage rate, and full amount hit volume in the distribution diagram.

[0219] As an example, the above embodiment is described. As Figure 8 shown in the distribution diagram, Figure 8 the dashed line 802 in it is the metric threshold line that can be dragged. The user can set the real-time metric value by dragging this metric threshold line, or enter the set real-time metric value above the horizontal line on the right side of "Selected Metric Value" in Figure 8 . When the computer device responds to the operation of triggering the movement of the metric threshold line in the distribution diagram, it obtains the real-time metric value that changes in real time during the movement of the metric threshold line, and displays the obtained real-time metric value in "Selected Metric Value" in Figure 8 ; when the computer device responds to the operation of inputting the real-time metric value and obtains the input real-time metric value, it moves the metric threshold line displayed in the distribution diagram to the position corresponding to the real-time metric value. After the computer device obtains the real-time metric value, it determines the candidate real-time metric values that match the real-time metric value; based on the account distribution numbers of the first sample accounts and the second sample accounts corresponding to the candidate real-time metric values, it calculates the second hit rate and the second coverage rate for detecting the first sample accounts corresponding to the real-time metric value; based on the account distribution numbers of the full amount of accounts corresponding to the candidate real-time metric values, it calculates the full amount hit volume corresponding to the real-time metric value; and displays the second hit rate, second coverage rate, and full amount hit volume in the distribution diagram.

[0220] In the above embodiments, the computer device obtains the real-time metric values that change in real time during the movement of the metric threshold line by responding to the movement operation of the metric threshold line in the trigger distribution diagram, determines the candidate real-time metric values that match the real-time metric values, and calculates and displays the second hit rate, the second coverage rate, and the full amount hit volume for detecting the first sample accounts corresponding to the real-time metric values based on the account distribution numbers of the first sample accounts and the second sample accounts corresponding to the candidate real-time metric values, as well as the account distribution numbers of all accounts, so that the evaluator can intuitively see the detection effects that can be achieved by each metric value, so that the evaluator can autonomously select appropriate metric values based on the detection effects that can be achieved by each metric value to identify network money laundering behaviors.

[0221] In one embodiment, before the computer device displays the sample account distribution curves of the first sample accounts and the second sample accounts under the metrics to be measured, it may also pre-obtain the first sample accounts and the second sample accounts. The process of obtaining the first sample accounts and the second sample accounts includes the following steps: extracting sample accounts from all accounts; obtaining the interaction data corresponding to the sample accounts under the metrics to be measured; and marking the sample accounts based on the interaction data to obtain the first sample accounts and the second sample accounts.

[0222] Among them, the interaction data is the resource transfer data of the sample accounts corresponding to the metrics to be detected. For example, if the metric to be detected is the resource transfer amount, the interaction data is the statistical data of the resource transfer amounts of the sample accounts; if the metric to be detected is the resource transfer frequency, the interaction data is the statistical data of the resource transfer frequencies of the sample accounts; if the metric to be detected is the number of resource transfer objects, the interaction data is the statistical data of the resource transfer objects of the sample accounts.

[0223] Specifically, after the computer device obtains all accounts, it extracts a preset proportion of sample accounts from all accounts and marks each sample account according to the interaction data of the sample accounts, so as to obtain the first sample accounts and the second sample accounts. Marking the sample accounts can be manual marking or marking the sample accounts using a pre-trained sample recognition model. The sample recognition model can be a machine learning model. For example, RandomForest, GBM, AdaBoost, LightGBM, or XGBoost is used as the base learner to design a sample recognition model based on the majority voting rule.

[0224] In the above embodiments, the computer device extracts sample accounts from all accounts, obtains the interaction data corresponding to the sample accounts under the to-be-detected indicators, and marks the sample accounts based on the interaction data, so as to obtain the first sample accounts and the second sample accounts, so that the evaluator can determine the target indicator value based on the first sample accounts and the second sample accounts, and then determine the suspicious resource accounts through the determined target indicator value, and further can determine whether the numerical resource flow and transfer behavior is safe and legal, avoiding determining the target indicator value depending on the preference of the evaluator, ensuring the consistency of the identification criteria for suspicious resource transfer accounts, and further improving the identification effect of the safety and legality of the numerical resource flow and transfer behavior.

