Method, device, computer equipment and storage medium for determining suspicious cases

By receiving cases and finding conditions, finding and displaying key and non-key cases, and using machine learning models to screen suspicious cases, the problem of low audit efficiency of illegal fund transfer identification software in the existing technology is solved, and a method of timely reporting suspicious cases is realized.

CN111737287BActive Publication Date: 2024-11-26SHENZHEN ZHUIYI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010473593.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-05-29
Publication Date
2024-11-26
Estimated Expiration
2040-05-29

AI Technical Summary

Technical Problem

In the prior art, due to too many cases of illegal fund transfer identification software triggering fixed rules, the auditors have a large workload and slow progress, and they cannot report suspicious cases in a timely manner.

Method used

Provide a method to determine suspicious cases, find conditions for receiving cases, find and display key and non-key cases, determine suspicious cases to be reported based on user operations, and use machine learning models to screen the suspicious confidence of transaction subjects, and optimize the review process.

Benefits of technology

It improves the review efficiency, promptly reports suspicious cases, reduces the review burden of business personnel, and improves the response speed of illegal fund transfer identification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111737287B_ABST
    Figure CN111737287B_ABST
Patent Text Reader

Abstract

The present application relates to a method, device, computer equipment and storage medium for determining suspicious cases. The method comprises: receiving case search conditions; searching in a pre-acquired key case collection according to the case search conditions, and using the found key case as a target key case; wherein the key case collection includes multiple key cases; the key case is a case of focus selected from a preset time period; displaying the case information of the target key case in a case display interface; receiving a selection operation based on the case display interface, and determining the target key case corresponding to the selection operation as a suspicious case to be reported. The use of this method can improve the audit efficiency and report suspicious cases in a timely manner.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of identifying illegal fund transfers, and in particular to a method, apparatus, computer equipment and storage medium for determining suspicious cases. Background Art

[0002] At present, business personnel of many financial institutions regularly report suspicious cases of suspected illegal fund transfer to relevant regulatory authorities. In related technologies, fixed rules are usually implanted in the illegal fund transfer identification software based on laws and expert experience, and then the illegal fund transfer identification software determines whether the relevant information of the transaction subject (customer) triggers the fixed rules. If the relevant information of the transaction subject triggers one or more fixed rules, the case corresponding to the transaction subject is determined as a case to be reviewed. After that, the business personnel will review these cases to be reviewed one by one to determine whether these cases are indeed suspected of illegal fund transfer. If there is a suspicion of illegal fund transfer, it will be reported to the regulatory authorities.

[0003] However, since there are many cases that trigger fixed rules, the workload of auditors is heavy, resulting in slow audit progress and untimely reporting. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for determining suspicious cases that can improve audit efficiency and report suspicious cases in a timely manner in response to the above technical problems.

[0005] A method for determining a suspicious case, the method comprising:

[0006] Receive case search conditions;

[0007] Searching in a pre-acquired key case collection according to case search conditions, and using the found key case as a target key case; wherein the key case collection includes multiple key cases; and the key case is a case of key concern selected from a preset time period;

[0008] Display case information of target key cases in the case display interface;

[0009] A selection operation is received based on the case display interface, and a target key case corresponding to the selection operation is determined as a suspicious case to be reported.

[0010] In one embodiment, after searching for cases in the pre-acquired key case set according to the case search condition, the method further includes:

[0011] If no key case meeting the case search criteria is found in the key case collection, feedback information indicating that no case was found is generated;

[0012] Display feedback information in the case display interface.

[0013] In one embodiment, after failing to find a key case that meets the case search condition in the key case collection, the method further includes:

[0014] Searching in a pre-acquired non-key case collection according to case search conditions; the non-key case collection includes multiple non-key cases; non-key cases are cases other than key cases within a preset time period;

[0015] If a non-key case that meets the case search condition is found in the non-key case collection, the found non-key case is used as the target non-key case;

[0016] Display case information of target non-key cases in the case display interface.

[0017] In one embodiment, the case display interface includes a search condition input area and a case information display area;

[0018] The above-mentioned conditions for searching for received cases include:

[0019] Receive the case search condition entered in the search condition input area;

[0020] The case information of the target key cases displayed in the case display interface includes:

[0021] The case information of the target key case is displayed in the case information display area; the case information includes at least one of the transaction subject identification, case status, suspicion confidence and case generation time; the suspicion confidence represents the probability that the target key case is suspected of illegal fund transfer.

[0022] In one embodiment, the case display interface includes a filter area, and the filter area includes a plurality of filter options; before displaying the case information of the target key case in the case information display area, the method further includes:

[0023] Receive trigger actions for target filter options;

[0024] Correspondingly, the case information of the target key case is displayed in the case information display area, including:

[0025] The case information of multiple target key cases is displayed in the case information display area according to the target filtering options.

[0026] In one embodiment, the above-mentioned screening options include an unreviewed state and a reviewed state; the above-mentioned case information of multiple target key cases is displayed in the case information display area according to the target screening options, including:

[0027] If the target screening option is in the unreviewed state, multiple unreviewed target key cases are screened out from multiple target key cases;

[0028] Multiple unreviewed target key cases are displayed in order from high to low suspicion confidence.

[0029] In one embodiment, after screening out a plurality of unreviewed target key cases from the plurality of target key cases, the method further includes:

[0030] Multiple unreviewed target key cases with the same suspicious confidence level are displayed in order of case generation time from recent to ancient.

