CN111815169A

CN111815169A - Business approval parameter configuration method and device

Info

Publication number: CN111815169A
Application number: CN202010659624.XA
Authority: CN
Inventors: 赵若愚; 沈巍毅; 钱铖; 瞿伟
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2020-07-09
Filing date: 2020-07-09
Publication date: 2020-10-23
Anticipated expiration: 2040-07-09
Also published as: CN111815169B

Abstract

The application provides a method and a device for configuring service approval parameters, wherein the method comprises the following steps: acquiring a plurality of sets of approval parameter sets corresponding to a target service scene, wherein the sets of approval parameter sets comprise: a plurality of approval parameters and the incidence relation among the approval parameters; determining a plurality of target approval sub-scenes corresponding to the target service scene by applying a preset spectral clustering model and each approval parameter group, wherein each target approval sub-scene comprises: and at least one group of examination and approval parameter groups are used for determining a target examination and approval sub-scene corresponding to a parameter configuration request when the parameter configuration request of a target auditor is received. The method and the device can improve accuracy and efficiency of parameter configuration, are suitable for complex parameter configuration scenes, and further improve accuracy and efficiency of service approval.

Description

Business approval parameter configuration method and device

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for configuring service approval parameters.

Background

Aiming at the approval requirements of different users at different stages, different approval processes need to be developed in a customized manner, wherein parameters are configured as core links in the process of the customized development approval processes, and the trend of the processes is dynamically controlled. Therefore, the completeness and correctness of the parameter configuration directly affect the accuracy of the operation of the approval process. In the prior art, the parameter configuration process has the following problems:

(1) the service flow is complex, and the configuration is difficult: at present, many business approval needs not only the authorized person of the mechanism at the current level to perform approval, but also the authorized person of the mechanism at the higher level or even the higher level to perform approval, so that the configuration of the relevant parameters of the approval process is based on dynamism, and the compatibility is difficult to be realized by using a set of fixed configuration method within a certain interval range. Environmental failures due to parameter mismatch are therefore likely to occur.

(2) The mechanism is complicated, and the parameter classification is many: large companies often have the right to set a parameter list which accords with the characteristics of the company for a specific service in headquarters, province level subdivisions and city level subdivisions and does not violate superior institutions. Some service scenes even allow the sub-organizations to set characteristic parameters, so that the problems of low efficiency, missing configuration and mismatching are often caused during configuration due to complicated organizations and parameter types, so that the actual service function is influenced, and further the production efficiency is influenced.

(3) The parameter configuration process is complicated, time-consuming and labor-consuming: when configuring parameters, the parameter configuration is often completed by adopting the processes of parameter searching, parameter inputting and parameter checking, so that the efficiency is low, and the parameters are possibly omitted to influence the production efficiency.

Disclosure of Invention

Aiming at the problems in the prior art, the application provides a method and a device for configuring service approval parameters, which can improve the accuracy and efficiency of parameter configuration, are suitable for complex parameter configuration scenes, and further can improve the accuracy and efficiency of service approval.

In order to solve the technical problem, the present application provides the following technical solutions:

in a first aspect, the present application provides a method for configuring service approval parameters, including:

acquiring a plurality of sets of approval parameter sets corresponding to a target service scene, wherein the sets of approval parameter sets comprise: a plurality of approval parameters and the incidence relation among the approval parameters;

determining a plurality of target approval sub-scenes corresponding to the target service scene by applying a preset spectral clustering model and each approval parameter group, wherein each target approval sub-scene comprises: and at least one group of examination and approval parameter groups are used for determining a target examination and approval sub-scene corresponding to a parameter configuration request when the parameter configuration request of a target auditor is received.

Further, before the applying a preset spectral clustering model and each approval parameter group and determining a plurality of target approval sub-scenes corresponding to the target service scene, the method further includes: obtaining historical user information groups corresponding to the examination and approval parameter groups respectively, wherein the historical user information groups comprise: role information and organization information of historical users; correspondingly, when a parameter configuration request of a target auditor is received, determining a target approval sub-scene corresponding to the parameter configuration request includes: receiving a parameter configuration request of a target auditor, wherein the parameter configuration request comprises: role information and organization information of a target auditor; determining a historical user information group matched with the role information and the organization information of the target auditor; and determining a target approval sub-scene corresponding to the target auditor based on the approval parameter group corresponding to the matched historical user information group, and outputting and displaying each approval parameter group corresponding to the target approval sub-scene.

Further, the acquiring multiple sets of approval parameter sets corresponding to the target service scene includes: acquiring a plurality of sets of historical parameter sets corresponding to a target service scene and historical parameter vector sets corresponding to the historical parameter sets respectively; respectively applying a preset scene parameter mapping matrix and each historical parameter vector group to carry out similarity calculation, and taking the historical parameter vector group with the similarity calculation result larger than the optimal similarity threshold value as a target parameter vector group; and taking the historical parameter group corresponding to the target parameter vector group as the approval parameter group.