[0225] In one embodiment, as Figure 9 shown, a method for determining a target indicator value is provided. Taking the computer device (terminal or server) in Figure 1 as an example, the method includes the following steps:

[0226] S902, display the sample account distribution curves of the first sample accounts and the second sample accounts respectively under the to-be-detected indicators in the distribution diagram, and display the all-account distribution curve of all accounts under the to-be-detected indicators in the distribution diagram.

[0227] S904, in response to the triggered indicator value recommendation operation, sequentially obtain the account distribution numbers of the first sample accounts and the second sample accounts at each indicator value of the to-be-detected indicator according to the sample account distribution curve, and sequentially obtain the all-account distribution numbers of all accounts at each indicator value of the to-be-detected indicator according to the all-account distribution curve.

[0228] S906, based on the account distribution numbers and the all-account distribution numbers, determine the detection effect values corresponding to each indicator value when detecting the first sample accounts.

[0229] In one embodiment, S906 includes: calculating the first hit rate corresponding to each indicator value when detecting the first sample accounts according to the account distribution numbers; determining the all-account hit quantity difference corresponding to each indicator value according to the all-account distribution numbers of all accounts at each indicator value; calculating the detection effect values corresponding to each indicator value when detecting the first sample accounts based on the difference between the first hit rates corresponding to adjacent indicator values and the all-account hit quantity difference.

[0230] In another embodiment, S906 includes: calculating the difference in the first sample hit volume when detecting the first sample account corresponding to each adjacent index value according to the account distribution number of the first sample account; calculating the difference in the second sample hit volume when detecting the first sample account corresponding to each adjacent index value according to the account distribution number of the second sample account; determining the difference in the full volume hit volume corresponding to each index value according to the full volume account distribution number of the full volume account under each index value of the to-be-detected index; calculating the detection effect value corresponding to each index value when detecting the first sample account based on the difference in the first sample hit volume, the difference in the second sample hit volume, and the difference in the full volume hit volume.

[0231] S908, obtaining the amount of change in the effect based on the difference between the detection effect values corresponding to each adjacent index value.

[0232] S910, determining the target index value for detecting the first account according to the amount of change in the effect.

[0233] S912, displaying the target index value as a recommended result.

[0234] This application also provides an application scenario that applies the above method for determining the target index value. Specifically, the application of the method for determining the target index value in this application scenario is as follows:

[0235] When an evaluator independently determines the target value, it is often unable to make an appropriate balance between the hit rate and the coverage rate. Often, the index value with the highest hit rate is selected as the target index value. However, the quality preservation value with the highest hit rate often corresponds to a very low coverage rate and cannot achieve a good detection effect. To achieve a balance between the coverage rate and the hit rate, refer to Figure 7 , the index value with the highest hit rate can be determined first, and the account distribution number b of the first sample account corresponding to other index values is sequentially obtained along the direction of decreasing index value i , the account distribution number c of the second sample account i and the account distribution number c of the full volume account i , and then the detection effect value P corresponding to each index value is calculated through formula (15) i , and then the effect variable ΔP corresponding to each index value is calculated through formula (10) i , and the target index value with the smallest amount of change in the effect is selected as the recommended result for output.

[0236] It should be understood that although Figure 2 , Figure 6 and Figure 9The steps in the flowchart are shown in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 、 Figure 6 and Figure 9 At least some of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turns with at least some of the steps or stages in other steps.

[0237] In one embodiment, as Figure 10 shown, a target index value determination device is provided. This device can be a software module, a hardware module, or a combination of both to form a part of a computer device. Specifically, the device includes: a distribution curve display module 1002, an effect value determination module 1004, a change amount determination module 1006, a target index value calculation module 1008, and a result display module 1010, where:

[0238] The distribution curve display module 1002 is used to display the sample account distribution curves of the first sample account and the second sample account under the to-be-detected index respectively.

[0239] The effect value determination module 1004 is used to, in response to a triggered index value recommendation operation, sequentially obtain the account distribution numbers of the first sample account and the second sample account at each index value of the to-be-detected index based on the sample account distribution curve, and determine the detection effect values corresponding to each index value when detecting the first sample account based on the account distribution numbers.

[0240] The change amount determination module 1006 is used to obtain an effect change amount based on the difference between the detection effect values corresponding to adjacent index values.

[0241] The target index value calculation module 1008 is used to determine the target index value for detecting the first account according to the effect change amount.

[0242] The result display module 1010 is used to display the target index value as a recommended result.