[0031] In one embodiment, the above-mentioned screening options include a monitoring list and a white list, the monitoring list includes multiple identifiers of transaction entities that need to be monitored, and the white list includes multiple identifiers of transaction entities that do not need to be monitored;

[0032] The above target filtering options display case information of multiple target key cases in the case information display area, including:

[0033] If the target screening option is a monitoring list, determine whether the identifier of the transaction subject corresponding to each target key case is on the monitoring list;

[0034] If the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case will be displayed at the top.

[0035] In one embodiment, before searching in the pre-acquired key case set according to the case search condition, the method further includes:

[0036] Obtain transaction data of multiple transaction entities within a preset time period;

[0037] Filter out target transaction entities from multiple transaction entities based on transaction data;

[0038] The cases corresponding to the target transaction entities are identified as key cases, and a key case set is composed of multiple key cases.

[0039] In one embodiment, the above-mentioned screening out a target transaction subject from a plurality of transaction subjects according to the transaction data includes:

[0040] For each transaction subject, the transaction data is input into a pre-set machine learning model to obtain the suspicious confidence level corresponding to the transaction subject output by the machine learning model;

[0041] The transaction subject whose suspicious confidence level is greater than a preset threshold is determined as the target transaction subject.

[0042] A device for determining a suspicious case, the device comprising:

[0043] A case search condition receiving module is used to receive case search conditions;

[0044] A case search module, used to search in a pre-acquired key case set according to the case search condition, and use the found key case as a target key case; wherein the key case set includes a plurality of key cases; the key case is a case of key concern screened out within a preset time period;

[0045] A case information display module, used to display the case information of the target key case in the case display interface;

[0046] The suspicious case determination module is used to receive a selection operation based on the case display interface, and determine the target key case corresponding to the selection operation as a suspicious case to be reported.

[0047] In one embodiment, the case search module is further configured to generate feedback information indicating that the case was not found if no key case meeting the case search condition is found in the key case collection;

[0048] The above-mentioned case information display module is also used to display feedback information in the case display interface.

[0049] In one embodiment, the device further comprises:

[0050] The case search module is further used to search in a pre-acquired non-key case set according to the case search condition; the non-key case set includes multiple non-key cases; the non-key cases are cases other than key cases within a preset time period;

[0051] The case information display module is also used to, if a non-key case meeting the case search conditions is found in the non-key case collection, use the found non-key case as the target non-key case; and display the case information of the target non-key case in the case display interface.

[0052] In one embodiment, the case display interface includes a search condition input area and a case information display area;

[0053] The case search condition receiving module is specifically used to receive the case search condition input in the search condition input area;

[0054] The above-mentioned case information display module is specifically used to display the case information of the target key case in the case information display area; the case information includes at least one of the transaction subject identification, case status, suspicion confidence and case generation time; the suspicion confidence represents the probability that the target key case is suspected of illegal funds transfer.

[0055] In one embodiment, the case display interface includes a filter area, and the filter area includes a plurality of filter options; the device further includes:

[0056] A screening trigger operation receiving module, used for receiving a trigger operation for a target screening option;

[0057] Correspondingly, the above-mentioned case information display module is specifically used to display case information of multiple target key cases in the case information display area according to the target filtering options.

[0058] In one of the embodiments, the above-mentioned screening options include an unreviewed state and an reviewed state; the above-mentioned case information display module is specifically used to screen out multiple unreviewed target key cases from multiple target key cases if the target screening option is an unreviewed state; and display the multiple unreviewed target key cases in order of suspicion confidence from high to low.

[0059] In one of the embodiments, the case information display module is specifically used to display multiple unreviewed target key cases with the same suspicious confidence level in order of case generation time from recent to oldest.

[0060] In one embodiment, the above-mentioned screening options include a monitoring list and a white list, the monitoring list includes multiple identifiers of transaction entities that need to be monitored, and the white list includes multiple identifiers of transaction entities that do not need to be monitored;

[0061] The above-mentioned case information display module is specifically used to determine whether the identification of the transaction subject corresponding to each target key case is in the monitoring list if the target screening option is a monitoring list; if the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case will be displayed at the top.

[0062] In one embodiment, the device further comprises:

[0063] A transaction data acquisition module is used to acquire transaction data of multiple transaction entities within a preset time period;

[0064] A target transaction subject screening module is used to screen out a target transaction subject from multiple transaction subjects based on transaction data;

[0065] The key case collection obtaining module is used to determine the cases corresponding to the target transaction subject as key cases, and form a key case collection from multiple key cases.

[0066] In one of the embodiments, the above-mentioned target transaction subject screening module is specifically used to input the transaction data into a preset machine learning model for each transaction subject, obtain the suspicious confidence level corresponding to the transaction subject output by the machine learning model; and determine the transaction subject whose suspicious confidence level is greater than a preset threshold as the target transaction subject.

[0067] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0068] Receive case search conditions;

[0069] Searching in a pre-acquired key case collection according to case search conditions, and using the found key case as a target key case; wherein the key case collection includes multiple key cases; and the key case is a case of key concern selected from a preset time period;

[0070] Display case information of target key cases in the case display interface;

[0071] A selection operation is received based on the case display interface, and a target key case corresponding to the selection operation is determined as a suspicious case to be reported.

[0072] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0073] Receive case search conditions;

[0074] Searching in a pre-acquired key case collection according to case search conditions, and using the found key case as a target key case; wherein the key case collection includes multiple key cases; and the key case is a case of key concern selected from a preset time period;

[0075] Display case information of target key cases in the case display interface;

[0076] A selection operation is received based on the case display interface, and a target key case corresponding to the selection operation is determined as a suspicious case to be reported.