Further, before the applying the preset scene parameter mapping matrix and each historical parameter vector group to perform similarity calculation, the method further includes: performing an iteration step: obtaining an updated initial similarity threshold by applying a preset similarity optimization model, an initial similarity threshold and each historical parameter group, wherein the similarity optimization model is a machine learning model which is obtained by pre-training and is based on an L-BFGS algorithm; and acquiring a historical parameter vector group of which the similarity calculation result is greater than the updated initial similarity threshold as an intermediate parameter vector group, judging whether the ratio of the number of the intermediate parameter vector group to the total number of the historical parameter vector group is less than or equal to a proportional threshold, if so, applying the updated initial similarity threshold to execute the iteration step again, otherwise, stopping executing the iteration step and taking the current initial similarity threshold as the optimal similarity threshold.

Further, the preset spectral clustering model is a machine learning model based on a spectral clustering algorithm and obtained through pre-training, and is used for classifying the approval parameter group.

Further, the preset spectral clustering model includes: a gaussian kernel function and a number of separation clusters; correspondingly, before the determining of the plurality of target approval sub-scenes corresponding to the target service scene, the method further includes: and optimizing the Gaussian kernel function and the number of the separation clusters by using a simulated annealing algorithm.

In a second aspect, the present application provides a device for configuring service approval parameters, including:

the first obtaining module is configured to obtain multiple sets of approval parameter sets corresponding to a target service scene, where the approval parameter sets include: a plurality of approval parameters and the incidence relation among the approval parameters;

a determining module, configured to apply a preset spectral clustering model and each approval parameter group to determine a plurality of target approval sub-scenes corresponding to the target service scene, where each target approval sub-scene includes: and at least one group of examination and approval parameter groups are used for determining a target examination and approval sub-scene corresponding to a parameter configuration request when the parameter configuration request of a target auditor is received.

Further, the device for configuring the service approval parameters further includes: a second obtaining module, configured to obtain a historical user information group corresponding to each group of the approval parameter groups, where the historical user information group includes: role information and organization information of historical users; correspondingly, the determining module is configured to perform the following: receiving a parameter configuration request of a target auditor, wherein the parameter configuration request comprises: role information and organization information of a target auditor; determining a historical user information group matched with the role information and the organization information of the target auditor; and determining a target approval sub-scene corresponding to the target auditor based on the approval parameter group corresponding to the matched historical user information group, and outputting and displaying each approval parameter group corresponding to the target approval sub-scene.

Further, the first obtaining module is configured to perform the following: acquiring a plurality of sets of historical parameter sets corresponding to a target service scene and historical parameter vector sets corresponding to the historical parameter sets respectively; respectively applying a preset scene parameter mapping matrix and each historical parameter vector group to carry out similarity calculation, and taking the historical parameter vector group with the similarity calculation result larger than the optimal similarity threshold value as a target parameter vector group; and taking the historical parameter group corresponding to the target parameter vector group as the approval parameter group.

Further, the device for configuring the service approval parameters further includes: an iteration module for performing the iteration step: obtaining an updated initial similarity threshold by applying a preset similarity optimization model, an initial similarity threshold and each historical parameter group, wherein the similarity optimization model is a machine learning model which is obtained by pre-training and is based on an L-BFGS algorithm; and the optimal similarity threshold determining module is used for acquiring a historical parameter vector group of which the similarity calculation result is greater than the updated initial similarity threshold as an intermediate parameter vector group, judging whether the ratio of the number of the intermediate parameter vector group to the total number of the historical parameter vector group is less than or equal to a proportional threshold, if so, applying the updated initial similarity threshold to execute the iteration step again, and if not, stopping executing the iteration step and taking the current initial similarity threshold as the optimal similarity threshold.

Further, the preset spectral clustering model includes: a gaussian kernel function and a number of separation clusters; correspondingly, the service approval parameter configuration device further comprises: and the optimization module is used for optimizing the Gaussian kernel function and the number of the separation clusters by applying a simulated annealing algorithm.

In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the method for configuring the service approval parameter when executing the program.

In a fourth aspect, the present application provides a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed, the method for configuring the service approval parameters is implemented.

According to the technical scheme, the method and the device for configuring the service approval parameters are provided. Wherein, the method comprises the following steps: acquiring a plurality of sets of approval parameter sets corresponding to a target service scene, wherein the sets of approval parameter sets comprise: a plurality of approval parameters and the incidence relation among the approval parameters; determining a plurality of target approval sub-scenes corresponding to the target service scene by applying a preset spectral clustering model and each approval parameter group, wherein each target approval sub-scene comprises: the method comprises the steps that at least one group of examination and approval parameter groups are used for determining a target examination and approval sub-scene corresponding to a parameter configuration request when the parameter configuration request of a target auditor is received, so that the accuracy and efficiency of parameter configuration can be improved, the accuracy of service examination and approval can be further improved, specifically, the intelligentization and visualization degree of parameter configuration can be improved, and the possibility of parameter missing is reduced; based on the incidence relation between the service scene and the role, the personalized configuration of the parameters can be realized; the problem of complexity and variability in the parameter configuration process can be solved, the labor and time cost is reduced, and meanwhile, the usability and maintainability of parameter configuration can be improved.