[0243] In one embodiment, the to-be-detected index includes at least one of the resource transfer amount, the resource transfer times, and the resource transfer object number.

[0244] In the above embodiments, after presenting the sample account distribution curves of the first sample account and the second sample account respectively under the to-be-detected indicator, in response to the triggered indicator value recommendation operation, the account distribution numbers of the first sample account and the second sample account at each indicator value of the to-be-detected indicator are sequentially obtained according to the sample account distribution curves, and the detection effect values of the first sample account at each indicator value are determined based on the account distribution numbers. Based on the differences between the detection effect values corresponding to adjacent indicator values, the effect change amount is obtained. Furthermore, according to the determined effect change amount, the target indicator value for detecting the first account is further determined and presented as the recommendation result, so that the evaluation personnel can determine the suspicious resource accounts based on the target indicator value, and then can determine whether the numerical resource flow and transfer behavior is safe and legal, avoiding determining the target indicator value depending on the preferences of the evaluation personnel, ensuring the consistency of the identification criteria for suspicious resource transfer accounts, and thus improving the identification effect of the safety and legality of the numerical resource flow and transfer behavior.

[0245] In one embodiment, the effect value determination module 1004 is further configured to:

[0246] According to the account distribution numbers, calculate the first hit rates when detecting the first sample account corresponding to each indicator value;

[0247] Based on the differences between the first hit rates corresponding to adjacent indicator values, determine the detection effect values when detecting the first sample account corresponding to each indicator value.

[0248] In the above embodiments, according to the account distribution numbers, calculate the first hit rates when detecting the first sample account corresponding to each indicator value, and based on the differences between the first hit rates corresponding to adjacent indicator values, determine the detection effect values when detecting the first sample account corresponding to each indicator value, so that the indicator value with the best detection effect for detecting the first account can be determined based on the detection effect values, avoiding determining the target indicator value depending on the preferences of the evaluation personnel, and ensuring the consistency of the identification criteria for suspicious resource transfer accounts.

[0249] In one embodiment, the effect value determination module 1004 is further configured to:

[0250] According to the account distribution numbers of the first sample account, calculate the difference in the first sample hit amounts when detecting the first sample account corresponding to adjacent indicator values;

[0251] According to the account distribution numbers of the second sample account, calculate the difference in the second sample hit amounts when detecting the first sample account corresponding to adjacent indicator values;

[0252] Based on the difference in the first sample hit amounts and the difference in the second sample hit amounts, calculate the detection effect values when detecting the first sample account corresponding to each indicator value.

[0253] In the above embodiments, the computer device calculates the difference in the first sample hit count and the difference in the second sample hit count when detecting the first sample account corresponding to each adjacent index value according to the account distribution count, and calculates the detection effect value when detecting the first sample account corresponding to each index value based on the difference in the first sample hit count and the difference in the second sample hit count, so that the index value of the first account detection with the best detection effect can be determined based on the detection effect value, avoiding the determination of the target index value relying on the preferences of the evaluators and ensuring the consistency of the identification criteria for suspicious resource transfer accounts.

[0254] In one embodiment, the result display module 1010 is further configured to:

[0255] Determine the first candidate index value interval that matches the target index value;

[0256] Based on the account distribution counts of the first sample account and the second sample account within the first candidate index value interval, calculate the first target hit rate and the first target coverage rate for detecting the first sample account corresponding to the target index value;

[0257] Display the first target hit rate and the first target coverage rate.

[0258] In the above embodiments, by determining the first candidate index value interval that matches the target index value, calculating and displaying the first target hit rate and the first target coverage rate for detecting the first sample account corresponding to the target index value based on the account distribution counts of the first sample account and the second sample account within the first candidate index value interval, the evaluators can intuitively see the detection effect that can be achieved by the target index value, so that the evaluators can determine the suspicious resource accounts based on the target index value, and further can determine whether the numerical resource flow and transfer behaviors are safe and legal.

[0259] In the above embodiments, by determining the first candidate index value interval that matches the target index value, calculating and displaying the first target hit rate and the first target coverage rate for detecting the first sample account corresponding to the target index value based on the account distribution counts of the first sample account and the second sample account within the first candidate index value interval, the evaluators can intuitively see the detection effect that can be achieved by the target index value, so that the evaluators can determine the suspicious resource accounts based on the target index value, and further can determine whether the numerical resource flow and transfer behaviors are safe and legal.