[0077] The above-mentioned method, device, computer equipment and storage medium for determining suspicious cases receive case search conditions; search in a pre-acquired set of key cases according to the case search conditions, and use the found key cases as target key cases. Display case information of target key cases in the case display interface; receive a selection operation based on the case display interface, and determine the target key case corresponding to the selection operation as a suspicious case to be reported. Through the embodiments of the present application, the user does not need to review the cases to be reviewed one by one, but only needs to enter the case search conditions according to the review requirements to find the target key cases that meet the review requirements, and then give priority to reviewing the found target key cases. In this way, not only the review efficiency can be improved, but also suspicious cases can be reported in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 is an application environment diagram of a method for determining a suspicious case in an embodiment;

[0079] Figure 2 is a flow chart of a method for determining a suspicious case in one embodiment;

[0080] Figure 3 is a flow chart of a method for determining a suspicious case in another embodiment;

[0081] Figure 4 A schematic diagram of a case display interface in an embodiment;

[0082] Figure 5 A schematic diagram of screening options in one embodiment;

[0083] Figure 6 is a flow chart of a method for determining a suspicious case in another embodiment;

[0084] Figure 7 A schematic diagram of a case display interface in another embodiment;

[0085] Figure 8 is a structural block diagram of a device for determining a suspicious case in one embodiment;

[0086] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0087] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with 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.

[0088] The method for determining suspicious cases provided in this application can be applied to Figure 1In the application environment shown. The application environment includes a terminal 01 and a server 02; wherein the terminal 01 receives a case search condition; searches in a pre-acquired key case set according to the case search condition, and uses the key case found as a target key case; displays the case information of the target key case in the case display interface; receives a selection operation based on the case display interface, and determines the target key case corresponding to the selection operation as a suspicious case to be reported. Then, the terminal 01 can communicate with the server 02 through the network and send the suspicious case to the server 02. The above-mentioned terminal 01 can be, but is not limited to, various personal computers, laptops, smart phones and tablet computers, and the above-mentioned server 02 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0089] In one embodiment, Figure 2 As shown, a method for determining a suspicious case is provided. This embodiment uses the method applied to a terminal as an example for illustration, and may include the following steps:

[0090] Step 101, receiving case search conditions.

[0091] The case display interface can be pre-set, and when the user needs to review the case, the terminal displays the case display interface after receiving the opening operation of the case display interface. When the user enters the case search condition in the case display interface according to the review requirements, the terminal receives the case search condition.

[0092] For example, if a user needs to review a case corresponding to a certain transaction subject, he can enter the identifier of the transaction subject in the case display interface, such as the name of the transaction subject, or the number of the transaction subject. The terminal receives the identifier of the transaction subject and uses the identifier of the transaction subject as a case search condition. The embodiment of the present application does not make a detailed limitation on the case search condition, and it can be set according to the actual situation.

[0093] The terminal may also receive the voice input by the user and determine the case search condition according to the voice. Alternatively, the case search condition may be received in other ways, which are not specifically limited in the present embodiment and may be set according to actual conditions.

[0094] Step 102: Search in the pre-acquired key case set according to the case search condition, and use the found key case as the target key case.

[0095] A key case collection is obtained in advance, wherein the key case collection includes multiple key cases; key cases are cases of key concern that are selected from a preset time period. For example, 100 cases of key concern are selected from January 1 to January 31, and the key case collection is composed of these 100 cases of key concern. The present application embodiment does not make a detailed limitation on the screening method, and it can be set according to actual conditions.

[0096] After receiving the case search condition, a search is performed in the key case collection according to the case search condition. If a key case that meets the case search condition is found, the found key case is used as the target key case.

[0097] For example, searching is performed in the key case set according to the identifier of the transaction subject, where the identifiers of the transaction subjects corresponding to key cases 1, 5, 8, and 11 meet the case search condition, and key cases 1, 5, 8, and 11 are taken as target key cases.

[0098] Step 103: Display case information of the target key case in the case display interface.

[0099] After finding the target key case, the case information of the target key case is displayed in the case display interface. For example, the identification of the transaction subject, transaction time, transaction amount, transaction counterparty, triggered fixed rules, etc. corresponding to the target key case are displayed. The embodiment of the present application does not make a detailed limitation on the case information, and it can be set according to the actual situation.

[0100] Step 104: receiving a selection operation based on the case display interface, and determining the target key case corresponding to the selection operation as a suspicious case to be reported.

[0101] If the user determines that a target key case is a suspicious case to be reported based on the case information, the user enters a selection operation in the case display interface. The terminal receives the selection operation based on the case display interface and determines the target key case corresponding to the selection operation as a suspicious case.

[0102] The selection operation may be a click operation or a check operation. The present application embodiment does not limit the selection operation in detail and may be set according to actual conditions.

[0103] In one embodiment, after a suspicious case is determined, a pop-up window is generated to ask whether to report the case, and a report button is provided in the pop-up window. When the terminal receives a trigger operation for the report button, the terminal reports the suspicious case to the relevant regulatory department.

[0104] In the above-mentioned method for determining suspicious cases, a case search condition is received; a search is performed in a pre-acquired set of key cases according to the case search condition, and the key case found is used as a target key case. The case information of the target key case is displayed in the case display interface; a selection operation is received based on the case display interface, and the target key case corresponding to the selection operation is determined as a suspicious case to be reported. Through the embodiment of the present application, the user does not need to review the cases to be reviewed one by one, but only needs to enter the case search condition according to the review requirements to find the target key cases that meet the review requirements, and then give priority to reviewing the found target key cases. In this way, not only the review efficiency can be improved, but also suspicious cases can be reported in a timely manner.

