CN112053224A

CN112053224A - Business processing monitoring implementation method, device and system

Info

Publication number: CN112053224A
Application number: CN202010908891.6A
Authority: CN
Inventors: 黄文强; 季蕴青; 胡路苹; 胡玮; 黄雅楠; 浮晨琪; 李蚌蚌; 徐晨敏
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2020-09-02
Filing date: 2020-09-02
Publication date: 2020-12-08
Anticipated expiration: 2040-09-02
Also published as: CN112053224B

Abstract

The application provides a method, a device and a system for realizing service audit monitoring, which are used for obtaining monitoring parameters of a monitored object aiming at a service to be audited and an audit state of the service to be audited, such as target shooting frequency of an image collector for shooting the audit state of the service to be audited of the monitored object, thereby controlling the image collector to continuously audit multi-frame state images shot according to the target shooting frequency in the process of auditing the service to be audited of the monitored object, further accurately obtaining effective audit time of the service to be audited of the monitored object according to the target shooting frequency, verifying the effective audit time according to the audit time standard of the monitored object, so that when the monitored object is determined not to be audited, a next audit cycle of the service to be audited can not be switched to, and the technical problem caused by finding a problem in the last audit link is avoided, the invalid waiting time of the client is greatly reduced, and the client experience is improved.

Description

Business processing monitoring implementation method, device and system

Technical Field

The present application relates to the field of service auditing applications, and in particular, to a method, an apparatus, and a system for implementing service processing monitoring.

Background

At present, in financial service industries such as banks and the like, since businesses handled by customers often relate to various assets, in order to ensure the security of customer information and assets, a stricter auditing mechanism is adopted to audit businesses requested to be handled by customers, and whether the businesses are approved or not is determined after multiple audits.

In practical application, in a service auditing process, due to the reasons of non-scrutiny, trouble saving and the like, some auditors may not really audit the service content of a service to be audited, so that some services to be audited have problems only found in the last auditing link, and the services to be audited need to be returned to be audited again, which wastes time and labor, increases the waiting time of clients, and reduces the experience of the clients.

Disclosure of Invention

In view of the above, in order to solve the above technical problems, the present application provides the following technical solutions:

on one hand, the application provides a method for implementing service audit monitoring, and the method comprises the following steps:

acquiring monitoring parameters aiming at a service to be audited and auditing a monitored object of the service to be audited, wherein the monitoring parameters comprise: the image collector shoots a target shooting frequency of the monitored object for auditing the auditing state of the service to be audited;

in the process of auditing the business to be audited by the monitored object, acquiring continuous multi-frame audit state images shot by the image collector according to the target shooting frequency;

obtaining effective auditing time of the monitored object for auditing the service to be audited according to the continuous multi-frame auditing state images and the target shooting frequency;

and verifying the effective auditing time according to the auditing time standard of the monitored object to obtain a monitoring result for auditing the service to be audited by the monitored object.

Optionally, the obtaining, according to the continuous multiple frames of audit state images and the target shooting frequency, effective audit time for the monitored object to audit the service to be audited includes:

inputting the continuous multi-frame auditing state images and the target shooting frequency into an auditing time statistical model, and outputting effective auditing time of the monitored object for auditing the service to be audited;

the auditing time statistical model is obtained by training first sample data based on a neural network algorithm and a genetic algorithm, wherein the first sample data comprises different sample shooting frequencies and multi-frame sample auditing state images corresponding to the different sample shooting frequencies.

Optionally, the training process of the statistical model of the audit time includes:

acquiring shooting frequencies of different samples and continuous multi-frame sample audit state images shot at the different shooting frequencies;

inputting the sample shooting frequency and the corresponding continuous multi-frame sample auditing state images into a neural network, performing learning training according to a genetic algorithm until a training constraint condition is met, and determining a neural network model obtained by final training as an auditing time statistical model;

the training constraint condition comprises that the accuracy verification result of the output of the neural network model obtained by each training meets the accuracy requirement by using test sample data.

Optionally, the obtaining manner of the audit time standard of the monitored object includes:

acquiring historical behavior data of the monitored object;

according to the historical behavior data, determining an auditing time standard corresponding to the object class of the monitored object from auditing time standards corresponding to respective preset multiple classes of objects;

the verifying the effective auditing time according to the auditing time standard of the monitored object to obtain the monitoring result of auditing the service to be audited aiming at the monitored object comprises the following steps:

verifying whether the effective auditing time meets the auditing time standard of the monitored object;

if the auditing time standard of the monitored object is met, determining that the auditing result of the monitored object to the service to be audited is valid;

and if the audit time standard of the monitored object is not met, determining that the audit result of the monitored object on the service to be audited is invalid.

Optionally, the verifying the valid audit time according to the audit time standard of the monitored object to obtain a monitoring result for auditing the service to be audited by the monitored object includes:

inputting the effective auditing time and the image information corresponding to the monitored object into an auditing verification model, and outputting a monitoring result of whether the auditing result of the monitored object to the service to be audited is effective;

the auditing and verifying model is obtained by training second sample data based on an artificial intelligence algorithm, wherein the second sample data comprises different sample auditing time and portrait information of different monitored objects.

Optionally, the method further includes:

and outputting review prompt information under the condition that the monitored object is determined to be invalid to the auditing result of the service to be audited, wherein the review prompt information is used for reminding the monitored object to audit the service to be audited again.

Optionally, the obtaining of the monitoring parameters for the to-be-audited service and the auditing of the monitored object of the to-be-audited service includes:

acquiring the service type of a service to be audited;

determining a monitoring mode of the monitored object of the service to be audited according to the service type;

if the monitoring mode is a first monitoring mode, acquiring a target shooting frequency matched with the service type and used for shooting the checking state of the service to be checked by the monitored object through the image collector;

the higher the importance level of the service to be audited of different service types is, the higher the corresponding target shooting frequency is.

