Information processing method for virtual network point based on behavior anomaly event and related device

Abstract

The embodiment of the application discloses a kind of virtual net point based on the information processing method of behavior abnormal event and related device, method includes: obtaining the business state and behavior data of virtual teller model of teller in current monitoring period;Retrieve the individualized compliance behavior subset of preset teller in business state;Determine the reference behavior of teller;If reference behavior is determined to be suspicious according to the individualized compliance behavior subset query, and business state is not handled business, then create the behavior abnormal event of teller according to the business state and behavior data of current monitoring period, execute step a, step b or step c, if it is determined that reference behavior is compliant, then continue the data processing of next monitoring period.Adopt the embodiment of the application, it can be realized to the monitoring of individualized behavior of teller in virtual net point, avoid to misidentify as abnormal behavior for teller individualized behavior, improve the accuracy, efficiency and real-time of virtual net point abnormal event identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital twinning, in particular to a virtual point information processing method based on behavior abnormal events and related devices. BACKGROUND

[0002] At present, the abnormal events of bank entities are often analyzed by calling monitoring videos to analyze the behaviors of the tellers, which requires a lot of manpower and material resources, and the abnormal event processing efficiency is low and not timely. SUMMARY

[0003] The embodiments of the present application provide a virtual point information processing method based on behavior abnormal events and related devices, which can realize the monitoring of the individual behavior of the tellers in the virtual point, avoid misidentifying the individual behavior of the tellers as abnormal behavior, and improve the accuracy, efficiency and real-time performance of the virtual point abnormal event identification.

[0004] In a first aspect, the embodiments of the present application provide a virtual point information processing method based on behavior abnormal events, applied to a group device of a bank service system, the bank service system comprising a collection device of an entity point and the group device, the group device being used to support data interaction between the entity point and the virtual point to realize identification of abnormal behavior of a teller of the entity point, the data interaction being a process of collecting entity information of the teller by the collection device and transmitting the entity information to the group device, the virtual point being a digital twinning model constructed according to physical data of the entity point, the physical data of the entity point comprising entity information of a plurality of construction objects of the entity point, the plurality of construction objects comprising the teller of the entity point, the digital twinning model of the virtual point comprising a virtual teller model constructed by integrating a static model and a dynamic simulation model of the teller in different scale dimensions of a fixed space, and the method comprises:

[0005] Obtaining business state and behavior data of the virtual teller model of the teller in a current monitoring period, the business state being used to indicate a business processing condition of the virtual teller model, and the business processing condition comprising an unprocessed business, an online business accepted, or an offline business accepted;

[0006] Calling a preset individual compliance behavior subset of the teller in the business state, the individual compliance behavior subset comprising at least one compliance behavior of the teller in the business state;

[0007] Determining a reference behavior of the teller according to the behavior data;

[0008] if the reference behavior is determined to be suspicious according to the personalized compliance behavior subset queried by the reference behavior, and the business state is the unprocessed business, then an abnormal behavior event of the teller is created according to the business state and the behavior data of the current monitoring period, and the abnormal behavior event is cached; and steps a, b or c are performed: step a, determining whether real-time prompting is needed according to the type of the reference behavior; step b, if it is determined that real-time prompting is needed, visualizing a risk prompt of an image of the virtual teller model in an image of the virtual site displayed by a background management center; step c, if it is determined that real-time prompting is not needed, continuing data processing of the next monitoring period;

[0009] if the reference behavior is determined to be suspicious according to the personalized compliance behavior subset queried by the reference behavior, and the business state is the unprocessed business, then an abnormal behavior event of the teller is created according to the business state and the behavior data of the current monitoring period, and the abnormal behavior event is cached; and steps a, b or c are performed: step a, determining whether real-time prompting is needed according to the type of the reference behavior; step b, if it is determined that real-time prompting is needed, visualizing a risk prompt of an image of the virtual teller model in an image of the virtual site displayed by a background management center; step c, if it is determined that real-time prompting is not needed, continuing data processing of the next monitoring period;

[0010] if the reference behavior is determined to be suspicious according to the personalized compliance behavior subset queried by the reference behavior, and the business state is the unprocessed business, then an abnormal behavior event of the teller is created according to the business state and the behavior data of the current monitoring period, and the abnormal behavior event is cached; and steps a, b or c are performed: step a, determining whether real-time prompting is needed according to the type of the reference behavior; step b, if it is determined that real-time prompting is needed, visualizing a risk prompt of an image of the virtual teller model in an image of the virtual site displayed by a background management center; step c, if it is determined that real-time prompting is not needed, continuing data processing of the next monitoring period;

[0011] if the reference behavior is determined to be suspicious according to the personalized compliance behavior subset queried by the reference behavior, and the business state is the unprocessed business, then an abnormal behavior event of the teller is created according to the business state and the behavior data of the current monitoring period, and the abnormal behavior event is cached; and steps a, b or c are performed: step a, determining whether real-time prompting is needed according to the type of the reference behavior; step b, if it is determined that real-time prompting is needed, visualizing a risk prompt of an image of the virtual teller model in an image of the virtual site displayed by a background management center; step c, if it is determined that real-time prompting is not needed, continuing data processing of the next monitoring period;

[0012] if the reference behavior is determined to be suspicious according to the personalized compliance behavior subset queried by the reference behavior, and the business state is the unprocessed business, then an abnormal behavior event of the teller is created according to the business state and the behavior data of the current monitoring period, and the abnormal behavior event is cached; and steps a, b or c are performed: step a, determining whether real-time prompting is needed according to the type of the reference behavior; step b, if it is determined that real-time prompting is needed, visualizing a risk prompt of an image of the virtual teller model in an image of the virtual site displayed by a background management center; step c, if it is determined that real-time prompting is not needed, continuing data processing of the next monitoring period;

[0013] In a second aspect, embodiments of the present application provide a virtual site information processing device based on behavior abnormality events, applied to a group device of a bank service system, the bank service system comprising a collection device of an entity site and the group device, the group device being used to support data interaction between the entity site and the virtual site to realize identification of abnormal behavior of a teller of the entity site, the data interaction being a process of collecting entity information of the teller by the collection device and transmitting the entity information to the group device, the virtual site being a digital twin model constructed according to physical data of the entity site, the physical data of the entity site comprising entity information of a plurality of construction objects of the entity site, the plurality of construction objects comprising the teller of the entity site, the digital twin model of the virtual site comprising a virtual teller model constructed by integrating static models and dynamic simulation models of the teller in fixed space different scale dimensions, and the device comprises an acquisition unit, a calling unit, a determination unit, a processing unit and a prediction unit, wherein,

[0014] The acquisition unit is configured to acquire service state and behavior data of the virtual teller model of the teller in a current monitoring period, the service state being used to indicate a service processing condition of the virtual teller model, and the service processing condition including an unprocessed service, an online service accepted, or an offline service accepted.

[0015] The calling unit is configured to call a preset personalized compliance behavior subset of the teller in the service state, the personalized compliance behavior subset including at least one compliance behavior of the teller in the service state.

[0016] The determining unit is configured to determine a reference behavior of the teller according to the behavior data.

[0017] The processing unit is configured to, if it is determined that the reference behavior is suspicious according to the personalized compliance behavior subset queried based on the reference behavior, and the service state is the unprocessed service, create a behavior abnormality event of the teller according to the service state and the behavior data in the current monitoring period, and cache the behavior abnormality event; and perform step a, step b, or step c: step a, determine whether real-time reminding is needed according to a type of the reference behavior; step b, if it is determined that real-time reminding is needed, visually prompt a risk of the virtual teller model in an image of the virtual site displayed on a background management center; and step c, if it is determined that real-time reminding is not needed, continue data processing in a next monitoring period.