[0260] In one embodiment, the sample account distribution curve is displayed in the distribution map; the distribution curve display module 1002 is further configured to:

[0261] Display the full - volume account distribution curve of the full - volume accounts under the index to be measured in the distribution map;

[0262] The effect value determination module 1004 is further configured to, in response to a triggered metric value recommendation operation, sequentially obtain the full-amount account distribution numbers of the full-amount accounts at each metric value of the to-be-detected metric according to the full-amount account distribution curve.

[0263] The effect value determination module 1004 is further configured to determine the detection effect values when detecting the first sample accounts corresponding to each metric value based on the account distribution numbers and the full-amount account distribution numbers.

[0264] In the above embodiments, by displaying the full-amount account distribution curve of the full-amount accounts at the to-be-detected metric in the distribution diagram, in response to a triggered metric value recommendation operation, the full-amount account distribution numbers of the full-amount accounts are obtained. Furthermore, based on the account distribution numbers of the first sample accounts and the second sample accounts, and the full-amount account distribution numbers, the detection effect values when detecting the first sample accounts corresponding to each metric value are determined, further improving the accuracy of the detection effect values corresponding to each metric value. Thus, the metric value with the detection effect closest to the actual detection situation can be determined based on the detection effect values, improving the accuracy of determining the target metric value.

[0265] In one embodiment, the effect value determination module 1004 is further configured to:

[0266] Calculate the first hit rates when detecting the first sample accounts corresponding to each metric value according to the account distribution numbers.

[0267] Determine the full-amount hit quantity differences corresponding to each metric value according to the full-amount account distribution numbers of the full-amount accounts at each metric value.

[0268] Calculate the detection effect values when detecting the first sample accounts corresponding to each metric value based on the differences between the first hit rates corresponding to adjacent metric values and the full-amount hit quantity differences.

[0269] In the above embodiments, according to the account distribution numbers of the first sample accounts and the second sample accounts, and the full-amount account distribution numbers, the first hit rates and the full-amount hit quantity differences when detecting the first sample accounts corresponding to each metric value are calculated, and based on the differences between the first hit rates corresponding to adjacent metric values and the full-amount hit quantity differences, the detection effect values when detecting the first sample accounts corresponding to each metric value are calculated, further improving the accuracy of the detection effect values corresponding to each metric value. Thus, the metric value with the detection effect closest to the actual detection situation can be determined based on the detection effect values, improving the accuracy of determining the target metric value.

[0270] In one embodiment, the effect value determination module 1004 is further configured to:

[0271] Calculate the first sample hit quantity differences when detecting the first sample accounts corresponding to adjacent metric values according to the account distribution numbers of the first sample accounts.

[0272] According to the account distribution numbers of the second sample accounts, calculate the difference in the second sample hit counts when detecting the first sample accounts corresponding to each adjacent index value;

[0273] According to the full - volume account distribution numbers of all full - volume accounts under each index value of the index to be measured, determine the difference in full - volume hit counts corresponding to each index value;

[0274] Based on the difference in the first sample hit counts, the difference in the second sample hit counts, and the difference in the full - volume hit counts, calculate the detection effect value corresponding to each index value when detecting the first sample accounts.

[0275] In the above - mentioned embodiments, according to the account distribution numbers of the first sample accounts and the second sample accounts, as well as the full - volume account distribution numbers, calculate the difference in the first sample hit counts, the difference in the second sample hit counts, and the difference in the full - volume hit counts corresponding to each index value, and based on the difference in the first sample hit counts, the difference in the second sample hit counts, and the difference in the full - volume hit counts, calculate the detection effect value corresponding to each index value when detecting the first sample accounts, further improving the accuracy of the detection effect values corresponding to each index value. Thus, the index value with the detection effect closest to the actual detection situation can be determined based on the detection effect value, improving the accuracy of the determination of the target index value.

[0276] In one embodiment, the result display module 1010 is further configured to:

[0277] Determine the second candidate index value interval that matches the target index value;

[0278] Based on the account distribution numbers of the first sample accounts and the second sample accounts within the second candidate index value interval, calculate the second target hit rate and the second target coverage rate for detecting the first sample accounts corresponding to the target index value;

[0279] Based on the account distribution numbers of all full - volume accounts within the second candidate index value interval, calculate the full - volume hit count corresponding to the target index value;

[0280] Display the second target hit rate, the second target coverage rate, and the full - volume hit count in the distribution graph.