Optionally, the method further includes:

if the monitoring mode is a second monitoring mode, obtaining the average auditing time of the monitored object for auditing the same type of service of the service to be audited;

counting the current auditing time of the monitored object for auditing the service to be audited;

obtaining a monitoring result whether the auditing result of the service to be audited is valid or not aiming at the monitored object according to the comparison result of the current auditing time and the average auditing time;

and if the monitoring mode is the third monitoring mode, forbidding to respond to the monitoring request aiming at the checking state of the monitored object for checking the service to be checked.

In another aspect, the present application further provides a device for implementing service audit monitoring, where the device includes:

a monitoring parameter obtaining module, configured to obtain monitoring parameters for a service to be audited and for auditing monitored objects of the service to be audited, where the monitoring parameters include: the image collector shoots a target shooting frequency of the monitored object for auditing the auditing state of the service to be audited;

an audit state image acquisition module, configured to acquire continuous multiple frames of audit state images captured by the image collector according to the target shooting frequency in the process of auditing the service to be audited by the monitored object;

an effective auditing time obtaining module, configured to obtain effective auditing time for auditing the service to be audited by the monitored object according to the continuous multiple frames of auditing state images and the target shooting frequency;

and the effective auditing time verifying module is used for verifying the effective auditing time according to the auditing time standard of the monitored object to obtain a monitoring result for auditing the service to be audited by the monitored object.

In another aspect, the present application further provides a system for implementing service audit monitoring, where the system includes:

the image collector is used for carrying out image collection on the auditing state of the monitored object auditing the service to be audited to obtain continuous multi-frame auditing state images;

a computer device, the computer device comprising:

a communication interface;

a memory for storing a program for implementing the service audit monitoring implementation method;

and the processor is used for loading and executing the program stored in the memory so as to realize the steps of the service audit monitoring realization method.

Therefore, compared with the prior art, the application provides a method, a device and a system for realizing service audit monitoring, in order to supervise the audit state of the audit service of any current audit service and find out the audit problem in time to solve the audit problem, a computer device obtains the monitoring parameters of the service to be audited and the monitored object of the audit service to be audited, such as the target shooting frequency of the image collector for shooting the audit state of the service to be audited of the monitored object, thereby controlling the image collector to shoot continuous multi-frame audit state images according to the target shooting frequency in the process of auditing the service to be audited of the monitored object, further accurately obtaining the effective audit time of the service to be audited of the monitored object according to the continuous multi-frame audit state images and the target shooting frequency, and thus being capable of according to the audit time standard of the monitored object, the effective auditing time is verified, whether the auditing state of the service to be audited of the monitored object is authentic or not is known, so that whether the auditing result of the service to be audited is correct or not is determined, and when the monitored object is determined not to be authentic, the next auditing link of the service to be audited is not switched to, so that the problem is found in the last auditing link in the prior art is solved, the service to be audited needs to be returned and audited again, time and labor are wasted, the waiting time of a client is prolonged, and the technical problem of client experience is reduced.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a schematic diagram illustrating an alternative example of a business audit monitoring implementation system according to the present application;

FIG. 2 is a diagram illustrating a hardware architecture of an alternative example of a computer device in a system for implementing business audit monitoring proposed in the present application;

FIG. 3 is a flow chart diagram illustrating an alternative example of a business audit monitoring implementation method proposed in the present application;

FIG. 4 is a flow diagram illustrating yet another alternative example of a business audit monitor implementation method presented herein;

FIG. 5 is a flow diagram illustrating yet another alternative example of a business audit monitor implementation method presented herein;

FIG. 6 is a schematic structural diagram illustrating an alternative example of a business audit monitor implementation apparatus according to the present application;

fig. 7 is a schematic structural diagram illustrating still another alternative example of the service audit monitoring implementation apparatus provided in the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present application may be combined with each other without conflict.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements. An element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

In the description of the embodiments herein, "/" means "or" unless otherwise specified, for example, a/B may mean a or B; "and/or" herein is merely an association describing an associated object, and means that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality" means two or more than two. The terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

Additionally, flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Referring to fig. 1, a schematic structural diagram of an optional example of a system for implementing service audit monitoring provided in the present application may include: image collector 11 and computer device 12, wherein:

the image collector may be configured to perform image collection on an audit state of an audit service to be audited for the monitored object, to obtain a continuous multi-frame audit state image, so as to subsequently determine an audit state of the monitored object in the process of auditing the service to be audited, and further determine an effective audit time of the monitored object for this audit service to be audited, where a specific implementation process may refer to descriptions of corresponding parts in the following embodiments.

In practical application, the image collector may be a camera integrated in the computer device 12, or may be an independent camera, and the like, and the product type of the image collector is not limited in the present application, and may be determined according to the requirements of a practical application scene, but a shooting lens of the image collector is required to face a monitored object, and at least a facial image of the monitored object can be shot, so that whether the monitored object is seriously auditing a service to be audited is analyzed through facial image features. Of course, according to actual requirements, the captured image of the examination status may further include image features of other body parts of the monitored object, which is not described in detail herein.

The computer device 12 may execute the service audit monitoring implementation method provided in this application, so as to implement supervision of each auditor auditing a service to be audited. In the embodiment of the present application, the computer device 12 may be a service terminal or a service server, which may be determined according to a specific application scenario. Regardless of the type of product the computer device 12 is, as shown in FIG. 2, it may include, but is not limited to: a communication interface 21, a memory 22, and a processor 23, wherein:

the number of the communication interface 21, the memory 22, and the processor 23 may be at least one, and the communication interface 21, the memory 22, and the processor 23 may all be connected to a communication bus to implement data interaction therebetween.