Drawings

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

FIG. 1 is a schematic flow chart of a method for configuring service approval parameters in an embodiment of the present application;

FIG. 2 is a schematic flow chart illustrating a method for configuring business approval parameters according to another embodiment of the present application;

fig. 3 is a schematic flowchart of steps S301 to S303 in the method for configuring service approval parameters in the embodiment of the present application;

fig. 4 is a schematic flowchart of step S401 and step S402 in the method for configuring service approval parameters in the embodiment of the present application;

FIG. 5 is a flowchart illustrating a parameter configuration method based on a service scenario in an application example of the present application;

fig. 6 is a schematic flowchart of steps 10 to 12 in a parameter configuration method based on a service scenario in an application example of the present application;

FIG. 7 is a schematic diagram showing a comparison of logical relationships among a minimum closed loop, a theoretical maximum closed loop and a rational closed loop in an application example of the present application;

FIG. 8 is a schematic flowchart illustrating steps 20 to 22 in a parameter configuration method based on a service scenario in an application example of the present application;

FIG. 9 is a schematic flowchart of steps 30 to 32 in a parameter configuration method based on a service scenario in an application example of the present application;

FIG. 10 is a flow chart illustrating a visualization parameter configuration process in an application example of the present application;

FIG. 11 is a diagram illustrating an effect of a parameter configuration interface in an exemplary application of the present application;

FIG. 12 is a schematic structural diagram of a service approval parameter configuration apparatus in an embodiment of the present application;

FIG. 13 is a diagram illustrating an example of a comparison between the configuration time of the existing parameter setting mode and the configuration time of the service approval parameter configuration method of the present application;

FIG. 14 is a diagram illustrating a comparison of single approval pass rates of an exemplary application of the prior art parameter setting mode and the business approval parameter configuration method of the present application;

fig. 15 is a block diagram schematically illustrating a system configuration of an electronic device 9600 according to an embodiment of the present application.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, 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.

Based on this, in order to improve accuracy and efficiency of parameter configuration, and be applicable to a complex parameter configuration scenario, and further improve accuracy and efficiency of service approval, an embodiment of the present application provides a service approval parameter configuration apparatus, which may be a server or a client device, where the client device may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, an intelligent wearable device, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch and intelligent bracelet etc..

In practical applications, the part for configuring the service approval parameter may be executed on the server side as described above, or all operations may be completed in the client device. The selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. The client device may further include a processor if all operations are performed in the client device.

The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.

The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of this application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.

The following examples are intended to illustrate the details.

In order to improve the accuracy and efficiency of parameter configuration, and be applicable to a complex parameter configuration scenario, and further improve the accuracy and efficiency of service approval, this embodiment provides a service approval parameter configuration method whose execution subject is a service approval parameter configuration device, as shown in fig. 1, the method specifically includes the following contents:

step S101: acquiring a plurality of sets of approval parameter sets corresponding to a target service scene, wherein the sets of approval parameter sets comprise: a plurality of examination and approval parameters and the incidence relation among the examination and approval parameters.

The target business scenario may be a production scenario used in actual production, having a complete process and having multiple sub-scenarios, such as business trip approval and business hospitality fee approval scenarios.

The approval parameters comprise audit role information and audit authority information corresponding to the audit role information. And the incidence relation between the auditing parameters represents the incidence relation between the auditing role information. The approval role information may be: department responsible person, financial approver and financial department responsible person information; the incidence relation among the approval role information can be that a department responsible person, a financial approval member and a financial department responsible person are in turn incidence.

Step S102: determining a plurality of target approval sub-scenes corresponding to the target service scene by applying a preset spectral clustering model and each approval parameter group, wherein each target approval sub-scene comprises: and at least one group of examination and approval parameter groups are used for determining a target examination and approval sub-scene corresponding to a parameter configuration request when the parameter configuration request of a target auditor is received.

The preset spectral clustering model is a machine learning model which is obtained by pre-training and based on a spectral clustering algorithm, and is used for classifying the approval parameter group. The spectral clustering model is suitable for processing sparse data as well as complex data.

As can be seen from the above description, in this embodiment, by applying the spectral clustering model, a target service scene can be efficiently and accurately divided to obtain a plurality of target approval sub-scenes, and then target approval sub-scenes corresponding to each approver can be configured, where each target sub-scene includes at least one group of approval parameter sets; in conclusion, the accuracy and efficiency of parameter configuration can be improved, the method is suitable for complex parameter configuration scenes, and the accuracy and efficiency of service approval are further improved.

In an application example of the present application, the step S102 includes: constructing a corresponding directed graph based on each approval parameter group; generating a weighted adjacency matrix and a degree matrix corresponding to the directed graph; obtaining a Laplace matrix based on the degree matrix and the degree matrix; solving a feature vector corresponding to the minimum eigenvalue of a preset number of Laplace matrixes, and constructing a feature vector space; clustering the feature vectors in the feature vector space by using a multi-path spectral clustering algorithm to obtain a plurality of cluster partitions, namely the target approval sub-scenes, wherein each target approval sub-scene comprises: at least one set of said approval parameter sets. The preset number can be set according to actual needs.

In order to further improve the accuracy of the parameter configuration, referring to fig. 2, in an embodiment of the present application, before step S102, the method further includes:

step S201: obtaining historical user information groups corresponding to the examination and approval parameter groups respectively, wherein the historical user information groups comprise: and character information and organization information of the historical users.

Correspondingly, step S102 includes:

step S202: determining a plurality of target approval sub-scenes corresponding to the target service scene by applying a preset spectral clustering model and each approval parameter group, wherein each target approval sub-scene comprises: at least one set of said approval parameter sets.

Step S203: receiving a parameter configuration request of a target auditor, wherein the parameter configuration request comprises: role information and organization information of the target auditor.

Step S204: and determining a historical user information group matched with the role information and the organization information of the target auditor.