[0018] The prediction unit is configured to, if it is determined that the reference behavior is suspicious according to the personalized compliance behavior subset queried based on the reference behavior, and the service state is the online service accepted or the offline service accepted, determine a target service currently accepted by the teller, and predict whether the behavior of the teller is abnormal according to a service condition of the target service.

[0019] The processing unit is further configured to, if it is predicted that the behavior of the teller is abnormal, create the behavior abnormality event, and cache the behavior abnormality event; and perform the step a, the step b, or the step c.

[0020] The processing unit is further configured to, if it is predicted that the behavior of the teller is compliant, continue data processing in a next monitoring period.

[0021] The processing unit is further configured to, if it is determined that the reference behavior is compliant according to the personalized compliance behavior subset queried based on the reference behavior, continue data processing in a next monitoring period.

[0022] In a third aspect, an electronic device is provided and includes a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor. The program includes instructions for performing some or all of the steps described in the method of the first aspect.

[0023] In a fourth aspect, a computer-readable storage medium is provided and stores a computer program for electronic data exchange. The computer program causes a computer to perform some or all of the steps described in the method of the first aspect.

[0024] It can be seen that, in the embodiments of the present application, the group device can acquire the business state and behavior data of the virtual teller model of the teller in the current monitoring period, and call the preset personalized compliance behavior subset of the teller in the business state, then determine the reference behavior of the teller according to the behavior data, if the reference behavior is determined to be suspicious according to the reference behavior query of the personalized compliance behavior subset, and the business state is unprocessed business, then create a behavior abnormal event of the teller according to the business state and behavior data of the current monitoring period, and cache the behavior abnormal event, and perform steps a, b or c: step a, determine whether real-time reminding is needed according to the type of the reference behavior; step b, if it is determined that real-time reminding is needed, then the image of the virtual teller model in the image of the virtual site displayed by the background management center is visually prompted; step c, if it is determined that real-time reminding is not needed, then continue data processing of the next monitoring period, if the reference behavior is determined to be suspicious according to the reference behavior query of the personalized compliance behavior subset, and the business state is online business or offline business, then determine the target business currently handled by the teller, and predict whether the behavior of the teller is abnormal according to the business situation of the target business, if the behavior of the teller is predicted to be abnormal, then create a behavior abnormal event, and cache the behavior abnormal event, and perform steps a, b or c, if the behavior of the teller is predicted to be compliant, then continue data processing of the next monitoring period, finally, if the reference behavior is determined to be compliant according to the reference behavior query of the personalized compliance behavior set, then continue data processing of the next monitoring period. In this way, the personalized behavior of the teller in the virtual site can be monitored, the teller's personalized behavior can be avoided from being misidentified as abnormal behavior, and the accuracy, efficiency and real-time performance of the abnormal event identification of the virtual site can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other accompanying drawings can be obtained by those skilled in the art without any creative effort on the basis of these accompanying drawings.

[0026] Figure 1 is a schematic diagram of an architecture of a virtual point based on behavior abnormal event information processing system provided by an embodiment of the present application;

[0027] Figure 2 is a schematic diagram of a flow of a virtual point based on behavior abnormal event information processing method provided by an embodiment of the present application;

[0028] Figure 3 is a schematic diagram of a structure of an electronic device provided by an embodiment of the present application;

[0029] Figure 4A is a schematic diagram of a virtual point based on behavior abnormal event information processing apparatus provided by an embodiment of the present application;

[0030] Figure 4B is a schematic diagram of another virtual point based on behavior abnormal event information processing apparatus provided by an embodiment of the present application;

[0031] Figure 4C is a schematic diagram of another virtual point based on behavior abnormal event information processing apparatus provided by an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other accompanying drawings can be obtained by those skilled in the art without any creative effort on the basis of these accompanying drawings.

[0033] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned accompanying drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0034] Reference to“an embodiment” herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase“in an embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that any of the embodiments described herein can be incorporated into any other embodiment.

[0035] The group device involved in the embodiments of the present application can be an electronic device, which can include various handheld devices, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to a wireless modem, and various forms of user equipment (UE), mobile stations (MS), terminal devices, etc. with wireless communication functions. For convenience of description, the above-mentioned devices are collectively referred to as electronic devices.

[0036] At present, the abnormal events of tellers in bank entity outlets are often analyzed by calling monitoring videos to analyze the behaviors of tellers, which requires a huge amount of manpower and material resources, and often has low abnormal event processing efficiency and is not timely enough.

[0037] To solve the above problems, the present application provides a virtual point based on behavior abnormal event information processing method and related device, which will be described in detail below.

[0038] Please refer to Figure 1 , Figure 1 is a schematic diagram of the architecture of a virtual point based on behavior abnormal event information processing system provided by the embodiments of the present application. The system architecture can include a bank service system 100, which includes a collection device 101 and a group device 102.

[0039] The group device 102 is used to support data interaction between the entity point and the virtual point to realize the identification of the abnormal behavior of the teller of the entity point. The data interaction refers to the process of collecting the entity information of the teller by the collection device 101 and transmitting the entity information to the group device 102.

[0040] The bank service system 100 can include a plurality of entity points, a plurality of bank points, and a virtual point corresponding to each entity point. The virtual point is a digital twin model constructed according to the physical data of the entity point. The physical data of the entity point includes entity information of a plurality of construction objects of the entity point, and the plurality of construction objects include tellers of the entity point. The digital twin model of the virtual point includes a virtual teller model constructed by integrating static models and dynamic simulation models of the tellers in different scale dimensions of a fixed space.

[0041] The group device 102 can process data of the virtual teller model for multiple monitoring periods, the data being collected by the collection device 101 and sent to the group device 102, the data including business state and behavior data, and the business processing including unprocessed business, online business, or offline business.

[0042] The group device 102 can be an electronic device in the embodiments of the present application. For example, the group device 102 can be a notebook computer, a tablet computer, a mobile phone, or the like, or a smart watch or the like wearable electronic device.

[0043] In one possible example, the group device 102 can obtain the business state and behavior data of the virtual teller model of the teller in the current monitoring period, and call the preset individualized compliance behavior subset of the teller in the business state. The group device 102 then determines the reference behavior of the teller according to the behavior data. If the group device 102 determines that the reference behavior is suspicious according to the reference behavior query of the individualized compliance behavior subset, and the business state is unprocessed business, the group device 102 creates a behavior abnormal event of the teller according to the business state and behavior data of the current monitoring period, and caches the behavior abnormal event. The group device 102 then performs steps a, b, or c: step a, determines whether real-time prompting is needed according to the type of the reference behavior; step b, if it is determined that real-time prompting is needed, visualizes the image of the virtual teller model in the image of the virtual site displayed on the background management center; step c, if it is determined that real-time prompting is not needed, continues data processing of the next monitoring period. If the group device 102 determines that the reference behavior is suspicious according to the reference behavior query of the individualized compliance behavior subset, and the business state is online business or offline business, the group device 102 determines the target business currently handled by the teller, and predicts whether the behavior of the teller is abnormal according to the business state of the target business. If the group device 102 predicts that the behavior of the teller is abnormal, the group device 102 creates a behavior abnormal event and caches the behavior abnormal event. The group device 102 then performs steps a, b, or c. If the group device 102 predicts that the behavior of the teller is compliant, the group device 102 continues data processing of the next monitoring period. Finally, if the group device 102 determines that the reference behavior is compliant according to the reference behavior query of the individualized compliance behavior set, the group device 102 continues data processing of the next monitoring period. In this way, the individualized behavior of the teller in the virtual site can be monitored, the teller's individualized behavior can be avoided from being misidentified as abnormal behavior, and the accuracy, efficiency, and real-time performance of the abnormal event identification of the virtual site can be improved.