The communication interface 21 may include an interface of a communication module, such as a GSM module, a WIFI module, an interface for implementing data communication of a mobile communication network (such as a 5G network or a 6G network), and in practical applications, it may be used to implement data interaction with other devices, such as transmitting an audit state image of a monitored object captured by an image collector, and a monitoring result of the monitored object.

According to actual needs, the communication interface 21 may further include interfaces such as a USB interface and a serial/parallel interface, which are used to implement data interaction between internal components of the computer device, for example, various intermediate data, input parameters, and the like generated or required in the implementation process of the service audit monitoring implementation method provided by the present application may be determined according to requirements of an actual application scenario, and details of the present application are not described in detail.

The memory 22 may store a program formed by a plurality of instructions for implementing the method for implementing service audit monitoring provided by the embodiment of the present application, and the processor 23 calls and loads the program stored in the memory 22, so as to implement the method for implementing service audit monitoring provided by the embodiment of the present application, and the specific implementation process may refer to, but is not limited to, the following description of the corresponding embodiment.

In the present embodiment, the memory 22 may include a high speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device or other volatile solid state storage device. The processor 23 may be a Central Processing Unit (CPU), an application-specific integrated circuit (ASIC), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices.

In one possible implementation, the memory 22 may include a program storage area and a data storage area, and the program storage area may store an operating system, and application programs required for at least one function (such as an image processing function), programs for implementing the service audit monitoring implementation method proposed in the present application, and the like; the data storage area may store data generated during the use of the computer device, such as an audit state image of the monitored object, a monitoring result of the monitored object, related service information of a service to be audited, and an audit progress, which are captured by the image capture device, as appropriate.

In some embodiments provided in the present application, if the computer device 12 is a service server, the service auditing and monitoring implementation system provided in the present application may further include a corresponding service terminal, and the monitored person operates the service terminal to implement auditing of a service to be audited. It can be seen that, in this case, after the monitored object receives the audit task for the service to be audited, when the audit task is completed, for example, when the audit button for the service to be audited is clicked, the service terminal usually receives the audit instruction for the service to be audited, and determines that the monitored object starts to audit the service to be audited, at this time, the service terminal may notify the service server to control the image collector, perform image acquisition on the audit state of the service to be audited of the monitored object according to the target shooting frequency obtained by the present application, obtain the continuous multi-frame audit state images shot and fed back by the image collector, and subsequently may be executed according to the service audit monitoring implementation method provided by the present application.

For data interaction between the image collector and the service server, communication connection can be established by utilizing respective communication modules, so that direct communication between the image collector and the service server is realized; or, the image collector and the service server may also implement data interaction through the service terminal, that is, the service terminal serves as an intermediate bridge for communication between the image collector and the service server to implement communication between the image collector and the service server, especially in an application scenario in which the image collector is integrated in the service terminal, but not limited to this application scenario.

In still other embodiments provided by the present application, the computer device 12 provided by the present application may also be a service terminal, and the service terminal may be an electronic device used by a staff in the system during a service transaction process, such as an electronic device used by a monitored object to audit a service to be audited. In practical applications, the electronic device may include, but is not limited to, a smart phone, a tablet computer, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), an e-book reader, a desktop computer, and the like, where the application does not limit the product type of the service terminal used by each worker, and in practical applications, the product types of the service terminals used by different workers may be the same or different, and may specifically be determined according to the work type and the application scenario thereof.

It should be understood that, since the service auditing process usually includes multiple auditing links, different auditors may audit the service for safety and reliability, and auditors for different types of services may also be different, and service terminals used by different auditors may be different, the number of service terminals in the system provided by the present application is often multiple, and specifically may be determined or extended according to the requirements of an application scenario, and detailed description is not given in this application.

In addition, in order to meet the business processing requirements, a business server supporting business handling or auditing can be configured in the system, corresponding services are provided for business application of the business terminal, sharing of business information in different regions is realized, and the like.

In practical application of this embodiment, if the computer device 12 is an electronic device, the computer device may further include a display screen, which is used to output an audit interface, related information of a service to be audited, an audit result, a monitoring result for a monitored object, and the like, and may be determined according to a specific application scenario. The display screen can be a touch display screen or a non-touch display screen, and the type and the working principle of the display screen are not detailed in the application.

It should be understood that, in the case that the computer device is a service terminal, the structure of the service terminal described in the foregoing embodiments of the present application does not constitute a limitation to the service terminal in the embodiments of the present application, and in practical applications, the service terminal may include more or less components than the structure described in the foregoing embodiments, or may combine some components, such as at least one input device, e.g., a keyboard, a mouse, and at least one output device, e.g., a speaker, a vibration mechanism, a lamp, and the like, and the present application is not listed here.

In addition, the system structure composition provided by the present application is not limited to the image collector and the computer device listed above, and may further include other service devices such as a database, a queuing device, and an autonomous service device, and may be specifically determined according to the specific application scenario of the service audit monitoring implementation system, which is not described in detail herein.