Step S205: and determining a target approval sub-scene corresponding to the target auditor based on the approval parameter group corresponding to the matched historical user information group, and outputting and displaying each approval parameter group corresponding to the target approval sub-scene.

Specifically, after the output display of each approval parameter group, the method may further include: and receiving a parameter group selection request of the target auditor, and determining a target approval parameter group corresponding to the target auditor according to the parameter group selection request so as to configure the parameter values of all the parameters in the target approval parameter group.

As can be seen from the above description, in this embodiment, by associating the approval sub-scene with the role information and deducing the relationship between the two, the auditor can visually see the role corresponding to the auditor and the parameter configuration scene under the mechanism where the auditor is located, so that the communication from the role to the business scene, from the business scene to the sub-scene, and then to the specific parameter can be realized, and the reliability of parameter configuration is improved.

For example, when the target business scenario is a hospitality fee approval scenario, the business approval parameter configuration method includes:

s211: acquiring the respective corresponding hospitality fee approval parameter groups of a plurality of historical users, wherein each approval parameter group comprises: and the business hospitality fee approval roles, the authority information of each hospitality fee approval role and the incidence relation among the approval roles.

The service hospitality fee approval role can comprise: department responsible persons, financial approvers and financial department responsible persons; the incidence relation among the approval roles can be that a department responsible person, a financial approval member and a financial department responsible person are sequentially associated.

S212: grouping the set of hospitality fee approval parameters by using a preset spectral clustering model to obtain a plurality of target hospitality fee approval sub-scenes, wherein each target hospitality fee approval sub-scene comprises: at least one set of said hospitality fee approval parameter sets.

S213: and receiving a parameter configuration request of the target auditor, determining a target approval sub-scene corresponding to the target auditor according to the parameter configuration request, and outputting and displaying each hospitality fee approval parameter group in the target approval sub-scene.

S214: and receiving a parameter group selection request of the target auditor, and determining a hospitality fee examination and approval parameter group corresponding to the target auditor according to the parameter group selection request so as to configure the parameter values of all parameters in the hospitality fee examination and approval parameter group.

S215: and if the admission charge examination and approval request of the target user is received, determining an admission charge examination and approval parameter group corresponding to the admission charge examination and approval request and parameter values of all parameters in the admission charge examination and approval parameter group so as to complete the examination and approval process of the admission charge of the target user.

As can be seen from the above description, in this example, parameter configuration of different target approval sub-scenes can be realized, and target approval sub-scenes corresponding to different auditors are determined, so that the parameter configuration process is efficient and accurate, and the efficiency and accuracy of the approval process are further improved.

In order to obtain a reliable approval parameter set and then determine different target approval sub-scenarios by using the reliable approval parameter set, referring to fig. 3, in an embodiment of the present application, step S101 includes:

step S301: acquiring a plurality of sets of historical parameter sets corresponding to a target service scene and historical parameter vector sets corresponding to the historical parameter sets respectively.

Specifically, each of the sets of history parameters includes: and the unique historical user completes the approval parameters applied in the parameter configuration process once and the incidence relation among the approval parameters. Judging whether each approval parameter in a preset maximum approval parameter closed loop exists in the historical parameter group, if so, setting the corresponding position in the historical parameter vector group as 1, and if not, setting the corresponding position in the historical parameter vector group as 0 to generate the historical parameter vector group, wherein the length of the preset maximum approval parameter closed loop is the same as that of the historical parameter vector group.

Step S302: and respectively applying a preset scene parameter mapping matrix and each historical parameter vector group to carry out similarity calculation, and taking the historical parameter vector group with the similarity calculation result larger than the optimal similarity threshold as a target parameter vector group.

Specifically, the Scene Parameter mapping matrix is a Parameter and Scene mapping matrix (PMMS), referred to as a, which is a Z × J matrix, where a column dimension represents a preset service sub-Scene in a target service Scene, a row dimension is determined according to a length of a maximum closed-loop Parameter, and a Parameter of each sub-Scene is mapped at the length, that is, the row dimension represents a preset maximum closed-loop Parameter in each preset service sub-Scene, and may be set according to actual needs. The matrix is used to characterize the details of the parameters used in the different sub-scenarios. Since the matrix is a 0-1 matrix, 0 represents that the parameter is not used in the sub-scene, 1 represents that the parameter is used in the sub-scene, a standard PMMS matrix is as follows:

step S303: and taking the historical parameter group corresponding to the target parameter vector group as the approval parameter group.

As can be seen from the above description, in this embodiment, by applying the scene parameter mapping matrix and the similarity algorithm, filtering the historical parameter set, removing redundant data, and obtaining a reliable approval parameter set can be achieved, so that reliability and efficiency of parameter configuration can be improved.

In order to obtain a reliable similarity threshold and further apply the reliable similarity threshold to improve the reliability of obtaining the target parameter vector set, referring to fig. 4, in an embodiment of the present application, before step S302, the method further includes:

step S401: performing an iteration step: and obtaining an updated initial similarity threshold by applying a preset similarity optimization model, an initial similarity threshold and each historical parameter group, wherein the similarity optimization model is a machine learning model which is obtained by pre-training and is based on an L-BFGS algorithm.