[0105] In one embodiment, Figure 3 As shown, an optional process of the method for determining suspicious cases, based on the above embodiment, may specifically include the following steps:

[0106] Step 201, receiving the case search condition input in the search condition input area.

[0107] Display the case display interface, such as Figure 4 As shown, the case display interface includes a search condition input area and a case information display area. The terminal receives the case search condition input by the user according to the review requirements in the search condition input area.

[0108] In one embodiment, the case display interface also includes icons of various functional modules, such as Figure 4 The icon on the left is shown, and the details will be displayed when the mouse hovers.

[0109] Step 202: Search in the pre-acquired key case set according to the case search condition, and use the found key case as the target key case.

[0110] Step 203: Display case information of the target key case in the case information display area.

[0111] The case information includes at least one of the identification of the transaction subject, the case status, the suspicion confidence and the case generation time; the suspicion confidence represents the probability that the target key case is suspected of illegal fund transfer. For example, if the target key case is determined to be key case 1 in the key case set, the case information of key case 1 is displayed: the name of the transaction subject is A, the case status is unreviewed, the suspicion confidence is 90%, and the case generation time is X year X day. The embodiment of the present application does not make a detailed limitation on the case information, and it can be set according to the actual situation.

[0112] like Figure 4As shown, the case display interface includes a filtering area, and the filtering area includes multiple filtering options; the embodiment of the present application may also include the following steps:

[0113] Step 204: receiving a trigger operation for a target screening option.

[0114] Among them, the trigger operation can be a click operation or other operations. The embodiment of the present application does not make any detailed restrictions on this and can be set according to actual conditions.

[0115] Step 205: Display case information of multiple target key cases in the case information display area according to the target screening options.

[0116] Among them, the screening options include unreviewed status and reviewed status; if the target screening option is unreviewed status, multiple unreviewed target key cases are screened out from multiple target key cases; the multiple unreviewed target key cases are displayed in order of suspicion confidence from high to low.

[0117] Specifically, after finding the target key case from the key case collection, if the user wants to view the unreviewed target key cases, the user can click the unreviewed status in the filter option. After receiving the click operation, the terminal filters out the target key cases whose case status is the unreviewed status from the multiple target key cases. And, the filtered target key cases are displayed in descending order of suspicion confidence.

[0118] For example, the target key cases are key cases 1, 5, 8, and 11, wherein the case status of key case 1 is reviewed, and the case status of key cases 5, 8, and 11 is unreviewed; and the suspicious confidence of key case 5 is 89%, and the suspicious confidence of key cases 8 and 11 is 90%. After receiving the click operation, the terminal displays the case information of key cases 1, 5, 8, and 11, and displays them in the order of key cases 8, 11, 5, and 1.

[0119] In one of the embodiments, a plurality of unreviewed target key cases with the same suspicious confidence level are displayed in order of case generation time from recent to ancient.

[0120] For example, key cases 8 and 11 have the same suspicion confidence level, key case 8 was generated on January 1, and key case 11 was generated on January 2. When displaying case information, it is displayed in the order of key cases 11, 8, 5, and 1.

[0121] Among them, the screening options can also include suspicion confidence and case generation time, such as Figure 5 The filter options can also include reported status and excluded status.

[0122] Among them, the screening options include a monitoring list and a white list. The monitoring list includes multiple identifications of transaction entities that need to be monitored, and the white list includes multiple identifications of transaction entities that do not need to be monitored. If the target screening option is a monitoring list, determine whether the identification of the transaction entity corresponding to each target key case is in the monitoring list; if the identification of the transaction entity corresponding to the target key case is in the monitoring list, the target key case will be displayed at the top.

[0123] Specifically, after finding the target key case from the key case collection, if the user wants to view the cases corresponding to each transaction subject in the monitoring list, the user can click the monitoring list in the filter option. After receiving the click operation, the terminal determines whether the identification of the transaction subject corresponding to the target key case is in the monitoring list. If the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case is displayed at the top.

[0124] For example, the target key cases are key cases 1, 5, 8, and 11, and the name of the transaction subject included in the monitoring list is A. It is determined that the identification of the transaction subject corresponding to key case 11 is A, and key case 11 is displayed at the top. It can be understood that when the identifications of the transaction subjects corresponding to multiple target key cases are all in the monitoring list, they can be displayed in the order of suspicion confidence from high to low, or in the order of case generation time from recent to distant. This embodiment does not make a detailed limitation on the display method, and it can be set according to actual conditions.

[0125] Step 206: receiving a selection operation based on the case display interface, and determining the target key case corresponding to the selection operation as a suspicious case to be reported.

[0126] When the user determines that a certain target key case is a suspicious case based on the case information displayed by the terminal, the user inputs a selection operation. After receiving the selection operation, the terminal determines the suspicious case to be reported based on the selection operation.

[0127] In the above-mentioned method for determining suspicious cases, a case search condition inputted in the search condition input area is received; a search is performed in a pre-acquired key case set according to the case search condition, and the key case found is used as a target key case; case information of the target key case is displayed in the case information display area; a trigger operation for a target screening option is received; case information of multiple target key cases is displayed in the case information display area according to the target screening option; a selection operation is received based on the case display interface, and the target key case corresponding to the selection operation is determined as a suspicious case to be reported. Through the embodiment of the present application, the user can further screen the target key cases according to the audit requirements, and then give priority to the audit of the further screened target key cases, so that the audit efficiency can be further improved and suspicious cases can be reported in a timely manner.