Referring to fig. 3, a schematic flow chart of an alternative example of a method for implementing service audit monitoring provided by the present application, which may be applied to the above computer device, and the present application does not limit the product type of the computer device, and reference may be made to, but is not limited to, the description of the corresponding parts of the above embodiments. As shown in fig. 3, the method for implementing service audit monitoring provided by this embodiment may include, but is not limited to, the following steps:

step S11, acquiring monitoring parameters aiming at the service to be audited and the monitored object for auditing the service to be audited;

in combination with the above background art and the related description of the system structure, in order to supervise the audit state of the auditor responsible for the service audit task and ensure the reliability and accuracy of the audit result given by the auditor, the auditor is provided as a monitored object, and the audit state of the auditor is monitored in the audit process of the service to be audited (i.e. any service which is distributed to the auditor and needs to be audited), so as to determine whether the auditor is seriously auditing the service to be audited, if the auditor is seriously auditing the service to be audited in the whole audit process of auditing the service to be audited, the audit result of the service to be audited given by the auditor can be considered to be effective (i.e. correct); otherwise, the audit result of the service to be audited given by the auditor may be considered invalid (i.e. incorrect), and the auditor is reminded to audit the service to be audited again, so as to ensure that the audit result sent to the next auditing link is correct.

Based on this, the method and the device for acquiring the images of the monitored object shoot the auditing state of the monitored object during the process of auditing the service to be audited by the monitored object, and further provide that the image acquisition is carried out according to a higher frequency in order to ensure that the shot continuous images can more reliably reflect the auditing state of the service to be audited by the monitored object, so that the phenomenon that the shooting frequency is too low and the monitored object is lazy in the process of acquiring two adjacent frames of images is avoided.

Therefore, after determining the service to be audited for the current audit, monitoring parameters for the service to be audited and the monitored object for auditing the service to be audited may be obtained first, where the monitoring parameters may include: the image collector shoots the target shooting frequency of the monitored object for auditing the auditing state of the service to be audited, but the target shooting frequency is not limited to the target shooting frequency, and other monitoring parameters such as the shooting angle and the shooting resolution of the image collector can also be included. The content contained in the acquired monitoring parameters can be determined according to the requirements of practical application scenes, the target shooting frequency is mainly taken as an example for explanation, other parameters can be flexibly selected according to the shooting requirements, and detailed description is not needed.

In practical application of the method, the configuration of the shooting frequency of the image collector can be determined according to the importance of the service to be audited, for example, for the more important service to be audited, the image collection can be carried out by adopting the higher shooting frequency; on the contrary, for the less important service to be audited, the lower shooting frequency can be adopted for image acquisition, the corresponding relation between the importance of the service to be audited and the shooting frequency can be obtained according to the service requirement or experience or model training, and the acquisition mode and the representation mode of the corresponding relation are not limited.

In still other embodiments, the configuration of the shooting frequency of the image acquirer may be determined by combining with the monitored object currently auditing the service to be audited. Specifically, different auditors often have different attitudes towards audit work, and the accuracy of the audit result of the same type of service often differs, so that the audit attitude is generally more serious, and the accuracy of the audit result of the type of service is higher, whereas the audit attitude is generally more diffuse, and the accuracy of the audit result of the type of service is lower. Therefore, when determining the target shooting frequency of the image collector, in addition to referring to the importance of the service to be audited, which type of auditor the monitored object belongs to can be properly considered, the two factors (other factors can be included according to needs, and detailed description is not given in the present application) are integrated to determine the corresponding relationship between the monitored object and the shooting frequency, and detailed implementation processes are not given in the present application.

It should be noted that, regarding the monitoring parameters in the step S11, especially the obtaining manner of the target shooting frequency, is not limited to the above-listed implementation manners, and may be determined according to actual requirements, and the detailed description is not given in this application.

Step S12, acquiring continuous multi-frame auditing state images shot by an image collector according to target shooting frequency in the process of auditing the business to be audited by the monitored object;

with reference to the description of the corresponding part of the foregoing embodiment, the computer device may determine whether to start auditing of a service to be audited based on an audit confirmation operation of the service to be audited by a monitored object, and when it is determined that the service to be audited is started, control the image collector to collect images of the monitored object according to the target shooting frequency, and obtain continuous multiple frames of audit state images captured by the image collector.

Step S13, obtaining effective auditing time of the monitored object for auditing the service to be audited according to the continuous multi-frame auditing state image and the target shooting frequency;

in the process of auditing the service to be audited by the monitored object, the image collector captures an image of the monitored object, namely an audit state image, and subsequently, whether the monitored object in the audit state image is seriously auditing the service to be audited can be determined by carrying out image analysis on each frame of audit state image.

In this embodiment, the target shooting frequency may be data information obtained by performing data fitting processing on the monitored object according to the importance of the service to be audited and in combination with the error accuracy, or may be obtained in the manner described in the above corresponding section. Therefore, the importance of the service to be audited and the auditing status of the service to be audited of the monitored object can be reflected by the target shooting frequency, that is, the higher the target shooting frequency is, the more important the service to be audited can be represented, and/or the more serious the auditing status of the service to be audited of the monitored object is, on the basis, the auditing status represented by two adjacent frames of auditing status images and the determination of the target shooting frequency can be comprehensively considered in the process of obtaining the effective auditing time of the service to be audited of the monitored object.

For example, if two frames of the audit state images are respectively subjected to image analysis, it is determined that the audit states of the monitored object in each frame of the audit state images are serious (different audit states can be represented by corresponding identifiers, which is not limited in the present application), it may be considered that the monitored object is in a state of seriously auditing the service to be audited between the shooting times of the two frames of the audit state images, and the obtained effective audit time may not be affected by the target shooting frequency, and the shooting times of the two frames of the audit state images are determined, for example, the shooting times of the two frames of the audit state images are added to add up the effective audit time of the service to be audited of the monitored object, but the implementation is not limited thereto.

If the two frames of audit state images (i.e. the two frames of audit state images at the corresponding time points in the above example) are subjected to image analysis respectively, it is determined that the audit state of the monitored object in one frame of audit state image is authentic, and the audit state of the monitored object in the next frame of audit state image is not authentic, which indicates that at a certain time point between the shooting times of the two frames of audit state images, the monitored object starts to be lazed and does not audit the service to be audited seriously, and at this time, if the shooting times are added according to the above method, the obtained audit time is greater than the actual effective audit time, so as to ensure the accuracy of the obtained effective audit result, different shooting frequencies can be configured for the two cases.