[0044] It should be noted that two or more can be referred to as multiple in the present application, and the subsequent description will not be repeated.

[0045] Please refer to Figure 2 , Figure 2is a flowchart of a virtual point of presence information processing method based on behavior abnormal events provided by the present application, applied to a group device of a bank service system, the bank service system comprising a collection device of a physical point of presence and the group device, the group device being used to support data interaction between the physical point of presence and the virtual point of presence to realize identification of abnormal behavior of a teller of the physical point of presence, the data interaction referring to a process of collecting entity information of the teller by the collection device and transmitting the entity information to the group device, the virtual point of presence being a digital twin model constructed according to physical data of the physical point of presence, the physical data of the physical point of presence comprising entity information of a plurality of construction objects of the physical point of presence, the plurality of construction objects comprising the teller of the physical point of presence, the digital twin model of the virtual point of presence comprising a virtual teller model constructed by integrating a static model and a dynamic simulation model of the teller in different scale dimensions of a fixed space, as shown in the figure, the virtual point of presence information processing method based on behavior abnormal events comprises the following operations.

[0046] S201, acquiring business state and behavior data of the virtual teller model of the teller in a current monitoring period, the business state being used to indicate a business processing condition of the virtual teller model, the business processing condition comprising unprocessed business, online business accepted, or offline business accepted.

[0047] Among them, the collection device can be used to collect the business state and the behavior of the teller according to the monitoring period, generate the business state and the behavior data, and send the business state and the behavior data to the group device. The monitoring period can be artificially set or system default. One monitoring period can be 5 minutes, 10 minutes or 30 minutes, which is not limited here.

[0048] Among them, the virtual point of presence can provide bank point of presence services such as inquiry, account opening, transfer, signing, credit card, etc. The user can initiate a handling request through a terminal device for the above bank point of presence services.

[0049] S202, calling a preset individualized compliance behavior subset of the teller in the business state, the individualized compliance behavior subset comprising at least one compliance behavior of the teller in the business state.

[0050] Among them, there are different individualized compliance behavior subsets for different business states, that is, there are different requirements for the behavior of the teller under different business states.

[0051] S203, determining a reference behavior of the teller according to the behavior data.

[0052] In a specific implementation, the behavior data can be classified by behavior, at least one teller behavior is classified, teller interference behavior is filtered out, and at least one teller behavior after the teller interference behavior is filtered out is taken as a reference behavior.

[0053] The teller interference behavior refers to some action of the teller with small amplitude and irrelevant to the business handling, for example, the teller shakes legs while sitting on a chair, the teller holds a mouse, the teller releases the mouse, and the like, which are not limited herein.

[0054] S204, if it is determined that the reference behavior is suspicious according to the reference behavior query of the personalized compliance behavior subset, and the business state is the unprocessed business, an abnormal behavior event of the teller is created according to the business state and the behavior data of the current monitoring period, and the abnormal behavior event is cached; and steps a, b or c are performed: step a, whether real-time reminding is needed is determined according to the type of the reference behavior; step b, if it is determined that real-time reminding is needed, the image of the virtual teller model in the image of the virtual site displayed by the background management center is visually prompted; step c, if it is determined that real-time reminding is not needed, data processing of the next monitoring period is continued.

[0055] The suspicious reference behavior can be that boat socks are worn on feet, the boat socks slide to the bottom of the feet, the hands are stretched to pull up, the hands are stretched to put under the armpit, the armpit is itchy, the money is counted, the banknotes are not counted one by one, a dispute with a customer and inappropriate conflictive behavior occur in the business handling process, the conflictive behavior can be cursing, punching / pointing at others with fingers, knocking the window glass, and the like, which are not limited herein.

[0056] The group device can visually prompt the image of the virtual teller model in the image of the virtual site displayed by the background management center, business handling prompt, business allocation prompt, business cancellation prompt, business order-taking prompt, and the like, which are not limited herein.

[0057] The setting period, setting time and display mode of the visual risk prompt can be preset in advance, and the visual risk prompt can be classified by level, and the higher the level is, the higher the abnormal degree of the teller behavior is.

[0058] S205, if it is determined that the reference behavior is suspicious according to the reference behavior query of the personalized compliance behavior subset, and the business state is the online business or the offline business, a target business currently handled by the teller is determined; and whether the behavior of the teller is abnormal is predicted according to the business situation of the target business; and

[0059] Among these measures, when handling online or offline business, it is necessary to determine whether the teller's behavior is suspicious or abnormal. Tellers also have specific business behaviors related to the target business. Considering that the teller's business behaviors and other behaviors may differ for different target businesses, it is necessary to predict the teller's behavior based on the business situation.

[0060] S206. If abnormal behavior of the teller is predicted, create the abnormal behavior event and cache the abnormal behavior event; and execute step a, step b or step c.

[0061] The group device includes a behavior anomaly event database, which includes a sub-behavior anomaly event database for each teller. After creating a behavior anomaly event for a teller, the group device will cache the behavior anomaly event in the corresponding sub-behavior anomaly event database.

[0062] S207. If the teller's behavior is predicted to be compliant, then continue data processing for the next monitoring cycle.

[0063] S208. If the reference behavior is found to be compliant based on the personalized compliance behavior set, then data processing for the next monitoring cycle continues.

[0064] It can be seen that in the embodiments of the present application, the group device can obtain the business state and behavior data of the virtual teller model of the teller in the current monitoring period, and call the preset personalized compliance behavior subset of the teller in the business state, and then determine the reference behavior of the teller according to the behavior data, and if the reference behavior is determined to be suspicious according to the query of the personalized compliance behavior subset, and the business state is an unprocessed business, then create a behavior abnormal event of the teller according to the business state and behavior data of the current monitoring period, and cache the behavior abnormal event, and perform steps a, b or c: step a, determine whether real-time reminding is needed according to the type of the reference behavior; step b, if it is determined that real-time reminding is needed, then the image of the virtual teller model in the image of the virtual site displayed on the background management center is visually prompted; step c, if it is determined that real-time reminding is not needed, then continue data processing of the next monitoring period, if the reference behavior is determined to be suspicious according to the query of the personalized compliance behavior subset, and the business state is to handle online business or offline business, then determine the target business currently handled by the teller, and predict whether the behavior of the teller is abnormal according to the business situation of the target business, and if it is predicted that the behavior of the teller is abnormal, then create a behavior abnormal event, and cache the behavior abnormal event, and perform steps a, b or c, if it is predicted that the behavior of the teller is compliant, then continue data processing of the next monitoring period, and finally, if the reference behavior is determined to be compliant according to the query of the personalized compliance behavior set, then continue data processing of the next monitoring period. In this way, the personalized behavior of the teller in the virtual site can be monitored, the teller's personalized behavior can be avoided from being misidentified as abnormal behavior, and the accuracy, efficiency and real-time performance of the virtual site abnormal event identification can be improved.

[0065] In one possible example, the business situation of the target business includes business information of the target business and behavior data of a customer requesting to handle the target business, and the method of predicting whether the behavior of the teller is abnormal according to the business situation of the target business can further include the following steps: predicting whether the reference behavior of the teller has violated the rules according to the business information of the target business and the behavior data of the customer; if yes, then predicting that the behavior of the teller is abnormal; and if no, then predicting that the behavior of the teller is compliant.

[0066] Wherein, if the reference behavior of the teller deviates from the necessary business handling behavior of the business information of the target business, then the reference behavior of the teller can be abnormal or non-compliant.