Step S402: and acquiring a historical parameter vector group of which the similarity calculation result is greater than the updated initial similarity threshold as an intermediate parameter vector group, judging whether the ratio of the number of the intermediate parameter vector group to the total number of the historical parameter vector group is less than or equal to a proportional threshold, if so, applying the updated initial similarity threshold to execute the iteration step again, otherwise, stopping executing the iteration step and taking the current initial similarity threshold as the optimal similarity threshold.

The updated initial similarity threshold is applied to execute the iteration step again, and the updated initial similarity threshold is used as the initial similarity threshold in the iteration step; the applying the preset similarity optimization model, the initial similarity threshold, and each of the historical parameter sets to obtain an updated initial similarity threshold, which may include: obtaining a gradient and a self-conjugate matrix corresponding to the initial similarity threshold according to each historical parameter group; and obtaining an updated initial similarity threshold according to the gradient and the self-conjugate matrix.

Specifically, the initial similarity threshold is set to be gamma, the percentage number TPR of the number of parameters with positive prediction and positive result in the total number is greater than the preset value theta, the adopted iteration method is an L-BFGS algorithm, and the specific iteration process is as follows:

s41: inputting an initial similarity threshold value gamma and a sample set m, wherein the sample set is a historical parameter set, and the output result is a threshold value.

S42: when TPR is not more than θ, execute steps S43 to S47, otherwise execute S48.

S43: calculating the gamma gradient:

s44: calculating a Hessian matrix:

s45: calculating the inverse H of the Hessian matrix^-1。

S46: and (3) calculating and updating: Δ γ ← H^-1g。

S47: application updating: γ ← γ + Δ γ.

S48: and outputting a result: and gamma.

As can be seen from the above description, in this embodiment, by efficiently and accurately obtaining the optimal similarity threshold, the optimal similarity threshold can be applied to filter the historical parameter vector group, so as to obtain a reliable target parameter vector group.

In order to obtain an efficient and reliable spectral clustering model, the spectral clustering model is further applied to group the approval parameter groups to obtain a plurality of target approval sub-scenes and the approval parameter groups in each target approval sub-scene; in an embodiment of the present application, the preset spectral clustering model includes: a gaussian kernel function and a number of separation clusters; correspondingly, before step S102, the method further includes: and optimizing the Gaussian kernel function and the number of the separation clusters by using a simulated annealing algorithm.

As can be seen from the above description, in this embodiment, by optimizing the gaussian kernel function and the number of the separation clusters, the reliability and efficiency of the spectral clustering model can be improved, and further, the accuracy and efficiency of obtaining the target approval sub-scenes are improved, so as to determine the target approval sub-scenes corresponding to different auditors, and the auditors do not need to manually configure parameters item by item.

In order to further improve the efficiency and quality of parameter configuration and ensure the robustness of parameters, the application example of the application provides a parameter configuration method based on a service scene. The application example comprises a theoretical method and a data base for realizing parameter visualization configuration on a theoretical side, but does not comprise implementation specific details and data supply of related methods. The application example includes module disassembly and sample display from the functional and architecture perspectives on the application side, but does not include specific implementation details such as detailed design, table structure design and the like on the application side.

For the application side: the theoretical side of the application can be applied to the development of various different terminals and different platforms. From the perspective of the terminal, those skilled in the art can develop a related visual display and configuration module for a smart phone, a tablet electronic device, a portable computer, and a desktop computer according to the related theoretical method of the present application. The application side of the application is based on a B/S architecture and web application taking a browser as a medium.

The following detailed development steps are set forth based on the legend:

fig. 5 is a flowchart of an overall implementation of a parameter configuration method based on a service scenario, where a main body is divided into four parts, as shown in fig. 5, the method includes the following contents:

step 100: based on the service scene, a one-to-many relationship is formed by combining the specific parameter configuration process of the service scene, and the mapping relationship between the service scene and the minimum closed-loop parameter set and the theoretical maximum closed-loop configuration parameter set is realized.

Wherein, this step provides a basis for establishing the parameter and scene mapping matrix and the check of the whole flow basic data in step 200. The service scenarios all refer to an actual and complete service flow scenario: such as hospitality approval and business approval. For such a business scenario, there are minimum necessary flows that can satisfy the scenario flow, and maximum flows, referred to as minimum closed loop and theoretical maximum closed loop.

For the business scenario, the following is set forth in the context of business hospitality fee approval. There are several necessary and optional steps, based on different circumstances:

the method comprises the following necessary steps:

(1) the department responsible person examines and approves, need to confirm the personnel and examine and approve the role;

(2) the financial auditor needs to determine the auditing ranges of the financial accounting department and the auditor;

(3) the responsible person of the financial accounting department needs to determine the examination and approval role of the person and the control parameter list of the responsible person of the department.

Optional steps are as follows:

between the necessary steps (1) and (2), optional steps can be added:

1) the examination and approval of the returning department need to determine the examination and approval roles of the returning department and personnel;

2) the responsible person of the returning department needs to determine the returning department, the examining and approving role of the person and the responsible person of the returning department.