Of course, the two cases listed above may be included in the captured continuous multiple-frame audit state images, but the pre-configured target capture frequency is fixed, and at this time, in order to ensure the accuracy of the obtained effective audit result, the effective audit time obtained for the first case is often greater than the effective audit time obtained for the second case. According to the method and the device, the relation between the continuous multi-frame auditing state images and the target shooting frequency and the effective auditing time of the monitored object for auditing the service to be audited can be determined according to the analysis, so that in practical application, the effective auditing time of the monitored object for auditing the service to be audited can be directly obtained according to the relation, and the obtaining mode and the representing mode of the relation are not limited.

It should be noted that the implementation method how to obtain the effective audit time of the monitored object for auditing the service to be audited according to the continuous multiple audit state images and the target shooting frequency is not limited to the implementation manner described in the above embodiments,

and step S14, verifying the effective auditing time according to the auditing time standard of the monitored object, and obtaining the monitoring result of auditing the service to be audited aiming at the monitored object.

As described in the foregoing embodiment, for different auditors, audit attitudes of auditing services of the same class are often different, and according to the present application, the auditors can audit attitudes of services of various classes in advance for each auditor, cluster the auditors, and determine a standard of auditing the services of the class in the audit time, that is, the audit time standard, according to the audit time of the auditors of the same class for the services of the same class, and subsequently, it can be determined whether effective audit time of the monitored object belonging to the auditors of the class is within a reasonable range, and further determine whether the monitored object is audited seriously, and whether an audit result of the monitored object to be audited is correct or effective.

It should be noted that, the present application does not limit the obtaining manner and the representing manner of the auditing time standards of different types of auditors for various services to be audited, and can determine the auditing time standards according to the requirements of the actual application scenario.

Based on the above analysis, after the effective auditing time of the monitored object for auditing the service to be audited is obtained according to the above manner, the auditing time standard of the monitored object can be obtained according to the monitored object and the service to be audited (the auditing time standard can also be obtained before or during the process of obtaining the effective auditing time, which is not limited by the application), whether the effective auditing time accords with the auditing time standard is judged, if so, the auditing state of the service to be audited of the monitored object can be determined as authentication, the obtained auditing result of the service to be audited is valid (namely correct), the next auditing link of the service to be audited can be entered, and auditing and supervision of auditors in the auditing environment can be realized according to the service auditing and monitoring implementation method provided by the application in the next auditing link, and the implementation process is not repeated.

Through the verification, if the audit time standard of the monitored object is not met, the audit state of the to-be-audited service of the monitored object can be determined to be not authentic, the obtained audit result of the to-be-audited service is invalid (namely incorrect), review prompt information can be output to remind the monitored object to review the to-be-audited service, or the audit task of the to-be-audited service is sent to other auditors to be executed, of course, the audit task of the to-be-audited service can be sent to other auditors to be executed under the condition that the current multiple monitoring results of the monitored object are invalid, if the preset invalid time threshold value is reached, the audit task of the to-be-audited service is sent to other auditors to be executed, and the method can be determined according to the requirements of the actual scene.

In summary, in the embodiment of the present application, a scheme for monitoring the audit state of an audit service of any current audit service is provided, specifically, a computer device obtains monitoring parameters for a service to be audited and a monitored object of the audit service, such as a target shooting frequency of an image collector for shooting the audit state of the service to be audited by the monitored object, so that in the process of auditing the service to be audited by the monitored object, the image collector is controlled to capture continuous multiple frames of audit state images according to the target shooting frequency, and further, according to the continuous multiple frames of audit state images and the target shooting frequency, an effective audit time of the service to be audited by the monitored object is accurately obtained, so that the effective audit time can be verified according to the audit time standard of the monitored object, and whether the audit state of the service to be audited of the monitored object is authentic or not is known, whether the obtained auditing result of the service to be audited is correct or not is determined, so that when the monitored object is determined not to audit the service to be audited seriously, the next auditing link of the object to be audited can not be switched to, and the technical problems that in the prior art, problems are found in the last auditing link, the service to be audited needs to be reviewed again, time and labor are wasted, the waiting time of a client is prolonged, and the experience of the client is reduced are solved.

Referring to fig. 4, which is a schematic flow chart of another optional example of the service audit monitoring implementation method provided in the present application, this embodiment may be an optional detailed implementation manner of the service audit monitoring implementation method provided in the foregoing embodiment, but is not limited to this implementation manner, and as shown in fig. 4, the method may include:

step S21, acquiring the service type of the service to be reviewed;

step S22, determining the monitoring mode of the monitored object of the service to be audited according to the service type;

in this embodiment, the importance of each service may be determined according to the service type of the service, that is, the service type of the service to be audited may represent the importance degree of the service to be audited, and based on this, the monitoring mode of the monitored object of the service to be audited may be further determined, and the monitoring mode may be divided into a first monitoring mode, a second monitoring mode, and a third monitoring mode according to the monitoring severity degree, where the monitoring severity degree of the first monitoring mode is the highest, the monitoring severity degree of the third monitoring mode is the lowest, or even the monitoring is not required, and for the monitoring implementation process in each monitoring mode, reference may be made to the description of the corresponding part in the following embodiment.

It should be understood that, in combination with the above analysis, for the service to be audited with higher importance, the higher the monitoring severity of the monitored object of the service to be audited is, the closer the determined monitoring mode is to or directly is the first monitoring mode, that is, the higher the importance level of the service to be audited of different service types is, the higher the corresponding target shooting frequency is. The method for acquiring the corresponding relation between different service types of each service and each monitoring mode and the representing mode thereof are not limited.