[0067] Wherein, when the teller handles the target service, the reference behavior of the teller and the behavior of the customer have certain relevance, for example: the customer can only perform the next business operation step after completing a business operation step, when the customer's behavior is abnormal, for example: there are abuses, knocking the service window, etc., the normal business handling behavior of the teller will also be affected; for example: the customer's card actually has no money, but the teller is forced to take out money, causing a quarrel, and the teller has abnormal behavior due to lack of experience, and needs to intervene in real time to avoid escalation of the dispute; for example: the customer's card originally has money, and the bank misappropriates it, causing the customer's bank card to display an incorrect balance and cannot be withdrawn, and the teller has abnormal behavior due to lack of experience, and needs to intervene in real time to avoid escalation of the dispute; Therefore, when predicting whether the teller's behavior is in line with the regulations when handling online or offline services, the user's behavior information needs to be considered as an influencing factor for prediction.

[0068] Wherein, the acquisition device can also acquire the behavior information of the customer and send the behavior information to the group device.

[0069] In a specific implementation, the group device predicts whether the reference behavior of the teller is in violation of the regulations according to the necessary business handling behavior of the target service handled by the teller and the behavior information of the customer handling the target service, obtains a prediction result, and if the prediction result is that the reference behavior is in violation of the regulations, it is predicted that the behavior of the teller is abnormal; if the prediction result is that the reference behavior is not in violation of the regulations, it is predicted that the behavior of the teller is in line with the regulations.

[0070] As can be seen, in this example, whether the reference behavior of the teller is in line with the regulations is predicted according to the business information of the target service handled by the teller and the behavior information of the customer, which helps to improve the accuracy of predicting whether the behavior of the teller is abnormal.

[0071] In one possible example, the method can include the following steps: determining a state label according to the business state, the state label including an idle label corresponding to the unprocessed business, an online service handling label corresponding to the processed online business, and an offline service handling label corresponding to the processed offline business; querying the preset personalized compliance behavior set of the teller with the state label as a query identifier, obtaining a personalized compliance behavior subset corresponding to the state label, and the personalized compliance behavior set including a corresponding relationship between the state label and the personalized compliance behavior subset.

[0072] Wherein, the state label is associated with the business state, the unprocessed business corresponds to the idle label, the processed online business corresponds to the online service handling label, and the processed offline business corresponds to the offline service handling label.

[0073] As can be seen, in this example, using the status label associated with the business status as the query identifier to query the preset personalized compliance behavior subset under the current business status is beneficial to improving the retrieval efficiency of the preset personalized compliance behavior subset, and further beneficial to improving the efficiency of identifying abnormal events in virtual outlets.

[0074] In one possible example, before acquiring the business status and behavior data of the virtual teller model of the teller in the current monitoring period, the above method may include the following steps: collecting sample data of the virtual teller model of the teller within a preset time period, the sample data including first sample behavior data of the teller in the business status of unprocessed business, second sample behavior data in the business status of accepting online business, and third sample data in the business status of accepting offline business; performing statistical analysis on the first sample behavior data to obtain at least one first compliance behavior in the business status of unprocessed business, and creating a personalized compliance behavior subset corresponding to the status label of unprocessed business based on the correspondence between the first compliance behavior and the status label of unprocessed business; performing statistical analysis on the second sample behavior data to obtain at least one second compliance behavior in the business status of accepting online business, and creating a personalized compliance behavior subset corresponding to the status label of accepting online business based on the correspondence between the second compliance behavior and the status label of accepting online business; performing statistical analysis on the third sample behavior data to obtain at least one second compliance behavior in the business status of accepting offline business, and creating a personalized compliance behavior subset corresponding to the status label of accepting offline business based on the correspondence between the second compliance behavior and the status label of accepting offline business.

[0075] The first sample behavioral data consists of teller behavior data during a preset time period when there are no transactions being processed; the second sample behavioral data consists of teller behavior data during a preset time period when there are online transactions being processed; and the third sample behavioral data consists of teller behavior data during a preset time period when there are offline transactions being processed. The first sample behavioral data includes at least one first teller behavior, the first sample behavioral data includes at least one second teller behavior, and the first sample behavioral data includes at least one third teller behavior.

[0076] The statistical analysis on the first sample behavior data is a statistical analysis on at least one first teller behavior in the first sample data, and a compliance behavior in the at least one first teller behavior is screened out as at least one first compliance behavior. The statistical analysis on the second sample behavior data is a statistical analysis on at least one second teller behavior in the second sample data, and a compliance behavior in the at least one second teller behavior is screened out as at least one second compliance behavior. The statistical analysis on the third sample behavior data is a statistical analysis on at least one third teller behavior in the third sample data, and a compliance behavior in the at least one third teller behavior is screened out as at least one third compliance behavior.

[0077] In specific implementation, the group device collects a plurality of teller behaviors corresponding to different business states within a preset time as sample data. Specifically, at least one first teller behavior of a teller in a state of unprocessed business within the preset time is taken as first sample behavior data, at least one second teller behavior of a teller in a state of online business accepted within the preset time is taken as first sample behavior data, and at least one third teller behavior of a teller in a state of offline business accepted within the preset time is taken as third sample behavior data. Further, statistical analysis is performed on at least one first teller behavior in the first sample data, a compliance behavior in the at least one first teller behavior is screened out as at least one first compliance behavior, and a personalized compliance behavior subset corresponding to a state label of unprocessed business is created according to a corresponding relationship between the first compliance behavior and the state label of unprocessed business. Statistical analysis is performed on at least one second teller behavior in the second sample data, a compliance behavior in the at least one second teller behavior is screened out as at least one second compliance behavior, and a personalized compliance behavior subset corresponding to a state label of online business accepted is created according to a corresponding relationship between the second compliance behavior and the state label of online business accepted. Statistical analysis is performed on at least one third teller behavior in the third sample data, a compliance behavior in the at least one third teller behavior is screened out as at least one third compliance behavior, and a personalized compliance behavior subset corresponding to a state label of offline business accepted is created according to a corresponding relationship between the second compliance behavior and the state label of offline business accepted.

[0078] It can be seen that in the present example, the group device collects sample data of the virtual teller model in different business states within a preset time, and respectively performs statistical analysis on the first sample data, the second sample data and the third sample data, to obtain at least one first compliance behavior corresponding to the first sample data, at least one second compliance behavior corresponding to the second sample data, and at least one third compliance behavior corresponding to the third sample data. Further, according to the correspondence between the first compliance behavior and the state label of the unprocessed business, the correspondence between the second compliance behavior and the state label of the online business accepted, and the correspondence between the third compliance behavior and the state label of the offline business accepted, the fine planning compliance subset corresponding to different state labels is created, which is conducive to improving the accuracy of the compliance behavior in the individualized compliance subset corresponding to different business states.

[0079] In one possible example, before the virtual teller model of the teller is acquired, the business state and behavior data of the current monitoring period, the above method can further include the following steps: displaying a compliance behavior setting page, the compliance behavior setting page including a state label and an individualized compliance behavior setting area corresponding to the state label, the individualized compliance behavior setting area supporting user self-entry and / or preset behavior selection; marking the custom compliance behavior entered by the teller and / or the preset compliance behavior selected as the compliance behavior corresponding to the state label; creating an individualized compliance behavior subset corresponding to the state label according to the correspondence between the marked compliance behavior and the state label; repeating the above process until the individualized compliance behavior subset corresponding to all state labels is set.