After the necessary step (3), optional steps can be added:

3) the captain needs to determine the approval mode and the authorized person of the business captain;

4) reporting to a superior bank (a superior bank returning port and a financial accounting), and determining a principal of the superior bank returning port, a personnel approval role and a returning port department;

5) a financial audit meeting needs to determine a financial audit meeting consultation standard;

6) applying for reimbursement, wherein the receipt acceptance and approval modes of the general switch parameter table need to be determined;

7) the department responsible person examines and approves, confirm the personnel and examine and approve the role;

8) the back-to-mouth department examines and approves, and confirms the examination and approval roles of the back-to-mouth department and personnel;

9) the responsible person of the returning department confirms the returning department, the examining and approving role of the personnel and the responsible person of the returning department;

10) the financial reimbursement auditor confirms the auditing ranges of the financial accounting department and the auditor;

11) the accountant of the financial accounting department confirms the approval role of the personnel and the control parameter list of the accountant of the department;

12) the business leader confirms the approval mode and the authorized person of the business leader;

13) the information is reported to the superior level (the superior level returns to the mouth, the financial accounting), and the superior level returns to the mouth, the personnel approves roles, and the responsible person of the department of returning to the mouth.

Specifically, the parameter set of the service scenario is a parameter set of all required configurations that are further matched according to different possible service flows in the actual service system. The minimum closed-loop parameter set refers to a compliance parameter set which can implement closed-loop approval of the service scene and needs to be configured with the least parameters, and the minimum closed-loop parameter set is from step (1) to step (3) for the service hospitality scene. And the theoretical maximum closed-loop configuration parameter set refers to that a part of links are added on the basis of the minimum closed-loop parameter set, so that the minimum closed-loop parameter set becomes a parameter set of a subset of the minimum closed-loop parameter set, and for a service hospitality scenario, the theoretical maximum closed-loop configuration parameter set is that steps 1) to 13 are added on the basis of steps (1) to (3) (ignoring approval refusal). It is worth pointing out that: in fact for some of the business processes of a partial business system, it is in fact possible to make "dead cycles", i.e. to always circulate between the added parts. The theoretical maximum closed-loop parameter set here is therefore in fact a "finite" expanded part of the flow, the considered case being based on the judgment of the real traffic flow situation. After determining the best minimum set and the maximum set, the following conclusions can be drawn:

for a collection of parameter sets

Where i denotes a user role and j denotes a service scenario j.

Defining a minimum closed-loop parameter set and a theoretical maximum closed-loop configuration parameter set:

and

then there is

Defining an additional newly added parameter set

Then there is

Where k represents the kth parameter in the additional parameter set, and λ represents whether the parameter exists, then the value of λ is {0,1 }. Thus, for the minimum closed-loop parameter set and the theoretical maximum closed-loop configuration parameter set, there is the following relationship:

in step 100, a service scenario j and a minimum set of closed-loop parameters are mainly established

And theoretical maximum closed loop configuration parameter set

The part depends on the abstract ability of business personnel and business product managers on business scenes and the accuracy and precision of judging associated parameters.

Step 200: establishing a parameter and a scene mapping matrix of a service scene based on a corresponding relation between the service scene and a theoretical maximum closed-loop configuration parameter set; and measuring the matching degree of each service sub-scene in the service scene with the actual historical data through the similarity, and obtaining the optimal similarity threshold through training of a training set.

Specifically, if the matching is performed, a sub-scene parameter set is established, that is, a mapping relation between actual historical data and a service sub-scene is used as a training set 1; establishing a mapping relation between the service sub-scenes and mechanisms and roles of the parameter managers, and a training set 2, and providing a data basis for the subsequent common service sub-scene division and the personnel mechanism matching, wherein the common service sub-scenes are subsets of the service sub-scenes, and the result of spectral clustering is to cluster the common service sub-scenes in the sub-scenes based on historical data, namely the target approval sub-scenes; and if not, further analyzing whether the actual historical data is dirty data or not, and whether the actual historical data is one of a newly added service scene and a service sub-scene or not.

When the system is used in an actual service system, the mechanism and role of a parameter configuration manager and a parameter set during each closed-loop parameter setting, namely actual historical data, need to be recorded

Assume that the current set of all parameters is

Wherein

Representing the mth parameter in the service scenario j, there is a parameter set

Wherein z is_jRepresenting the maximum number of the traffic scenario parameters. Note that there are two parameters with the same name, type, present in different traffic scenarios. The total number of the defined parameters is Z, having

A mapping matrix a ═ a of parameters and service scenarios may be constructed here_pqWherein the element a_pqThe value rule is as follows:

the dimension of the mapping matrix is Z × J. For each service scene, a dimension z can be constructed_jIs defined as the column vector (i.e. the column vector formed by the set of theoretical maximum closed-loop configuration parameters).

Based on the above data, it may first be determined whether it is dirty data by comparing dimensions. If so, it is deleted. Otherwise, the similarity between each parameter configuration result and the service scene is obtained through matrix multiplication. Obviously, the scene with higher similarity indicates that the setting is more prone to setting the scene. In addition, if the actual intention of the parameter administrator is known in advance, a threshold exists, when the similarity of a certain scene is higher than the value, the intention of the setting is determined to set the corresponding scene, the prediction is called as positive, when the result is positive, the situation is called as true, the situation is marked as true, the situation is called as true positive, TP for short, the situation is indicated that the parameter set belongs to a certain sub-scene after the similarity determination, and the true intention of the parameter administrator for the parameter setting is also the situation of the scene; when the prediction is negative and the result is Positive, the result is marked as False Positive, abbreviated as FP, which indicates that the parameter set does not belong to a certain sub-scene but actually belongs to a certain sub-scene after the similarity determination.