Step S23, if the determined monitoring mode is the first monitoring mode, acquiring the target shooting frequency matched with the service type and used for shooting the auditing state of the monitored object for auditing the service to be audited by the image acquirer;

in combination with the description of the relationship between the shooting frequencies in the above embodiment, for the service to be audited with higher importance, a higher shooting frequency may be configured, so that the present application may determine in advance the relationship between different service types, different monitored objects, and each shooting frequency according to the requirements of the actual application scenarios, and the specific determination method may be according to, but is not limited to, the description of the corresponding parts in the above embodiment. Therefore, in the actual monitoring process, after the service type of the service to be audited and the monitored object of the service to be audited are determined, the target shooting frequency of the image collector for shooting the auditing state of the service to be audited of the monitored object can be determined according to the predetermined relation, and the specific implementation process is not described in detail.

It should be noted that, for the implementation manner of the above step S11 in the present application, the implementation manner is not limited to the technical solutions described in the steps S21 to S23 in the present embodiment, and the contents described in the steps S21 to S23 in the present embodiment can be properly adjusted according to actual needs and the inventive concept of the present application, which all belong to the protection scope of the present application, and the present embodiment is not described in detail herein.

Step S24, acquiring continuous multi-frame auditing state images shot by an image collector according to target shooting frequency in the process of auditing the business to be audited by the monitored object;

the implementation process of step S24 can refer to the description of the corresponding parts of the above embodiments.

Step S25, inputting continuous multiframe auditing state images and target shooting frequency into an auditing time statistical model, and outputting effective auditing time of the monitored object for auditing the service to be audited;

the auditing time statistical model can be obtained by training first sample data based on a neural network algorithm and a genetic algorithm, the first sample data can comprise different sample shooting frequencies and multi-frame sample auditing state images corresponding to the different sample shooting frequencies, and the detailed training process of the auditing time statistical model is not detailed in the application.

In a possible implementation manner, when the statistical model of the auditing time is trained, shooting frequencies of different samples and continuous multi-frame sample auditing state images shot under different shooting frequencies can be obtained, the shooting frequencies of the samples and the corresponding continuous multi-frame sample auditing state images are input into a neural network, learning training is carried out according to a genetic algorithm until a training constraint condition is met, and the neural network model obtained by final training is determined as the statistical model of the auditing time. The training constraint condition comprises that an accuracy verification result of the output of the neural network model obtained by each training meets the accuracy requirement by using test sample data, for example, a preset accuracy threshold value is obtained from the accuracy verification result, and the content of the training constraint condition is not limited by the application and can be determined according to actual requirements.

In practical application, for the audit state image captured in the above manner, the audit state of an auditor (i.e., the monitored object) in each two frames of audit state images can be analyzed through manual data, the effective audit time of the auditor is obtained according to the obtained audit state and the shooting time, and then the effective audit time can be determined as historical data for training and verifying the audit time statistical model.

As described above for the statistical model of audit time in the present application, it may optimize the conventional neural network by using a genetic algorithm, and perform learning training on the first sample data by using the optimized neural network model to improve the accuracy of model output. For example, in the model training process, for training parameters such as weights and thresholds in the neural network, a genetic algorithm may be used to implement, for example, the genetic algorithm determines the number of parameters to be trained, and learning and training of the neural network are completed according to the kolmogorov principle, and a specific learning and training process may be determined according to the genetic algorithm and the operation principle of the neural network, which is not described in detail in this application.

The neural network can be a neural network with a three-layer network structure, a hidden layer can be configured for the hidden layer of the neural network, the number of nodes of the hidden layer can be determined by adopting a trial and error method, and the specific implementation process is not detailed.

In order to ensure the output accuracy of the model obtained by training, the neural network model obtained by training can be verified by using test sample data, namely, a test auditing state image and a test shooting frequency in the test sample data are input into the neural network model to obtain effective auditing time to be verified, the effective auditing time to be verified is compared with corresponding test effective auditing time in the test sample data, if the time difference between the effective auditing time and the test effective auditing time is less than a time threshold value, the output accuracy of the neural network model can be considered to meet the requirement, and the output accuracy can be used as an auditing time statistical model; on the contrary, the training of the neural network model needs to be continued in the above manner, but is not limited to the verification manner described in the embodiment.

And step S26, inputting the effective auditing time and the image information corresponding to the monitored object into the auditing and verifying model, and outputting the monitoring result whether the auditing result of the monitored object to-be-audited service is effective or not.

The verification model can be obtained by training second sample data based on an artificial intelligence algorithm, the second sample data can comprise different sample verification time and portrait information of different monitored objects, and the training process of the verification model to be verified is not detailed in the application.

In the present application, the image information may be determined according to the parameters such as the historical behavior data and the personal attribute information of the auditors, which are determined above, and represents the audit state of the auditors, the audit time standard of various services to be audited, and the like.

It should be noted that how to obtain an implementation manner of auditing a monitoring result of a service to be audited for a monitored object by using the obtained effective auditing time is not limited to the model processing manner described in this embodiment, and a time comparison manner and the like of corresponding parts of the above embodiments may also be adopted, which is not described in detail in this application.

In addition, in practical application of the present application, with respect to the content of the monitoring result that whether the obtained checking result of the monitored object to-be-checked service is valid or not, and the steps executed by the computer device after obtaining the monitoring result, reference may be made to, but not limited to, the description of the corresponding parts of the above embodiments.