[0080] Among them, the preset behavior is associated with the business state, and the same or different preset behaviors can be set for different business states. At least one first preset compliance behavior is set for unprocessed business, at least one second preset compliance behavior is set for offline business accepted, and at least one third preset compliance behavior is set for online business accepted.

[0081] In a specific implementation, the custom compliance behavior entered by the teller and / or the preset compliance behavior selected is marked as the compliance behavior corresponding to the state label, and the compliance behavior corresponding to the state label of the unprocessed business, the compliance behavior corresponding to the state label of the offline business accepted, and the compliance behavior corresponding to the state label of the online business accepted are respectively set to the individualized compliance behavior setting area corresponding to the state label of the unprocessed business, the state label of the offline business accepted, and the state label of the online business accepted in the compliance behavior setting page.

[0082] It can be seen that in the present example, by corresponding the self-defined behavior and / or the preset compliance behavior autonomously inputted as the compliance behavior corresponding to the state label, and creating the personalized compliance behavior subset corresponding to the state label according to the correspondence between the marked compliance behavior and the state label, the accuracy of the compliance behavior in the personalized compliance subset corresponding to different business states is improved.

[0083] In one possible example, the plurality of construction objects further include the following elements of the entity site: a business process, a device, and a site environment; and the entity information includes static entity information and dynamic entity information, the static entity information including identity information, attribute information, and geometric information of the construction object, and the dynamic entity information including state information, position information, and process information of the construction object.

[0084] It can be seen that in the present example, the construction object includes elements such as the business process, the device, and the site environment of the entity site, and the entity information includes static entity information and dynamic entity information, which is conducive to constructing a virtual site corresponding to the entity site with higher simulation.

[0085] In one possible example, before the virtual teller model of the teller is obtained according to the business state and behavior data of the current monitoring period, the method can further include the following steps: constructing a static model of each construction object according to the static entity information of the plurality of tellers; constructing a dynamic simulation model of each construction object according to the dynamic entity information of the plurality of tellers; and integrating the static model and the dynamic simulation model of the teller at different scale dimensions in a fixed space based on a multi-scale model fusion modeling method and an anchor-based virtual-real entity calibration method, to obtain the virtual teller model corresponding to the teller.

[0086] The group device can utilize the multi-scale model fusion modeling method and the anchor-based virtual-real entity calibration method to construct the virtual teller model.

[0087] When the construction object includes a teller, it is assumed that the behavior activities of the teller at different times are different, and the behavior activities of the teller at different times are the dynamic entity information of the teller. At this time, the behavior activities of the teller can be dynamically modeled by using an existing behavior model to construct a dynamic simulation model.

[0088] It can be seen that in the present example, the group device integrates the static model of each construction object constructed according to the static entity information and the dynamic simulation model of each construction object constructed according to the dynamic entity information at different scale dimensions in a fixed space based on the multi-scale model fusion modeling method and the anchor-based virtual-real entity calibration method, to obtain the virtual teller model corresponding to the teller, which is conducive to improving the simulation degree of the virtual teller model construction.

[0089] Please refer toFigure 3 , Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application, as shown in the figure, the electronic device is applied to a group device of a bank service system, the bank service system includes a collection device of a physical point and the group device, the group device is used to support data interaction between the physical point and a virtual point to realize identification of abnormal behavior of a clerk of the physical point, the data interaction refers to a process of collecting entity information of the clerk by the collection device and transmitting the entity information to the group device, the virtual point is a digital twin model constructed according to physical data of the physical point, the physical data of the physical point includes entity information of a plurality of construction objects of the physical point, the plurality of construction objects include the clerk of the physical point, the digital twin model of the virtual point includes a virtual clerk model constructed by integrating a static model and a dynamic simulation model of the clerk in different scale dimensions of a fixed space, the electronic device includes a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs are configured to instruct the processor to execute the following steps:

[0090] obtain business state and behavior data of the virtual clerk model of the clerk in a current monitoring period, the business state is used to indicate a business processing condition of the virtual clerk model, and the business processing condition includes an unprocessed business, an online business accepted or an offline business accepted;

[0091] call a preset individualized compliance behavior subset of the clerk in the business state, the individualized compliance behavior subset includes at least one compliance behavior of the clerk in the business state;

[0092] determine a reference behavior of the clerk according to the behavior data;

[0093] if it is determined that the reference behavior is suspicious according to the reference behavior and the individualized compliance behavior subset, and the business state is the unprocessed business, create a behavior abnormal event of the clerk according to the business state and the behavior data of the current monitoring period, and cache the behavior abnormal event; and execute steps a, b or c: step a, determine whether real-time reminding is needed according to the type of the reference behavior; step b, if it is determined that real-time reminding is needed, visually risk prompt the image of the virtual clerk model in the image of the virtual point displayed by a background management center; step c, if it is determined that real-time reminding is not needed, continue data processing of the next monitoring period;

[0094] if the reference behavior is determined to be suspicious according to the query of the reference behavior on the personalized compliance behavior subset and the business state is the online business or the offline business, determining a target business currently received by the clerk; and predicting whether the behavior of the clerk is abnormal according to the business condition of the target business; and

[0095] if the behavior of the clerk is predicted to be abnormal, creating the behavior abnormal event and caching the behavior abnormal event; and executing the step a, the step b or the step c;

[0096] if the behavior of the clerk is predicted to be compliant, continuing the data processing of the next monitoring period;

[0097] if the reference behavior is determined to be compliant according to the query of the reference behavior on the personalized compliance behavior set, continuing the data processing of the next monitoring period.

[0098] It can be seen that in the embodiment of the present application, the electronic device can obtain the business state and behavior data of the virtual clerk model of the clerk in the current monitoring period, and call the preset personalized compliance behavior subset of the clerk in the business state, then determine the reference behavior of the clerk according to the behavior data, if the reference behavior is determined to be suspicious according to the query of the reference behavior on the personalized compliance behavior subset, and the business state is the unprocessed business, then create the behavior abnormal event of the clerk according to the business state and behavior data in the current monitoring period, and cache the behavior abnormal event, and execute the step a, the step b or the step c: the step a, determine whether real-time reminding is needed according to the type of the reference behavior; the step b, if it is determined that real-time reminding is needed, visually risk prompt the image of the virtual clerk model in the image of the virtual site displayed on the background management center; the step c, if it is determined that real-time reminding is not needed, continue the data processing of the next monitoring period, if the reference behavior is determined to be suspicious according to the query of the reference behavior on the personalized compliance behavior subset, and the business state is the online business or the offline business, determine the target business currently received by the clerk, and predict whether the behavior of the clerk is abnormal according to the business condition of the target business, if the behavior of the clerk is predicted to be abnormal, create the behavior abnormal event and cache the behavior abnormal event, and execute the step a, the step b or the step c, if the behavior of the clerk is predicted to be compliant, continue the data processing of the next monitoring period, finally, if the reference behavior is determined to be compliant according to the query of the reference behavior on the personalized compliance behavior set, continue the data processing of the next monitoring period. In this way, the personalized behavior of the clerk in the virtual site can be monitored, the personalized behavior of the clerk can be avoided to be misidentified as abnormal behavior, and the accuracy, efficiency and real-time performance of the abnormal event identification of the virtual site can be improved.

[0099] In a possible example, in the case where the business condition of the target service includes business information of the target service and behavior data of a customer requesting to handle the target service, the program for predicting whether the behavior of the clerk is abnormal according to the business condition of the target service includes instructions for performing the following steps:

[0100] predicting whether the reference behavior of the clerk has violated the rules according to the business information of the target service and the behavior data of the customer;

[0101] if yes, predicting that the behavior of the clerk is abnormal;

[0102] if no, predicting that the behavior of the clerk is compliant.