[0281] In the above - mentioned embodiments, by determining the second candidate index value interval that matches the target index value, and based on the account distribution numbers of the first sample accounts and the second sample accounts within the second candidate index value interval, as well as the full - volume account distribution numbers of all full - volume accounts within the second candidate index value interval, calculate and display the second target hit rate, the second target coverage rate, and the full - volume hit count for detecting the first sample accounts corresponding to the target index value, enabling the evaluator to intuitively see the detection effect that can be achieved by the target index value, so that the evaluator can determine the suspicious resource accounts based on the target index value, and further can judge whether the numerical resource flow and transfer behavior is secure and legal.

[0282] In one embodiment, the sample account distribution curve is shown in the distribution graph; as Figure 11 shown, the device further includes: a real-time acquisition module 1012, a real-time determination module 1014, a real-time calculation module 1016, and a real-time display module 1018, wherein,

[0283] The real-time acquisition module 1012 is configured to, in response to a moving operation that triggers the movement of the metric threshold line in the distribution graph, acquire real-time metric values that change in real time during the movement of the metric threshold line;

[0284] The real-time determination module 1014 is configured to determine candidate real-time metric values that match the real-time metric values;

[0285] The real-time calculation module 1016 is configured to calculate a second hit rate and a second coverage rate for detecting the first sample account corresponding to the real-time metric value based on the account distribution numbers of the first sample account and the second sample account corresponding to the candidate real-time metric value;

[0286] The real-time display module 1018 is configured to display the second hit rate and the second coverage rate in the distribution graph.

[0287] In the above embodiment, by responding to a moving operation that triggers the movement of the metric threshold line in the distribution graph, acquiring real-time metric values that change in real time during the movement of the metric threshold line, determining candidate real-time metric values that match the real-time metric values, and calculating and displaying the second hit rate and the second coverage rate for detecting the first sample account corresponding to the real-time metric value based on the account distribution numbers of the first sample account and the second sample account corresponding to the candidate real-time metric value, the evaluator can intuitively see the detection effects that can be achieved by each metric value, so that the evaluator can independently select appropriate metric values based on the detection effects that can be achieved by each metric value to identify network money laundering behavior.

[0288] In one embodiment, the distribution curve display module 1002 is further configured to: display the full amount account distribution curve of the full amount of accounts under the metric to be measured in the distribution graph;

[0289] The real-time calculation module 1016 is further configured to calculate the full amount hit amount corresponding to the real-time metric value based on the account distribution number of the full amount of accounts corresponding to the candidate real-time metric value;

[0290] The real-time display module 1018 is further configured to display the second hit rate, the second coverage rate, and the full amount hit amount in the distribution graph.

[0291] In the above embodiments, by responding to the operation of triggering the movement of the index threshold line in the distribution diagram, obtaining the real-time index value that changes in real time during the movement of the index threshold line, determining the candidate real-time index value that matches the real-time index value, and based on the account distribution numbers of the first sample account and the second sample account corresponding to the candidate real-time index value, as well as the account distribution number of all accounts, calculating and displaying the second hit rate, the second coverage rate, and the full-volume hit volume for detecting the first sample account corresponding to the real-time index value, so that the evaluator can intuitively see the detection effects that can be achieved by each index value, so that the evaluator can autonomously select an appropriate index value based on the detection effects that can be achieved by each index value to identify network money laundering behavior.

[0292] In one embodiment, the apparatus further includes: a sample determination module, wherein,

[0293] The sample determination module is configured to extract sample accounts from all accounts; obtain the interaction data corresponding to the sample accounts under the index to be measured; and mark the sample accounts based on the interaction data to obtain a first sample account and a second sample account.

[0294] In the above embodiments, by extracting sample accounts from all accounts, obtaining the interaction data corresponding to the sample accounts under the index to be measured, and marking the sample accounts based on the interaction data, a first sample account and a second sample account can be obtained, so that the evaluator can determine the target index value based on the first sample account and the second sample account, and then determine the suspicious resource accounts through the determined target index value, and further determine whether the numerical resource flow and transfer behavior is safe and legal, avoiding relying on the preferences of the evaluator to determine the target index value, ensuring the consistency of the identification criteria for suspicious resource transfer accounts, and further improving the identification effect of the safety and legality of the numerical resource flow and transfer behavior.