In summary, in this embodiment, compared to the above embodiments provided in this application, in order to obtain an accurate and real audit time for the monitored object to audit the service to be audited, in this embodiment, an audit time statistical model capable of obtaining an accurate and real effective audit time by using the audit state image and the shooting frequency is trained in advance, so that, in the process of auditing the service to be audited by the monitored object, after the image collector is controlled to capture continuous multiple frames of audit state images according to the target shooting frequency, the obtained continuous multiple frames of audit state images and the target shooting frequency are directly input into the audit time statistical model, the effective time for auditing the service to be audited by the monitored object can be quickly and accurately obtained, and further, the effective audit time is verified reasonably by using the audit time standard of the monitored object, and obtaining whether the current auditing result of the service to be audited is reliable or not so as to decide whether to audit again or enter the next auditing link. Compared with the auditing time of the auditing service obtained only from the time point of starting auditing the service to be audited and the time point of finishing the service with auditing, the auditing time obtaining mode provided by the application is more accurate and reliable, thereby ensuring the reliability and the accuracy of the monitoring result of the service to be audited of the monitored object obtained according to the method.

When the valid audit time is verified, in order to improve verification efficiency and reliability, in this embodiment, the auditor is divided into a plurality of categories, and the image information of the auditor of each category is obtained, so that an audit verification model for verifying whether the audit time is valid or reasonable is obtained by training according to the image information and the audit time.

Referring to fig. 5, which is a schematic flow diagram of another optional example of the service audit monitoring implementation method provided in this embodiment, this embodiment may be another optional detailed implementation manner of the service audit monitoring implementation method provided in the foregoing embodiment, and this embodiment mainly explains an obtaining manner of an audit time standard of a monitored object, and for other implementation steps, reference may be made to descriptions of corresponding parts in the foregoing embodiment, which is not described in detail in this embodiment. As shown in fig. 5, the method may include:

step S31, obtaining the historical behavior data of the monitored object;

the historical behavior data can include related record data of various services checked by the monitored object in the past, such as attribute information of the checked services, effective checking time spent on checking each service, and the like.

Step S32, according to historical behavior data, determining the auditing time standard corresponding to the object class of the monitored object from the auditing time standard corresponding to each preset object class;

for the obtaining process of the respective corresponding audit time standards of the different classes of objects, reference may be made to the description of the corresponding parts in the foregoing embodiments, which is not described in detail in this embodiment.

Step S33, verifying whether the effective auditing time accords with the auditing time standard of the monitored object, and if so, entering step S34; if not, go to step S35;

and step S34, determining that the auditing result of the service to be audited of the monitored object is valid.

And step S35, determining that the auditing result of the to-be-audited service of the monitored object is invalid, and outputting review prompt information.

The review prompt information is used for reminding the monitored object to review the service to be reviewed again, and the output mode of the review prompt information is not limited in the application.

When the verification result is in line with the verification result, the effective verification time of the service to be verified of the monitored object is considered to be reasonable, and the verification result to be verified is considered to be correct and effective; on the contrary, the effective auditing time of the service to be audited of the monitored object is unreasonable, the auditing result to be audited is considered to be incorrect, and the auditing result can be re-audited or transferred to other auditors for re-auditing, and the like, which is not limited in the present application.

It can be seen that, in this embodiment, in each audit link of a service to be audited, the audit process of a corresponding auditor can be monitored according to the above manner, and it is determined that the audit time of the service to be audited is unreasonable this time and the audit result is invalid, and a remedial measure is timely made, so that the next audit link of the service to be audited cannot be directly entered, thereby avoiding that a problem is found in the last audit link (or a later audit link), which causes that the service to be audited must be returned again, which wastes time and labor, and increases the waiting time of a client, and reduces the experience of the client.

In some embodiments provided by the application, after the monitoring mode of the monitored object of the service to be audited is determined according to the above manner, if the monitoring mode is the second monitoring mode, the average auditing time of the monitored object for auditing the services of the same type of the service to be audited can be obtained, and the current auditing time of the monitored object for auditing the services to be audited is counted; and obtaining a monitoring result whether the auditing result of the service to be audited is valid or not aiming at the monitored object according to the comparison result of the current auditing time and the average auditing time. And if the monitoring mode is the third monitoring mode, forbidding to respond to the monitoring request aiming at the checking state of the service to be checked of the monitored object, namely, not needing to supervise the checking process of the service to be checked.

Therefore, in the embodiment of the present application, all monitoring modes of the service to be audited can be divided into three monitoring modes according to the importance degree of the service to be audited (i.e., the content of the audit page), and in practical application, the corresponding monitoring mode can be flexibly selected according to the importance degree of the service to be audited, which needs to be audited, so as to implement supervision on the actual auditor, but the method is not limited to the implementation method described in this embodiment.

In a possible implementation manner, the configuration contents for the different monitoring modes can be stored in a database in the system in advance, so that in an actual monitoring process, the computer device can read the configuration contents, determine the monitoring mode adopted in the checking and monitoring process of the contents to be checked according to the configuration contents, and output the determined monitoring mode to inform the monitored person, thereby reminding the monitored person to check the service to be checked seriously.

Referring to fig. 6, a schematic structural diagram of yet another alternative example of the service audit monitoring implementation apparatus provided in this application, which may be applied to the foregoing computer device, as shown in fig. 6, may include:

a monitoring parameter obtaining module 31, configured to obtain a monitoring parameter for a service to be audited and for auditing a monitored object of the service to be audited;

wherein the monitoring parameters include: and the image collector shoots the target shooting frequency of the monitored object for auditing the auditing state of the service to be audited.