By using different thresholds, it is clear that different probabilities can be obtained. A true rate (TPR) is defined herein, which refers to the ratio of the total number of positive predictions and positive results (i.e., the number of TPs), the higher the ratio, the better the prediction accuracy. By obtaining the most appropriate threshold, TRP is approximated to 1. At this time, a mapping relationship between actual parameter closed-loop setting historical data and actual sub-scenes can be established. Furthermore, each piece of historical data has information of a role of a parameter manager, so that the mapping relation between the sub-scenes and the user roles can be obtained through simple clustering. As the basic data for the next step.

Step 300: carrying out business sub-scene division on an actual business scene by using a training set 1, and correcting the width of a minimum closed-loop parameter set and a theoretical maximum closed-loop configuration parameter set; and the mapping relation between the actual service scene and the user role obtained by the training set 2 is used for realizing configuration recommendation of different parameter managers, namely prompting the managers about the role common sub-scene.

Specifically, a training set 1 is used for further commonly dividing an actual service scene, namely the service scene, into sub-scenes, and the intervals between the actual service scene and the environments of the minimum closed-loop parameter set and the theoretical maximum closed-loop configuration parameter set are further corrected according to the division result; and obtaining the mapping relation between the actual service scene and the user role by using the training set 2. Configuration recommendation of different parameter administrators is realized, namely, closed-loop parameter setting commonly used by roles of the administrators is prompted, and a data basis is provided for visualization parameter configuration in step 400.

Based on the calculation results of step 200, training set 1 and training set 2 may be obtained. For the training set 1, the method can be used to divide the commonly used service sub-scenarios, and modify the width of the interval between the minimum closed-loop parameter set and the theoretical maximum closed-loop configuration parameter set in the actual service scenario. In step 100, it can be seen that: for each service scene j, the initialization interval for taking the parameters is

However, the interval may have a certain deviation from the actual interval, so that a correction is required to ensure the accuracy of the interval under the corresponding role. Therefore what needs to be corrected in practice is

Let us assume that

And the collected confirmation is a parameter configuration set belonging to the scene j under the role i, and the initialization interval can be converged through the set, so that the optimal interval is obtained.

After the optimal interval is determined, the relationship between the frequently used sub-scenes of the service scene and the user role needs to be further matched. It is worth noting that the obtained parameters actually contain role and mechanism information i, so that classification can be realized by using a simple algorithm, mapping from the business sub-scene to the role is realized, final closed-loop mapping from the role to the business sub-scene and then to a specific parameter set is realized, and data connection and circulation of the whole process are realized.

Step 400: a closed-loop parameter setting module based on visualization is designed, based on a minimum closed-loop parameter set, the closed-loop parameter setting module is dynamically expanded upwards to a theoretical maximum closed-loop configuration parameter set, visualization of parameter management configuration is achieved, and the closed-loop parameter setting module has the functions of automatically checking whether a closed loop exists or not and whether parameter values are in compliance or not.

It can be understood that whether the loop is closed and the parameter setting is in compliance is automatically verified after all inputs are finished. The part is not only the embodiment of the calculation results from step 100 to step 300, but also an important transition from theory to application. From the architecture perspective, the module is divided into a database module, a background module, and a front-end presentation module.

The database module mainly stores required relevant basic data, calculation results of an optimization part and all required relevant parameters, and is developed through an ORACLE database at present. The background module has three main functions: (1) the application background is developed based on JAVA, so that open source IBatis is adopted as an ORM framework for interacting with the database; (2) a logic calculation module: the part is mainly responsible for the specific logic execution of related calculation and optimization; (3) a front-end interaction module: the module is generally used as a module for responding an API request initiated by a front end and returning corresponding data, and is directly connected with the logic calculation module and the database interaction module. The front-end display module has three main functions: (1) a preview module: showing the minimum link which can be used for configuring the warehouse well by the user at present, wherein the user can select the link which meets the requirement most and does not need to start configuration from 0; (2) a configuration module: the main function is to display the flow links and link parameters in a visual mode, so that the user can understand and configure the flow links and the link parameters conveniently; (3) a checking module: the main function is to verify whether the whole process is closed loop or not and whether the parameter setting is correct or not, thereby reducing errors caused by process configuration. Front-end technology was developed using the open source framework vue.

Referring to fig. 6, step 100 of the parameter configuration method based on the service scenario specifically includes:

step 10: and confirming scene information of all roles through a business and product manager.

First, before starting to define the minimum closed-loop parameter set, the parameter configuration scenario in all roles needs to be defined in detail first. Assume the set of all business scenarios is S_i＝{

s

_ij1,2,3.. N }, where i, j have the same meaning as above, and N denotes the number of common characters. For each character S_iThere is a set of service scenarios that may exist repeatedly in different roles, but exist repeatedly in the set, so that different roles do not share the piece of data. The service scene data is generally determined through communication between the service manager and the product manager, and the detailed principle should be adhered to in the process, so that the service scene of any role is not omitted, and the reliability of the quality of the basic data is ensured. The information should be physically embodied in the requirements analysis, detailed design of the business system, or in the product report.

Step 11: a minimum set of closed-loop parameters for each scene is determined.