[0128] In one embodiment, Figure 6 As shown, an optional process of the method for determining suspicious cases, based on the above embodiment, may include the following steps:

[0129] Step 301, obtaining transaction data of multiple transaction entities within a preset time period; screening out a target transaction entity from the multiple transaction entities based on the transaction data; determining the case corresponding to the target transaction entity as a key case, and forming a key case set from the multiple key cases.

[0130] After data cleaning, the transaction data is stored in the transaction database. When determining suspicious cases, the transaction data of multiple transaction entities within a preset time period are obtained from the transaction database. Then, for each transaction entity, the transaction data is input into a preset machine learning model to obtain the suspicious confidence level corresponding to the transaction entity output by the machine learning model; the transaction entity with a suspicious confidence level greater than a preset threshold is determined as the target transaction entity. After that, the case corresponding to the target transaction entity is determined as a key case; after obtaining multiple key cases, the multiple key cases form a key case set.

[0131] For example, the suspicious confidences corresponding to 100 transaction entities are obtained, and the transaction entities with suspicious confidences greater than 60% are determined as target transaction entities. The present application embodiment does not make a detailed limitation on the preset threshold, and it can be set according to actual conditions.

[0132] In one embodiment, the transaction data corresponding to the reported suspicious cases can be used as training samples for the machine learning model. Using these training samples to update the machine learning model can make the suspicious confidence level output by the machine learning model more accurate. The present application embodiment does not make any specific restrictions on the training of the machine learning model, and it can be set according to actual conditions.

[0133] Step 302: display the case display interface and receive the case search condition input in the search condition input area.

[0134] Step 303: Search in the pre-acquired key case collection according to the case search condition.

[0135] If a key case is found, step 304 is executed; if no key case is found, step 305 is executed.

[0136] Step 304: The found key case is used as the target key case, and case information of the target key case is displayed in the case display interface.

[0137] Step 305: If no key case meeting the case search condition is found in the key case collection, feedback information indicating that no case is found in the key case collection is generated; and the feedback information is displayed in the case display interface.

[0138] like Figure 7 As shown, if a key case that meets the case search condition is not found in the key case collection, feedback information that the case was not found is generated and displayed in the case display interface.

[0139] Step 306: Search in the pre-acquired non-key case collection according to the case search condition.

[0140] While displaying the feedback information, you can search in the non-key case collection according to the case search conditions. The non-key case collection includes multiple non-key cases; non-key cases are cases other than key cases within a preset time period. For example, there are 300 cases within a preset time period, of which 100 are key cases and the other 200 are non-key cases. These 200 non-key cases constitute the non-key case collection.

[0141] Step 307: If a non-key case that meets the case search condition is found in the non-key case set, the found non-key case is used as a target non-key case.

[0142] Search in the non-key case collection according to the case search conditions. If a non-key case that meets the case search conditions is found, the found non-key case is used as the target non-key case. If a non-key case that meets the case search conditions is not found in the non-key case collection, search is performed in the archived case database.

[0143] Step 308: Display case information of the target non-key case in the case display interface.

[0144] If the target non-key case is found in the non-key case collection or the archived case database, the case information of the target non-key case is displayed; if the target non-key case is not found in the non-key case collection and the archived case database, feedback information that the case was not found is displayed.

[0145] In the above-mentioned method for determining suspicious cases, the transaction data of multiple transaction entities within a preset time period are first obtained, and a key case collection is obtained based on the transaction data; then, a case display interface is displayed, and the case search conditions entered in the search condition input area are received; a search is performed in the key case collection obtained in advance according to the case search conditions; the key case found is used as the target key case, and the case information of the target key case is displayed in the case display interface; if a key case that meets the case search conditions is not found in the key case collection, feedback information that the case is not found in the key case collection is generated; and the feedback information is displayed in the case display interface. Further, a search is performed in the non-key case collection obtained in advance according to the case search conditions; if a non-key case that meets the case search conditions is found in the non-key case collection, the non-key case found is used as the target non-key case; and the case information of the target non-key case is displayed in the case display interface. Through the embodiment of the present application, a search is performed in the key case collection, the non-key case collection, and even the archived case database according to the case search conditions, so that the found case meets the audit requirements and is convenient for user audit.

[0146] It should be understood that although Figure 2-Figure 6 The steps in the flowchart are shown in sequence as indicated by 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 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0147] In one embodiment, Figure 8 As shown, a device for determining a suspicious case is provided, comprising:

[0148] A case search condition receiving module 401 is used to receive case search conditions;

[0149] The case search module 402 is used to search in the key case set acquired in advance according to the case search condition, and use the key case found as the target key case; wherein the key case set includes a plurality of key cases; the key case is a case of key concern selected from a preset time period;

[0150] The case information display module 403 is used to display the case information of the target key case in the case display interface;

[0151] The suspicious case determination module 404 is used to receive a selection operation based on the case display interface, and determine the target key case corresponding to the selection operation as a suspicious case to be reported.

[0152] In the embodiment of the present application, a case display interface may be displayed, and case search conditions may be received based on the case display interface. The terminal may also receive voice input by the user and determine the case search conditions based on the voice. Alternatively, the case search conditions may be received in other ways.

[0153] A key case collection is obtained in advance, wherein the key case collection includes multiple key cases; key cases are cases of key concern that are screened out from a preset time period. After receiving the case search conditions, a search is performed in the key case collection according to the case search conditions. If a key case that meets the case search conditions is found, the found key case is used as the target key case.

[0154] After finding the target key case, the case information of the target key case is displayed in the case display interface. If the user determines that one of the target key cases is a suspicious case to be reported based on the case information, the user enters a selection operation in the case display interface. The terminal receives the selection operation based on the case display interface and determines the target key case corresponding to the selection operation as a suspicious case.