[0103] In a possible example, in the case where the preset individualized compliant behavior subset of the clerk in the business state is invoked, the program includes instructions for performing the following steps:

[0104] determining a state tag according to the business state, the state tag including an idle tag corresponding to the unprocessed service, an online service handling tag corresponding to the online service being handled, and an offline service handling tag corresponding to the offline service being handled;

[0105] querying a preset individualized compliant behavior set of the clerk by taking the state tag as a query tag, obtaining an individualized compliant behavior subset corresponding to the state tag, and the individualized compliant behavior set including a corresponding relationship between a state tag and an individualized compliant behavior subset.

[0106] In a possible example, before the business state and the behavior data of the virtual clerk model of the clerk in the current monitoring period are obtained, the program further includes instructions for performing the following steps:

[0107] collecting sample data of the virtual clerk model of the clerk in a preset time period, the sample data including first sample behavior data of the clerk in the business state of the unprocessed service, second sample behavior data of the clerk in the business state of the online service being handled, and third sample data of the clerk in the business state of the offline service being handled;

[0108] performing statistical analysis on the first sample behavior data to obtain at least one first compliant behavior in the business state of the unprocessed service, and creating an individualized compliant behavior subset corresponding to a state tag of the unprocessed service according to a corresponding relationship between the first compliant behavior and the state tag of the unprocessed service;

[0109] statistical analysis is performed on the second sample behavior data to obtain at least one second compliance behavior in the state of the online service, and a personalized compliance behavior subset corresponding to the state label of the online service is created according to the correspondence between the second compliance behavior and the state label of the online service;

[0110] statistical analysis is performed on the third sample behavior data to obtain at least one second compliance behavior in the state of the offline service, and a personalized compliance behavior subset corresponding to the state label of the offline service is created according to the correspondence between the second compliance behavior and the state label of the offline service.

[0111] In one possible example, before the obtaining of the business state and behavior data of the virtual teller model of the teller in the current monitoring period, the program further includes instructions for performing the following steps:

[0112] A compliance behavior setting page is displayed, the compliance behavior setting page including a state label and a personalized compliance behavior setting area corresponding to the state label, and the personalized compliance behavior setting area supporting user autonomous entry and / or preset behavior selection;

[0113] The custom compliance behavior autonomously entered by the teller and / or the selected preset compliance behavior are marked as the compliance behavior corresponding to the state label;

[0114] A personalized compliance behavior subset corresponding to the state label is created according to the correspondence between the marked compliance behavior and the state label;

[0115] The above process is repeated until the personalized compliance behavior subsets corresponding to all state labels are set.

[0116] In one possible example, before the obtaining of the business state and behavior data of the virtual teller model of the teller in the current monitoring period, the program includes instructions for performing the following steps:

[0117] A static model of each construction object is constructed according to static entity information of the plurality of tellers;

[0118] A dynamic simulation model of each construction object is constructed according to dynamic entity information of the plurality of tellers;

[0119] Based on a multi-scale model fusion modeling method and an anchor point-based virtual-real entity calibration method, the static model and the dynamic simulation model of the teller are integrated in fixed space and different scale dimensions to obtain the virtual teller model corresponding to the teller.

[0120] The above describes the scheme of the embodiments of the present application mainly from the perspective of the process of executing the method. It can be understood that, in order to implement the above functions, the electronic device comprises a hardware structure and / or a software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the examples described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in the form of hardware or computer software driving hardware depends on the specific application of the technical solution and the design constraints. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0121] The embodiments of the present application can divide the functional units of the electronic device according to the above method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical functional division. When actually implemented, there can be another division method.

[0122] In the case of dividing each functional module according to each function, Figure 4A A schematic diagram of a virtual point information processing device based on behavior abnormal event is given, as shown in Figure 4A The device is applied to a group equipment of a bank service system, the bank service system comprises a collection device of a physical point and the group equipment, the group equipment is used to support data interaction between the physical point and the virtual point to realize identification of abnormal behavior of a clerk of the physical point, the data interaction refers to a process that the collection device collects entity information of the clerk and transmits the entity information to the group equipment, the virtual point is a digital twin model constructed according to physical data of the physical point, the physical data of the physical point comprises entity information of a plurality of construction objects of the physical point, the plurality of construction objects comprise the clerk of the physical point, the digital twin model of the virtual point comprises a virtual clerk model constructed by integrating a static model and a dynamic simulation model of the clerk in a fixed space in different scale dimensions, the virtual point information processing device 400 based on the behavior abnormal event can comprise an acquisition unit 401, a calling unit 402, a determination unit 403, a processing unit 404 and a prediction unit 405, wherein

[0123] The acquisition unit 401 is configured to acquire service state and behavior data of the virtual teller model of the teller in a current monitoring period, the service state being used to indicate a service processing situation of the virtual teller model, and the service processing situation including an unprocessed service, an online service accepted, or an offline service accepted.

[0124] The calling unit 402 is configured to call a preset personalized compliance behavior subset of the teller in the service state, the personalized compliance behavior subset including at least one compliance behavior of the teller in the service state.

[0125] The determination unit 403 is configured to determine a reference behavior of the teller according to the behavior data.

[0126] The processing unit 404 is configured to, if it is determined that the reference behavior is suspicious by querying the personalized compliance behavior subset according to the reference behavior and the service state is the unprocessed service, create a behavior anomaly event of the teller according to the service state and the behavior data in the current monitoring period, and cache the behavior anomaly event; and perform step a, step b or step c: step a, determining whether real-time reminding is needed according to a type of the reference behavior; step b, if it is determined that real-time reminding is needed, visualizing a risk prompt of an image of the virtual teller model in an image of the virtual site displayed by a background management center; and step c, if it is determined that real-time reminding is not needed, continuing data processing in a next monitoring period.

[0127] The prediction unit 405 is configured to, if it is determined that the reference behavior is suspicious by querying the personalized compliance behavior subset according to the reference behavior and the service state is the online service accepted or the offline service accepted, determine a target service currently accepted by the teller; and predict whether the behavior of the teller is abnormal according to a service situation of the target service; and

[0128] The processing unit 404 is further configured to, if it is predicted that the behavior of the teller is abnormal, create the behavior anomaly event and cache the behavior anomaly event; and perform the step a, the step b or the step c.

[0129] The processing unit 404 is further configured to, if it is predicted that the behavior of the teller is compliant, continue data processing in a next monitoring period.

[0130] The processing unit 404 is further configured to, if it is determined that the reference behavior is compliant by querying the personalized compliance behavior set according to the reference behavior, continue data processing in a next monitoring period.

[0131] It can be seen that the virtual network point based on the information processing device of the behavior abnormal event described in the embodiment of the application can obtain the business state and behavior data of the virtual teller model of the teller in the current monitoring period, call the preset personalized compliance behavior subset of the teller in the business state, then determine the reference behavior of the teller according to the behavior data, if it is determined that the reference behavior is suspicious according to the reference behavior query of the personalized compliance behavior subset, and the business state is an unprocessed business, then create a behavior abnormal event of the teller according to the business state and behavior data of the current monitoring period, and cache the behavior abnormal event, and perform steps a, b or c: step a, determine whether real-time reminding is needed according to the type of the reference behavior; step b, if it is determined that real-time reminding is needed, then the image of the virtual teller model in the image of the virtual network point displayed by the background management center is visualized for risk prompt; step c, if it is determined that real-time reminding is not needed, then continue data processing of the next monitoring period, if it is determined that the reference behavior is suspicious according to the reference behavior query of the personalized compliance behavior subset, and the business state is an online business or an offline business, then determine the target business currently handled by the teller, and predict whether the behavior of the teller is abnormal according to the business situation of the target business, and if it is predicted that the behavior of the teller is abnormal, then create a behavior abnormal event, and cache the behavior abnormal event, and perform steps a, b or c, if it is predicted that the behavior of the teller is compliant, then continue data processing of the next monitoring period, finally, if it is determined that the reference behavior is compliant according to the reference behavior query of the personalized compliance behavior set, then continue data processing of the next monitoring period. In this way, the individualized behavior of the teller in the virtual network point can be monitored, the individualized behavior of the teller can be avoided to be misidentified as an abnormal behavior, and the accuracy, efficiency and real-time performance of the abnormal event identification of the virtual network point can be improved.