[0295] For the specific limitations of the target index value determination device, reference can be made to the limitations of the target index value determination method in the above text, which will not be elaborated here. Each module in the above target index value determination device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0296] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 12As shown in the figure. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store resource transfer data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for determining a target metric value.

[0297] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as Figure 13 shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for determining a target metric value. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0298] Those skilled in the art can understand that Figure 12 or Figure 13 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0299] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in the above method embodiments.

[0300] In one embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by the processor, it implements the steps in the above method embodiments.

[0301] In one embodiment, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above method embodiments.

[0302] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application may include at least one of non-volatile and volatile memories. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0303] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0304] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for determining a target index value, characterized in that The method includes: Displaying the sample account distribution curves of the first sample account and the second sample account respectively under the index to be measured; the first sample account refers to a sample account with suspected resource transfer; the second sample account is a sample account without suspected resource transfer behavior; In response to the triggered index value recommendation operation, successively obtaining the account distribution numbers of the first sample account and the second sample account at each index value of the index to be measured according to the sample account distribution curve, and determining the detection effectiveness values corresponding to each index value for detecting the first sample account based on the account distribution numbers; Obtaining the effectiveness change amount based on the differences between the detection effectiveness values corresponding to adjacent index values; Determining the target index value for detecting the first account according to the effectiveness change amount; Displaying the target index value as the recommended result.

2. The method according to claim 1, wherein The determining the detection effectiveness values corresponding to each index value for detecting the first sample account based on the account distribution numbers includes: Calculating the first hit rates corresponding to each index value for detecting the first sample account according to the account distribution numbers; Determining the detection effectiveness values corresponding to each index value for detecting the first sample account based on the differences between the first hit rates corresponding to adjacent index values.

3. The method according to claim 1, characterized in that The determining the detection effectiveness values corresponding to each index value for detecting the first sample account based on the account distribution numbers includes: Calculating the difference in the first sample hit amounts corresponding to adjacent index values for detecting the first sample account according to the account distribution numbers of the first sample account; Calculating the difference in the second sample hit amounts corresponding to adjacent index values for detecting the first sample account according to the account distribution numbers of the second sample account; Calculating the detection effectiveness values corresponding to each index value for detecting the first sample account based on the difference in the first sample hit amount and the difference in the second sample hit amount.

4. The method according to any one of claims 1 to 3, characterized in that, After determining the target index value for detecting the first account, the method further includes: Determining the first candidate index value interval matching the target index value; Calculating the first target hit rate and the first target coverage rate for detecting the first sample account corresponding to the target index value based on the account distribution numbers of the first sample account and the second sample account within the first candidate index value interval; Displaying the first target hit rate and the first target coverage rate.

5. The method according to claim 1, characterized in that The sample account distribution curve is displayed in the distribution diagram; the method further includes: Displaying the full - volume account distribution curve of the full - volume accounts under the index to be measured in the distribution diagram; In response to the triggered index value recommendation operation, successively obtaining the full - volume account distribution numbers of the full - volume accounts at each index value of the index to be measured according to the full - volume account distribution curve; The determining the detection effectiveness values corresponding to each index value for detecting the first sample account based on the account distribution numbers includes: Determining the detection effectiveness values corresponding to each index value for detecting the first sample account based on the account distribution numbers and the full - volume account distribution numbers.

6. The method according to claim 5, characterized in that, Determining the detection effect value when detecting the first sample account corresponding to each of the index values based on the account distribution number and the full - volume account distribution number includes: Calculating the first hit rate when detecting the first sample account corresponding to each of the index values according to the account distribution number; Determining the full - volume hit quantity difference corresponding to each of the index values according to the full - volume account distribution number of the full - volume accounts under each of the index values; Calculating the detection effect value when detecting the first sample account corresponding to each of the index values based on the difference between the first hit rates corresponding to adjacent index values and the full - volume hit quantity difference.