[0155] In one embodiment, the case search module 402 is further configured to generate feedback information indicating that the case was not found if no key case meeting the case search condition is found in the key case collection;

[0156] The case information display module 403 is also used to display feedback information in the case display interface.

[0157] In one embodiment, the device further comprises:

[0158] The case search module 402 is further used to search in a pre-acquired non-key case set according to the case search condition; the non-key case set includes a plurality of non-key cases; the non-key cases are cases other than key cases within a preset time period;

[0159] The case information display module 403 is also used to, if a non-key case meeting the case search condition is found in the non-key case collection, use the found non-key case as the target non-key case; and display the case information of the target non-key case in the case display interface.

[0160] In the embodiment of the present application, if a key case that meets the case search condition is not found in the key case collection, feedback information of not finding the case is generated, and the feedback information is displayed in the case display interface. In addition, while displaying the feedback information, a search can be performed in the non-key case collection according to the case search condition. The non-key case collection includes multiple non-key cases; non-key cases are cases other than key cases within a preset time period.

[0161] If a non-key case that meets the case search criteria is found in the non-key case collection, the non-key case found is used as the target non-key case. If a non-key case that meets the case search criteria is not found in the non-key case collection, a search is performed in the archived case database.

[0162] If the target non-key case is found in the non-key case collection or the archived case database, the case information of the target non-key case is displayed; if the target non-key case is not found in the non-key case collection and the archived case database, feedback information that the case was not found is displayed.

[0163] In one embodiment, the case display interface includes a search condition input area and a case information display area;

[0164] The case search condition receiving module 401 is specifically used to receive the case search condition input in the search condition input area;

[0165] The above-mentioned case information display module 403 is specifically used to display the case information of the target key case in the case information display area; the case information includes at least one of the transaction subject identification, case status, suspicion confidence and case generation time; the suspicion confidence represents the probability that the target key case is suspected of illegal funds transfer.

[0166] In one embodiment, the case display interface includes a filter area, and the filter area includes a plurality of filter options; the device further includes:

[0167] A screening trigger operation receiving module, used for receiving a trigger operation for a target screening option;

[0168] Correspondingly, the case information display module 403 is specifically used to display case information of multiple target key cases in the case information display area according to the target filtering options.

[0169] In one of the embodiments, the above-mentioned screening options include an unreviewed state and an reviewed state; the above-mentioned case information display module 403 is specifically used to screen out multiple unreviewed target key cases from multiple target key cases if the target screening option is an unreviewed state; and display the multiple unreviewed target key cases in order of suspicion confidence from high to low.

[0170] In one embodiment, the case information display module 403 is specifically used to display multiple unreviewed target key cases with the same suspicious confidence level in the order of case generation time from recent to oldest.

[0171] In one embodiment, the above-mentioned screening options include a monitoring list and a white list, the monitoring list includes multiple identifiers of transaction entities that need to be monitored, and the white list includes multiple identifiers of transaction entities that do not need to be monitored;

[0172] The case information display module 403 is specifically used to determine whether the identification of the transaction subject corresponding to each target key case is in the monitoring list if the target screening option is a monitoring list; if the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case is displayed at the top.

[0173] In an embodiment of the present application, after finding a target key case from a key case collection, if the user wants to view unreviewed target key cases, the user can click the unreviewed status in the filter option. After the terminal receives the click operation, it filters out target key cases whose case status is an unreviewed state from multiple target key cases. And, the filtered target key cases are displayed in order from high to low in terms of suspicious confidence. If there are multiple unreviewed target key cases with the same suspicious confidence, the multiple unreviewed target key cases with the same suspicious confidence are displayed in order from recent to far in terms of case generation time.

[0174] After finding the target key case from the key case collection, if the user wants to view the cases corresponding to each transaction subject in the monitoring list, the user can also click the monitoring list in the filter option. After receiving the click operation, the terminal determines whether the identification of the transaction subject corresponding to the target key case is in the monitoring list. If the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case is displayed at the top.

[0175] In one embodiment, the device further comprises:

[0176] A transaction data acquisition module is used to acquire transaction data of multiple transaction entities within a preset time period;

[0177] A target transaction subject screening module is used to screen out a target transaction subject from multiple transaction subjects based on transaction data;

[0178] The key case collection obtaining module is used to determine the cases corresponding to the target transaction subject as key cases, and form a key case collection from multiple key cases.

[0179] In one of the embodiments, the above-mentioned target transaction subject screening module is specifically used to input the transaction data into a preset machine learning model for each transaction subject, obtain the suspicious confidence level corresponding to the transaction subject output by the machine learning model; and determine the transaction subject whose suspicious confidence level is greater than a preset threshold as the target transaction subject.

[0180] In the embodiment of the present application, the transaction data is stored in the transaction database after data cleaning. When determining suspicious cases, the transaction data of multiple transaction entities within a preset time period are obtained from the transaction database. Then, for each transaction entity, the transaction data is input into a preset machine learning model to obtain the suspicious confidence level corresponding to the transaction entity output by the machine learning model; the transaction entity whose suspicious confidence level is greater than a preset threshold is determined as the target transaction entity. After that, the case corresponding to the target transaction entity is determined as a key case; after obtaining multiple key cases, the multiple key cases form a key case set.

[0181] Among them, the transaction data corresponding to the reported suspicious cases can be used as training samples for the machine learning model. Using these training samples to update the machine learning model can make the suspicious confidence level output by the machine learning model more accurate. The present application embodiment does not make any detailed restrictions on the training of the machine learning model, and it can be set according to actual conditions.