[0132] In one possible example, in the case where the business situation of the target business includes the business information of the target business and the behavior data of the customer requesting to handle the target business, the prediction unit 405 is specifically configured to:

[0133] predict whether the reference behavior of the teller has violated the rules according to the business information of the target business and the behavior data of the customer;

[0134] if yes, then it is predicted that the behavior of the teller is abnormal;

[0135] if no, then it is predicted that the behavior of the teller is compliant.

[0136] In one possible example, in the case where the preset personalized compliance behavior subset of the teller in the business state is called, the calling unit 402 is specifically configured to:

[0137] determine a state label according to the service state, the state label including an idle label corresponding to the unprocessed service, an online service handling label corresponding to the processed online service, and an offline service handling label corresponding to the processed offline service;

[0138] query a preset personalized compliance behavior set of the teller with the state label as a query identifier, and obtain a personalized compliance behavior subset corresponding to the state label, the personalized compliance behavior set including a corresponding relationship between a state label and a personalized compliance behavior subset.

[0139] In one possible example, before the processing unit 404 obtains the service state and behavior data of the virtual teller model of the teller in the current monitoring period, the processing unit 404 is specifically configured to:

[0140] collect sample data of the virtual teller model of the teller in a preset time period, the sample data including first sample behavior data of the teller in the service state of the unprocessed service, second sample behavior data of the teller in the service state of handling online service, and third sample data of the teller in the service state of handling offline service;

[0141] perform statistical analysis on the first sample behavior data to obtain at least one first compliance behavior in the service state of the unprocessed service, and create a personalized compliance behavior subset corresponding to the state label of the unprocessed service according to a corresponding relationship between the first compliance behavior and the state label of the unprocessed service;

[0142] perform statistical analysis on the second sample behavior data to obtain at least one second compliance behavior in the service state of handling online service, and create a personalized compliance behavior subset corresponding to the state label of the online service according to a corresponding relationship between the second compliance behavior and the state label of the online service;

[0143] perform statistical analysis on the third sample behavior data to obtain at least one second compliance behavior in the service state of handling offline service, and create a personalized compliance behavior subset corresponding to the state label of the offline service according to a corresponding relationship between the second compliance behavior and the state label of the offline service.

[0144] In one possible example, before the processing unit 404 obtains the service state and behavior data of the virtual teller model of the teller in the current monitoring period, the processing unit 404 is specifically configured to: Figure 4B as shown in Figure 4A On the basis of the above, the virtual site based on behavior abnormal event information processing apparatus 400 can further include a setting unit 406, which is configured to:

[0145] A compliance behavior setting page is displayed, the compliance behavior setting page including a state label and a personalized compliance behavior setting area corresponding to the state label, the personalized compliance behavior setting area supporting user self-entry and / or preset behavior selection;

[0146] The custom compliance behavior entered by the teller and / or the selected preset compliance behavior are marked as the compliance behavior corresponding to the state label;

[0147] A personalized compliance behavior subset corresponding to the state label is created according to the correspondence between the marked compliance behavior and the state label;

[0148] The above process is repeated until the personalized compliance behavior subsets corresponding to all state labels are set.

[0149] In one possible example, the obtaining of the business state and behavior data of the virtual teller model of the teller before the current monitoring period is performed based on Figure 4C , and Figure 4A , and / or Figure 4B The information processing apparatus 400 based on behavior abnormal event of the virtual site further includes an integration unit 407 configured to:

[0150] A static model of each construction object is constructed according to the static entity information of the plurality of tellers;

[0151] A dynamic simulation model of each construction object is constructed according to the dynamic entity information of the plurality of tellers;

[0152] Based on the multi-scale model fusion modeling method and the anchor point-based virtual-real entity calibration method, the static model and the dynamic simulation model of the teller are integrated in fixed space and different scale dimensions to obtain the virtual teller model corresponding to the teller.

[0153] It should be noted that all related contents of each step involved in the above method embodiments can be cited to the function description of the corresponding function module, which will not be repeated here.

[0154] The electronic device provided in the embodiment is used to execute the information processing method based on behavior abnormal event of the virtual site, and thus the same effect as the above implementation method can be achieved.

[0155] The embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all steps of any method described in the above method embodiments, and the computer includes the electronic device.

[0156] The embodiment of the present application further provides a computer program product, which comprises a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method described in the above method embodiments. The computer program product can be a software installation package, and the computer comprises a control platform.

[0157] The embodiment of the present application further provides a chip, which comprises a processor and can be used to execute instructions, and in the case that the processor executes the instructions, the chip can implement part or all of the steps of any method described in the above method embodiments. Optionally, the chip can further comprise a communication interface, which can be used to receive a signal or send a signal.

[0158] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0159] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0160] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented by other means. For example, the apparatus embodiments described above are only schematic, for example, the division of the above units is only a logical function division, and actual implementation can be in another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical or other forms.

[0161] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0162] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0163] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application, essentially or in the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods according to the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, etc.

[0164] A person of ordinary skill in the art can understand that all or part of the steps of the various methods of the above embodiments can be instructed by a program to relevant hardware, and the program can be stored in a computer readable memory, and the memory can include a flash disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0165] The embodiments of the present application are described in detail above, and the principles and implementation manners of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea; meanwhile, for a person of ordinary skill in the art, according to the idea of the present application, the specific implementation manner and application range will be changed, and the above description of the embodiments should not be understood as a limitation of the present application.

Claims

1. A method for information processing of virtual outlets based on abnormal behavior events, characterized in that, A group device is applied to a banking service system, the banking service system including a data acquisition device for physical branches and the group device. The group device is used to support data interaction between the physical branches and the virtual branches to identify abnormal behavior of tellers at the physical branches. The data interaction refers to the process by which the data acquisition device collects the physical information of the teller and transmits the physical information to the group device. The virtual branch is a digital twin model constructed based on the physical data of the physical branch. The physical data of the physical branch includes the physical information of multiple constructed objects of the physical branch, including the teller of the physical branch. The digital twin model of the virtual branch includes a virtual teller model constructed by integrating the static model and dynamic simulation model of the teller at different scales in a fixed space. The method includes: The business status and behavior data of the virtual teller model of the teller are obtained in the current monitoring period. The business status is used to indicate the business processing status of the virtual teller model, including unprocessed business, online business accepted, or offline business accepted. Retrieve a preset subset of personalized compliance behaviors of the teller in the business state, wherein the subset of personalized compliance behaviors includes at least one compliance behavior of the teller in the business state; The teller's reference behavior is determined based on the behavioral data; If, based on the reference behavior query of the personalized compliance behavior subset, the reference behavior is determined to be questionable, and the business status is unprocessed business, then an abnormal behavior event of the teller is created based on the business status and behavior data of the current monitoring period, and the abnormal behavior event is cached; and, steps a, b, or c are executed: Step a: Determine whether real-time reminder is needed based on the type of the reference behavior; Step b: If it is determined to be needed, then visualize the image of the virtual teller model in the image of the virtual branch displayed in the back-end management center to provide a risk warning; Step c: If it is determined not to be needed, then continue data processing for the next monitoring period; If, based on the reference behavior query of the personalized compliance behavior subset, the reference behavior is determined to be questionable, and the business status is either "accepting online business" or "accepting offline business," then the target business currently being handled by the teller is determined; and, based on the business situation of the target business, it is predicted whether the teller's behavior is abnormal; and... If abnormal behavior of the teller is predicted, an abnormal behavior event is created and cached; and step a, step b, or step c is executed. If the teller's behavior is predicted to be compliant, data processing will continue into the next monitoring cycle. If the reference behavior is found to be compliant based on the personalized compliance behavior set, then data processing continues for the next monitoring cycle. The business situation of the target business includes the business information of the target business and the behavioral data of the customer requesting the target business. The step of predicting whether the teller's behavior is abnormal based on the business situation of the target business includes: predicting whether the teller's reference behavior has violated regulations based on the business information of the target business and the customer's behavioral data; if so, the teller's behavior is predicted to be abnormal; if not, the teller's behavior is predicted to be compliant.