7. The method according to claim 5, wherein Determining the detection effect value when detecting the first sample account corresponding to each of the index values based on the account distribution number and the full - volume account distribution number includes: Calculating the first - sample hit quantity difference when detecting the first sample account corresponding to adjacent index values according to the account distribution number of the first sample account; Calculating the second - sample hit quantity difference when detecting the first sample account corresponding to adjacent index values according to the account distribution number of the second sample account; Determining the full - volume hit quantity difference corresponding to each of the index values according to the full - volume account distribution number of the full - volume accounts under each index value of the to - be - measured index; Calculating the detection effect value when detecting the first sample account corresponding to each of the index values based on the first - sample hit quantity difference, the second - sample hit quantity difference, and the full - volume hit quantity difference.

8. The method according to any one of claims 5 to 7, characterized in that After determining the target index value for detecting the first account, the method further includes: Determining a second candidate index value range that matches the target index value; Calculating the second target hit rate and the second target coverage rate for detecting the first sample account corresponding to the target index value based on the account distribution numbers of the first sample account and the second sample account within the second candidate index value range; Calculating the full - volume hit quantity corresponding to the target index value based on the account distribution number of the full - volume accounts within the second candidate index value range; Displaying the second target hit rate, the second target coverage rate, and the full - volume hit quantity in the distribution diagram.

9. The method according to claim 1, characterized in that The sample account distribution curve is displayed in the distribution diagram; the method further includes: In response to triggering a moving operation of the index threshold line in the distribution diagram, obtaining the real - time index value that changes in real time during the movement of the index threshold line; Determining a candidate real - time index value that matches the real - time index value; Calculating the second hit rate and the second coverage rate for detecting the first sample account corresponding to the real - time index value based on the account distribution numbers of the first sample account and the second sample account corresponding to the candidate real - time index value; Displaying the second hit rate and the second coverage rate in the distribution diagram.

10. The method according to claim 9, wherein The method further includes: Displaying the full - volume account distribution curve of the full - volume accounts under the to - be - measured index in the distribution diagram; Calculating the full - volume hit quantity corresponding to the real - time index value based on the account distribution number of the full - volume accounts corresponding to the candidate real - time index value; The displaying the second hit rate and the second coverage rate in the distribution diagram includes: Display the second hit rate, the second coverage rate, and the full hit volume in the distribution diagram.

11. The method according to claim 1, wherein Before displaying the sample account distribution curves of the first sample account and the second sample account under the to-be-detected metrics respectively, the method further includes: Extract sample accounts from all accounts. Obtain the interaction data corresponding to the sample accounts and under the to-be-detected metrics. Mark the sample accounts based on the interaction data to obtain a first sample account and a second sample account.

12. The method according to claim 11, wherein The to-be-detected metrics include at least one of the resource transfer amount, the resource transfer times, and the number of resource transfer objects.

13. A target index value determination device, characterized in that The device includes: A distribution curve display module, configured to display the sample account distribution curves of the first sample account and the second sample account under the to-be-detected metrics respectively; the first sample account refers to a sample account with suspicious resource transfer; the second sample account is a sample account without suspicious resource transfer behavior. An effect value determination module, configured to, in response to a triggered index value recommendation operation, sequentially obtain the account distribution numbers of the first sample account and the second sample account at each index value of the to-be-detected metrics according to the sample account distribution curve, and determine the detection effect values corresponding to each index value when detecting the first sample account based on the account distribution numbers. A change amount determination module, configured to obtain an effect change amount based on the difference between the detection effect values corresponding to adjacent index values. A target index value calculation module, configured to determine a target index value for detecting the first account according to the effect change amount. A result display module, configured to display the target index value as a recommended result.

14. The device according to claim 13, characterized in that, The effect value determination module is further configured to: Calculate a first hit rate corresponding to each index value when detecting the first sample account according to the account distribution numbers. Determine the detection effect values corresponding to each index value when detecting the first sample account based on the difference between the first hit rates corresponding to adjacent index values.

15. The device according to claim 13, characterized in that The effect value determination module is further configured to: Calculate a difference in the first sample hit volume corresponding to each adjacent index value when detecting the first sample account according to the account distribution number of the first sample account. Calculate a difference in the second sample hit volume corresponding to each adjacent index value when detecting the first sample account according to the account distribution number of the second sample account. Calculate the detection effect values corresponding to each index value when detecting the first sample account based on the difference in the first sample hit volume and the difference in the second sample hit volume.

16. The device according to any one of claims 13 to 15, characterized in that The result display module is further configured to: Determine a first candidate index value interval matching the target index value. Calculate a first target hit rate and a first target coverage rate for detecting the first sample account corresponding to the target index value based on the account distribution numbers of the first sample account and the second sample account within the first candidate index value interval. Display the first target hit rate and the first target coverage rate.