[0182] For the specific definition of the suspicious case determination device, please refer to the definition of the suspicious case determination method above, which will not be repeated here. Each module in the above suspicious case determination device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0183] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9As shown. 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, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining a suspicious case is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0184] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure 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 certain components, or have a different arrangement of components.

[0185] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0186] Receive case search conditions;

[0187] Searching in a pre-acquired key case collection according to case search conditions, and using the found key case as a target key case; wherein the key case collection includes multiple key cases; and the key case is a case of key concern selected from a preset time period;

[0188] Display case information of target key cases in the case display interface;

[0189] A selection operation is received based on the case display interface, and a target key case corresponding to the selection operation is determined as a suspicious case to be reported.

[0190] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0191] If no key case meeting the case search criteria is found in the key case collection, feedback information indicating that no case was found is generated;

[0192] Display feedback information in the case display interface.

[0193] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0194] Searching in a pre-acquired non-key case collection according to case search conditions; the non-key case collection includes multiple non-key cases; non-key cases are cases other than key cases within a preset time period;

[0195] If a non-key case that meets the case search condition is found in the non-key case collection, the found non-key case is used as the target non-key case;

[0196] Display case information of target non-key cases in the case display interface.

[0197] In one embodiment, the case display interface includes a search condition input area and a case information display area;

[0198] When the processor executes the computer program, it also performs the following steps:

[0199] Receive the case search condition entered in the search condition input area;

[0200] The case information of the target key case is displayed in the case information display area; the case information includes at least one of the transaction subject identification, case status, suspicion confidence and case generation time; the suspicion confidence represents the probability that the target key case is suspected of illegal fund transfer.

[0201] In one embodiment, the case display interface includes a filter area, and the filter area includes multiple filter options; when the processor executes the computer program, the following steps are also implemented:

[0202] Receive trigger actions for target filter options;

[0203] The case information of multiple target key cases is displayed in the case information display area according to the target filtering options.

[0204] In one embodiment, the above-mentioned screening options include an unreviewed state and a reviewed state; when the processor executes the computer program, the following steps are also implemented:

[0205] If the target screening option is in the unreviewed state, multiple unreviewed target key cases are screened out from multiple target key cases;

[0206] Multiple unreviewed target key cases are displayed in order from high to low suspicion confidence.

[0207] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0208] Multiple unreviewed target key cases with the same suspicious confidence level are displayed in order of case generation time from recent to ancient.

[0209] In one embodiment, the above-mentioned screening options include a monitoring list and a white list, wherein the monitoring list includes identifiers of multiple transaction entities that need to be monitored, and the white list includes identifiers of multiple transaction entities that do not need to be monitored;

[0210] When the processor executes the computer program, it also performs the following steps:

[0211] If the target screening option is a monitoring list, determine whether the identifier of the transaction subject corresponding to each target key case is on the monitoring list;

[0212] If the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case will be displayed at the top.

[0213] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0214] Obtain transaction data of multiple transaction entities within a preset time period;

[0215] Filter out target transaction entities from multiple transaction entities based on transaction data;

[0216] The cases corresponding to the target transaction entities are identified as key cases, and a key case set is composed of multiple key cases.

[0217] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0218] For each transaction subject, the transaction data is input into a pre-set machine learning model to obtain the suspicious confidence level corresponding to the transaction subject output by the machine learning model;

[0219] The transaction subject whose suspicious confidence level is greater than a preset threshold is determined as the target transaction subject.

[0220] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0221] Receive case search conditions;

[0222] Searching in a pre-acquired key case collection according to case search conditions, and using the found key case as a target key case; wherein the key case collection includes multiple key cases; and the key case is a case of key concern selected from a preset time period;

[0223] Display case information of target key cases in the case display interface;

[0224] A selection operation is received based on the case display interface, and a target key case corresponding to the selection operation is determined as a suspicious case to be reported.

[0225] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0226] If no key case meeting the case search criteria is found in the key case collection, feedback information indicating that no case was found is generated;

[0227] Display feedback information in the case display interface.

[0228] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0229] Searching in a pre-acquired non-key case collection according to case search conditions; the non-key case collection includes multiple non-key cases; non-key cases are cases other than key cases within a preset time period;

[0230] If a non-key case that meets the case search condition is found in the non-key case collection, the found non-key case is used as the target non-key case;

[0231] Display case information of target non-key cases in the case display interface.

[0232] In one embodiment, the case display interface includes a search condition input area and a case information display area;

[0233] When the computer program is executed by the processor, the following steps are also performed:

[0234] Receive the case search condition entered in the search condition input area;

[0235] The case information of the target key case is displayed in the case information display area; the case information includes at least one of the transaction subject identification, case status, suspicion confidence and case generation time; the suspicion confidence represents the probability that the target key case is suspected of illegal fund transfer.

[0236] In one embodiment, the case display interface includes a filter area, and the filter area includes multiple filter options; when the computer program is executed by the processor, the following steps are also implemented:

[0237] Receive trigger actions for target filter options;

[0238] The case information of multiple target key cases is displayed in the case information display area according to the target filtering options.

[0239] In one embodiment, the above-mentioned screening options include an unreviewed state and a reviewed state; when the computer program is executed by a processor, the following steps are also implemented:

[0240] If the target screening option is in the unreviewed state, multiple unreviewed target key cases are screened out from multiple target key cases;

[0241] Multiple unreviewed target key cases are displayed in order from high to low suspicion confidence.

[0242] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0243] Multiple unreviewed target key cases with the same suspicious confidence level are displayed in order of case generation time from recent to ancient.