An audit state image obtaining module 32, configured to obtain, during the process of auditing the service to be audited by the monitored object, a plurality of continuous audit state images shot by the image collector according to the target shooting frequency;

an effective audit time obtaining module 33, configured to obtain, according to the continuous multiple frames of audit state images and the target shooting frequency, effective audit time for the monitored object to audit the service to be audited;

in some embodiments, as described with reference to fig. 7, the valid audit time obtaining module 33 may include:

an audit time statistical mode processing unit 331, configured to input the continuous multiple frames of audit state images and the target shooting frequency into an audit time statistical model, and output effective audit time for the monitored object to audit the service to be audited;

In a possible implementation manner, as shown in fig. 7, in order to implement the training of the statistical model of the audit time, the valid audit time obtaining module 33 may further include:

a first sample data obtaining unit 332, configured to obtain different sample shooting frequencies and continuous multiple frames of sample audit state images shot at the different shooting frequencies;

a model training unit 333, configured to input the sample shooting frequency and the corresponding continuous multi-frame sample audit state image into a neural network, perform learning training according to a genetic algorithm until a training constraint condition is met, and determine a neural network model obtained through final training as an audit time statistical model;

And the effective auditing time verifying module 34 is configured to verify the effective auditing time according to the auditing time standard of the monitored object, so as to obtain a monitoring result for auditing the service to be audited by the monitored object.

In some embodiments, the apparatus may further include:

the historical behavior data acquisition module is used for acquiring historical behavior data of the monitored object;

an audit time standard determining module, configured to determine, according to the historical behavior data, an audit time standard corresponding to an object class to which the monitored object belongs from audit time standards corresponding to respective preset multiple classes of objects;

based on this, the valid audit time verification module 34 may include:

the checking time verifying unit is used for verifying whether the effective checking time meets the checking time standard of the monitored object;

and the first determining unit is used for determining that the monitored object is valid for the auditing result of the service to be audited under the condition that the verifying result of the auditing time verifying unit is yes.

A second determining unit, configured to determine that the audit result of the monitored object on the service to be audited is invalid when the verification result of the auditing time verifying unit is negative;

and the review prompt information output unit is used for outputting review prompt information under the condition that the monitoring object is determined to be invalid to the auditing result of the service to be audited, and the review prompt information is used for reminding the monitoring object to audit the service to be audited again.

In some embodiments of the present application, the valid audit time verification module 34 may also include:

the auditing and verifying module processing unit is used for inputting the effective auditing time and the image information corresponding to the monitored object into an auditing and verifying model and outputting a monitoring result of whether the auditing result of the monitored object to the service to be audited is effective;

In still other embodiments provided in the present application, the monitoring parameter obtaining module 31 may include:

the service type acquisition unit is used for acquiring the service type of the service to be audited;

a monitoring mode determining unit, configured to determine, according to the service type, a monitoring mode for the monitored object of the service to be audited;

a target shooting frequency obtaining unit, configured to obtain, when the monitoring mode is the first monitoring mode, a target shooting frequency, which is matched with the service type and used by the image collector to shoot the monitored object to audit the audit state of the service to be audited;

based on this, the above apparatus may further include:

the average auditing time obtaining device is used for obtaining the average auditing time of the monitored object for auditing the same type of service of the service to be audited under the condition that the monitoring mode is the second monitoring mode;

a current auditing time counting module, configured to count current auditing time for auditing the service to be audited by the monitored object;

a current auditing time comparison module, configured to obtain a monitoring result indicating whether the auditing result of the to-be-audited service for the monitored object is valid or not according to the comparison result between the current auditing time and the average auditing time;

and the monitoring request processing module is used for forbidding to respond to the monitoring request aiming at the auditing state of the monitored object for auditing the service to be audited under the condition that the monitoring mode is the third monitoring mode.

It should be noted that, various modules, units, and the like in the embodiments of the foregoing apparatuses may be stored in the memory as program modules, and the processor executes the program modules stored in the memory to implement corresponding functions, and for the functions implemented by the program modules and their combinations and the achieved technical effects, reference may be made to the description of corresponding parts in the embodiments of the foregoing methods, which is not described in detail in this embodiment.

The present application further provides a storage medium, on which a program is stored, where the program, when executed by a processor, implements the steps of the service auditing and processing method, and the specific implementation process may refer to the description of the corresponding parts of the embodiments of the method.

Finally, it should be noted that, in the present specification, the embodiments are described in a progressive or parallel manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device, the system and the computer equipment disclosed by the embodiment correspond to the method disclosed by the embodiment, so that the description is relatively simple, and the relevant points can be referred to the method part for description.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for implementing service audit monitoring is characterized in that the method comprises the following steps:

2. The method according to claim 1, wherein the obtaining of the effective review time for the monitored object to review the service to be reviewed according to the continuous multiple review state images and the target shooting frequency includes:

3. The method of claim 2, wherein the training process of the statistical model of audit time comprises:

4. The method according to claim 1, wherein the obtaining of the audit time criteria of the monitored object comprises:

acquiring historical behavior data of the monitored object;

5. The method according to claim 1, wherein the verifying the valid audit time according to the audit time standard of the monitored object to obtain the monitoring result of auditing the service to be audited for the monitored object includes:

6. The method according to claim 4 or 5, characterized in that the method further comprises:

7. The method according to any one of claims 1 to 5, wherein the obtaining of the monitoring parameters for the service to be audited and the auditing of the monitored object of the service to be audited includes:

acquiring the service type of a service to be audited;

8. The method of claim 7, further comprising:

9. A service audit monitoring implementation device is characterized in that the device comprises:

10. A service audit monitoring implementation system is characterized in that the system comprises:

a computer device, the computer device comprising:

a communication interface;

a memory for storing a program for implementing the service audit monitoring implementation method according to any one of claims 1 to 8;

a processor for loading and executing the program stored in the memory to implement the steps of the service audit monitoring implementation method according to any one of claims 1 to 8.