17. The device according to claim 13, characterized in that The sample account distribution curve is displayed in a distribution diagram; the distribution curve display module is further configured to: Display the full account distribution curve of all accounts under the to-be-detected metrics in the distribution diagram. The effect value determination module is further configured to, in response to a triggered metric value recommendation operation, sequentially obtain the full-amount account distribution numbers of the full-amount accounts at each metric value of the to-be-detected metric according to the full-amount account distribution curve; The effect value determination module is further configured to: Based on the account distribution numbers and the full-amount account distribution numbers, determine the detection effect values corresponding to each of the metric values when detecting the first sample account.

18. The device according to claim 17, characterized in that, The effect value determination module is further configured to: According to the account distribution numbers, calculate the first hit rates corresponding to each of the metric values when detecting the first sample account; According to the full-amount account distribution numbers of the full-amount accounts at each of the metric values, determine the full-amount hit quantity differences corresponding to each of the metric values; Based on the differences between the first hit rates corresponding to each adjacent metric value and the full-amount hit quantity differences, calculate the detection effect values corresponding to each of the metric values when detecting the first sample account.

19. The device according to claim 17, characterized in that, The effect value determination module is further configured to: According to the account distribution numbers of the first sample account, calculate the first sample hit quantity differences corresponding to each adjacent metric value when detecting the first sample account; According to the account distribution numbers of the second sample account, calculate the second sample hit quantity differences corresponding to each adjacent metric value when detecting the first sample account; According to the full-amount account distribution numbers of the full-amount accounts at each metric value of the to-be-detected metric, determine the full-amount hit quantity differences corresponding to each of the metric values; Based on the first sample hit quantity differences, the second sample hit quantity differences, and the full-amount hit quantity differences, calculate the detection effect values corresponding to each of the metric values when detecting the first sample account.

20. The device according to any one of claims 17 to 19, characterized in that, The result display module is further configured to: Determine a second candidate metric value interval that matches the target metric value; Based on the account distribution numbers of the first sample account and the second sample account within the second candidate metric value interval, calculate the second target hit rate and the second target coverage rate for detecting the first sample account corresponding to the target metric value; Based on the account distribution numbers of the full-amount accounts within the second candidate metric value interval, calculate the full-amount hit quantity corresponding to the target metric value; Display the second target hit rate, the second target coverage rate, and the full-amount hit quantity in the distribution diagram.

21. The device according to claim 13, characterized in that The sample account distribution curve is displayed in the distribution diagram; the device further includes: a real-time acquisition module, a real-time determination module, a real-time calculation module, and a real-time display module, where The real-time acquisition module is configured to, in response to a triggered operation of moving the metric threshold line in the distribution diagram, acquire the real-time metric values that change in real time during the movement of the metric threshold line; The real-time determination module is configured to determine candidate real-time metric values that match the real-time metric values; The real-time calculation module is configured to, based on the account distribution numbers of the first sample account and the second sample account corresponding to the candidate real-time metric values, calculate the second hit rate and the second coverage rate for detecting the first sample account corresponding to the real-time metric values; The real-time display module is configured to display the second hit rate and the second coverage rate in the distribution diagram.

22. The device according to claim 21, characterized in that, The distribution curve display module is further configured to: display the full - volume account distribution curve of all full - volume accounts under the to - be - measured indicator in the distribution diagram; The real - time calculation module is further configured to calculate the full - volume hit volume corresponding to the real - time indicator value based on the account distribution number of the full - volume accounts corresponding to the candidate real - time indicator value; The step of displaying the second hit rate and the second coverage rate in the distribution diagram includes: The real - time display module is further configured to display the second hit rate, the second coverage rate, and the full - volume hit volume in the distribution diagram.

23. The device according to claim 13, characterized in that, The device further includes: a sample determination module, configured to: extract sample accounts from all full - volume accounts; obtain the interaction data corresponding to the sample accounts under the to - be - measured indicator; mark the sample accounts based on the interaction data to obtain first sample accounts and second sample accounts.

24. The device according to claim 23, wherein, The to - be - measured indicator includes at least one of the resource transfer amount, the resource transfer times, and the number of resource transfer objects.

25. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 12 are implemented.

26. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 12 are implemented.

27. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images