[0244] In one embodiment, the above-mentioned screening options include a monitoring list and a white list, wherein the monitoring list includes identifiers of multiple transaction entities that need to be monitored, and the white list includes identifiers of multiple transaction entities that do not need to be monitored;

[0245] When the computer program is executed by the processor, the following steps are also performed:

[0246] If the target screening option is a monitoring list, determine whether the identifier of the transaction subject corresponding to each target key case is on the monitoring list;

[0247] If the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case will be displayed at the top.

[0248] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0249] Obtain transaction data of multiple transaction entities within a preset time period;

[0250] Filter out target transaction entities from multiple transaction entities based on transaction data;

[0251] The cases corresponding to the target transaction entities are identified as key cases, and a key case set is composed of multiple key cases.

[0252] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0253] For each transaction subject, the transaction data is input into a pre-set machine learning model to obtain the suspicious confidence level corresponding to the transaction subject output by the machine learning model;

[0254] The transaction subject whose suspicious confidence level is greater than a preset threshold is determined as the target transaction subject.

[0255] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0256] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0257] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for determining a suspicious case, characterized in that: The method comprises: Receive case search conditions; Searching in a pre-acquired key case collection according to the case search condition, and taking the found key case as a target key case; wherein the key case collection includes a plurality of key cases; and the key case is a case of key concern screened out within a preset time period; Displaying case information of the target key cases in the case display interface; receiving a selection operation based on the case display interface, and determining a target key case corresponding to the selection operation as a suspicious case to be reported; The case display interface includes a filter area, and the filter area includes multiple filter options; the filter options include a monitoring list and a white list, and the monitoring list includes multiple identifiers of transaction entities that need to be monitored, and the white list includes multiple identifiers of transaction entities that do not need to be monitored; The case information of the target key case displayed in the case display interface includes: If the target screening option is a monitoring list, determining whether the identifier of the transaction subject corresponding to each of the target key cases is in the monitoring list; If the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case will be displayed at the top.

2. The method according to claim 1, characterized in that After searching for cases in the pre-acquired key case set according to the case search condition, the method further includes: If the key case meeting the case search condition is not found in the key case collection, feedback information indicating that the case was not found is generated; The feedback information is displayed in the case display interface.

3. The method according to claim 2, characterized in that After the key case meeting the case search condition is not found in the key case collection, the method further includes: Searching in a pre-acquired non-key case set according to the case search condition; the non-key case set includes a plurality of non-key cases; the non-key cases are cases other than the key cases within the preset time period; If a non-key case that meets the case search condition is found in the non-key case set, the found non-key case is used as a target non-key case; The case information of the target non-key case is displayed in the case display interface.

4. The method according to claim 1, characterized in that: The case display interface includes a search condition input area and a case information display area; The receiving case search conditions include: receiving the case search condition inputted in the search condition input area; The case information of the target key case is displayed in the case display interface, including: The case information of the target key case is displayed in the case information display area; the case information includes at least one of a transaction subject identification, a case status, a suspicion confidence level and a case generation time; the suspicion confidence level represents the probability that the target key case is suspected of money laundering.

5. The method according to claim 4, characterized in that Before displaying the case information of the target key case in the case information display area, the method further includes: Receives trigger actions for target filter options.

6. The method according to claim 5, characterized in that The filtering options include unreviewed status and reviewed status; The displaying of case information of a plurality of target key cases in the case information display area according to the target screening option includes: If the target screening option is the unreviewed state, screening out a plurality of unreviewed target key cases from the plurality of target key cases; The multiple unreviewed target key cases are displayed in order from high to low suspicion confidence.

7. The method according to claim 6, characterized in that After screening out a plurality of unreviewed target key cases from the plurality of target key cases, the method further includes: The unreviewed target key cases with the same suspicious confidence level are displayed in the order of case generation time from recent to distant.

8. The method according to claim 1, characterized in that: Before searching in the pre-acquired key case set according to the case search condition, the method further includes: Acquiring transaction data of multiple transaction entities within the preset time period; According to the transaction data, a target transaction subject is selected from the plurality of transaction subjects; The case corresponding to the target transaction subject is determined as the key case, and a plurality of the key cases form the key case set.

9. The method according to claim 8, characterized in that The step of selecting a target transaction subject from the plurality of transaction subjects according to the transaction data includes: For each of the transaction entities, the transaction data is input into a preset machine learning model to obtain a suspicious confidence level corresponding to the transaction entity output by the machine learning model; A transaction subject whose suspicious confidence level is greater than a preset threshold is determined as the target transaction subject.

10. A device for determining suspicious cases, characterized in that: The device comprises: A case search condition receiving module is used to receive case search conditions; A case search module, used to search in a pre-acquired key case set according to the case search condition, and use the found key case as a target key case; wherein the key case set includes a plurality of key cases; the key case is a case of key concern screened out within a preset time period; A case information display module, used to display the case information of the target key case in the case display interface; A suspicious case determination module, configured to receive a selection operation based on the case display interface, and determine a target key case corresponding to the selection operation as a suspicious case to be reported; The case display interface includes a filter area, and the filter area includes multiple filter options; the filter options include a monitoring list and a white list, and the monitoring list includes multiple identifiers of transaction entities that need to be monitored, and the white list includes multiple identifiers of transaction entities that do not need to be monitored; The case information display module is specifically used for: If the target screening option is a monitoring list, determining whether the identifier of the transaction subject corresponding to each of the target key cases is in the monitoring list; If the identification of the transaction subject corresponding to the target key case is in the monitoring list, the target key case will be displayed at the top.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.