2. The method according to claim 1, characterized in that, The retrieval of a preset subset of the teller's personalized compliance behaviors under the business state includes: A status label is determined based on the business status, and the status label includes an idle label corresponding to the unprocessed business, an online business acceptance label corresponding to the online business being processed, and an offline business acceptance label corresponding to the offline business being processed. Using the status tag as the query identifier, query the preset set of personalized compliance behaviors of the teller, and obtain the personalized compliance behavior subset corresponding to the status tag. The personalized compliance behavior set includes the correspondence between the status tag and the personalized compliance behavior subset.

3. The method according to claim 2, characterized in that, Before obtaining the business status and behavior data of the virtual teller model of the teller in the current monitoring period, the method further includes: Collect sample data of the virtual teller model of the teller within a preset time period. The sample data includes the first sample behavior data of the teller in the business state of not processing business, the second sample behavior data in the business state of accepting online business, and the third sample behavior data in the business state of accepting offline business. Statistical analysis is performed on the first sample behavior data to obtain at least one first compliance behavior in the business state of the unprocessed business. A personalized compliance behavior subset corresponding to the state label of the unprocessed business is created based on the correspondence between the first compliance behavior and the state label of the unprocessed business. Statistical analysis is performed on the second sample behavior data to obtain at least one second compliance behavior under the business status of accepting online business. A personalized compliance behavior subset corresponding to the status label of accepting online business is created based on the correspondence between the second compliance behavior and the status label of accepting online business. Statistical analysis is performed on the third sample behavior data to obtain at least one third compliance behavior under the business status of the offline business. Based on the correspondence between the third compliance behavior and the status label of the offline business, a personalized compliance behavior subset corresponding to the status label of the offline business is created.

4. The method according to claim 2, characterized in that, Before obtaining the business status and behavior data of the virtual teller model of the teller in the current monitoring period, the method further includes: The compliance behavior settings page is displayed. The compliance behavior settings page includes status labels and personalized compliance behavior settings areas corresponding to the status labels. The personalized compliance behavior settings area supports user self-entry and / or selection of preset behaviors. The custom compliance behaviors and / or preset compliance behaviors entered by the tellers are marked as the compliance behaviors corresponding to the status tags. Create a personalized subset of compliance behaviors corresponding to the status tags based on the correspondence between the marked compliance behaviors and the status tags; Repeat the above process until the personalized compliance behavior subsets corresponding to all status labels are set.

5. The method according to any one of claims 1-4, characterized in that, The plurality of construction objects also include the following elements of the physical outlets: business processes, equipment, and site environment; The entity information includes static entity information and dynamic entity information. The static entity information includes the identity information, attribute information and geometric information of the constructed object. The dynamic entity information includes the state information, location information and process information of the constructed object.

6. The method according to claim 5, characterized in that, Before obtaining the business status and behavior data of the virtual teller model of the teller in the current monitoring period, the method further includes: A static model of each constructed object is constructed based on the static entity information of the multiple tellers; A dynamic simulation model of each constructed object is constructed based on the dynamic entity information of the multiple tellers; Based on the multi-scale model fusion modeling method and the anchor-point-based virtual-real entity calibration method, the static model and dynamic simulation model of the teller are integrated under different scale dimensions in a fixed space to obtain the virtual teller model corresponding to the teller.

7. A virtual branch information processing device based on abnormal behavior events, characterized in that, A group device is applied to a banking service system. The banking service system includes a data acquisition device for physical branches and the group device. The group device supports data interaction between the physical branches and virtual branches to identify abnormal behavior of tellers at the physical branches. The data interaction refers to the process where the data acquisition device collects the teller's physical information and transmits it to the group device. The virtual branch is a digital twin model constructed based on the physical data of the physical branch. The physical data of the physical branch includes entity information of multiple constructed objects, including the teller at the physical branch. The digital twin model of the virtual branch includes a virtual teller model constructed by integrating static and dynamic simulation models of the teller at different scales in a fixed space. The device includes: an acquisition unit, a retrieval unit, a determination unit, a processing unit, and a prediction unit. The acquisition unit is used to acquire the business status and behavior data of the virtual teller model of the teller in the current monitoring period. The business status is used to indicate the business processing status of the virtual teller model. The business processing status includes unprocessed business, online business accepted, or offline business accepted. The retrieval unit is used to retrieve a preset subset of the teller's personalized compliance behaviors in the business state, the subset of personalized compliance behaviors including at least one compliance behavior of the teller in the business state. The determining unit is used to determine the teller's reference behavior based on the behavioral data; The processing unit is configured to: if, based on the reference behavior query of the personalized compliance behavior subset, the reference behavior is determined to be questionable, and the business status is unprocessed business, then create a teller behavior anomaly event based on the business status and behavior data of the current monitoring period, and cache the behavior anomaly event; and execute step a, step b, or step c: step a, determine whether real-time reminder is needed based on the type of the reference behavior; step b, if it is determined to be needed, provide a visual risk warning for the image of the virtual teller model in the image of the virtual branch displayed in the back-end management center; step c, if it is determined not to be needed, continue data processing for the next monitoring period; The prediction unit is configured to: determine the target business currently being handled by the teller if, based on the reference behavior query of the personalized compliance behavior subset, the reference behavior is found to be questionable, and the business status is either online business processing or offline business processing; and predict whether the teller's behavior is abnormal based on the business situation of the target business; and... The processing unit is further configured to, if an abnormal behavior of the teller is predicted, create the abnormal behavior event and cache the abnormal behavior event; and execute step a, step b, or step c. The processing unit is also used to continue data processing for the next monitoring cycle if it is predicted that the teller's behavior is compliant. The processing unit is further configured to continue data processing for the next monitoring cycle if the reference behavior is found to be compliant based on the personalized compliance behavior set queried according to the reference behavior. The business situation of the target business includes the business information of the target business and the behavioral data of the customer requesting the target business. In the step of predicting whether the teller's behavior is abnormal based on the business situation of the target business, the prediction unit is specifically used to: predict whether the teller's reference behavior has violated regulations based on the business information of the target business and the customer's behavioral data; if yes, then predict that the teller's behavior is abnormal; if no, then predict that the teller's behavior is compliant.

8. An electronic device, characterized in that, The method includes a processor, a memory, a communication interface, and one or more programs, said programs being stored in the memory and configured to be executed by the processor, said programs including instructions for performing the steps of the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, A computer program for storing electronic data interchange is provided, wherein the computer program causes a computer to perform the method as described in any one of claims 1-6.

Images