When the set of service scenarios is determined in step 10, a minimum set of closed-loop parameters for these service scenarios needs to be determined. As shown in fig. 7, the basic steps involved in the minimum closed loop are the business trip initiated application, line manager approval, and department responsible approval, taking the basic business trip application as an example. However, the minimum closed loop only means that the approval is completed once from the application of a business trip to the approval of a department leader, and does not relate to more processes and the problem of approval and rejection of circulation. At this point, it is obvious that this is the simplest step to complete the flow. And therefore is a lower limit set on the traffic scenario parameters.

Step 12: a theoretical maximum closed-loop configuration parameter set for each scene is determined.

The minimum closed-loop parameter set can only meet the most basic closed-loop parameter setting of the service scene. In practical applications, the general approval process is much more complex than the minimum closed loop. As shown in fig. 7, the rational expansion part, namely the rational closed loop: the business trip applicant initiates an application, the application is transferred to a line manager for approval, when the line approver finishes approval and transfers to a department leader for approval, the application is rejected due to a certain reason and returned to the business trip person, and at the moment, the business trip applicant needs to correct part of information to reinitiate the application according to requirements. In this case, the situation is not only solved by the minimum closed loop, but also needs to be expanded upwards based on the minimum closed loop.

However, a general service system does not allow a certain flow to be circulated indefinitely, i.e., can never end. In this case, the termination condition needs to be set manually. If one business trip application cannot be approved and returned for more than three times, the process is automatically closed no matter how the business trip application is circulated, and the applicant is required to initiate a new process again as long as the business trip application is checked and returned for more than three times by different levels; as shown in fig. 7, for the theoretical maximum closed loop: the application can be returned by the department leader, the straight line manager and the department leader in sequence, and the application can not pass through until the application is submitted for the fourth time.

Taking the data in fig. 7 as an example, the minimum closed-loop parameter set is

The relevant parameters of the step 1 to the step 3 are included; theoretical maximum closed loop configuration parameter set

Including the relevant parameters of step 1 to step 9; whereas a reasonable closed-loop, i.e. a reasonable closed-loop parameter set, includes the relevant parameters from step 1 to step 5. Therefore, it is the additional newly added parameter set that needs to be shrunk in step 300

Step 4 to step 9.

As shown in fig. 8, step 200 of the parameter configuration method based on the service scenario specifically includes:

step 20: and establishing a matrix of the sub-scenes of the service scene and the configuration parameter vector. The method comprises the following three steps: data extraction, mapping matrix of parameters and scenes and establishment of associated vectors.

For data extraction, firstly, parameter sets corresponding to users and corresponding scenes are taken out from a database

Each of which is

Contains a cursor that indicates its position in the global parameter column. As mentioned in step 200, let the total parameter list of the service scenario be Ψ. And the parameter set of each sub-scene is combined as phi^jThen the following relationship exists between the two:

Ψ＝φ¹∪φ²∪φ³∪...∪φ^J

if, for a certain historical configured parameter set

There are:

it indicates that the dimension of the parameter set at this time exceeds the parameter set of any one sub-scene. In this case, there are two solutions: (1) if all existing sub-scenes are exhausted in the step 10 and no omission condition exists, the input is dirty data and a training set needs to be cleaned; (2) considering the omission that may exist by artificial exhaustion, the existence of the piece of data is actually a potential compliance sub-scenario. Then the data is stored in the alternative set Ψ_poAs a candidate set for subsequent further screening. If parameter set

And if the condition of the formula 1-2 is satisfied, the input requirement is satisfied from the aspect of dimensionality, and the input requirement is extracted as the input parameter of the next processing.

A Parameter Mapping Matrix on Scene (PMMS) a, which is a Matrix of Z × J, wherein a row dimension represents a Parameter and a column dimension represents a compliance sub-Scene in a service Scene. The matrix is used to characterize the details of the parameters used in the different sub-scenarios. Since the matrix is a 0-1 matrix, 0 represents that the parameter is not used in the sub-scene, 1 represents that the parameter is used in the sub-scene, a standard PMMS matrix is as follows:

the association Vector (RV) characterizes a certain configuration parameter

Associated with each sub-scene, assuming a configuration scenario

Is [ 1100 ]]^TThis indicates that the configuration uses the 1 st and 2 nd parameters in the total parameter sequence, but does not use the 3 rd and 4 th parameters. The calculation method of the association vector is as follows:

χ_RV＝A×φ_in

thus, according to the rule of operation of the vector, the result is a column vector of J × 1, with the symbol γ, the value γ of each dimension of the vector_jIndicates how similar the parameter set is to sub-scene j. Further, normalizing the vector specifically:

further obtaining a normalized similarity vector gamma^stdAs a measure of the similarity of the parameter set to the respective scene.

Step 21: and measuring the matching degree of the historical data and the sub-scenes through the similarity, and obtaining the optimal similarity threshold through training of the training set.

The standard similarity vector γ acquired in step 20^stdThe similarity between the closed-loop parameter set and each sub-scene can be known. However, only one sub-scene may be set in each closed-loop setting, so that the matching degree of the sub-scene with the sub-scene can be determined according to the value of the similarity. TPR and FPR are introduced, and are respectively the percentage of TP number and FP number in the total number. It is apparent that a larger TPR indicates a better result. For a certain threshold, when the TPR is close to the required accuracy, it indicates that all the results inferred from similarity are close to perfect agreement with the actual results at the threshold.

Step 22: when the optimal similarity threshold value is obtained, establishing a mapping relation (m) between actual parameter closed-loop setting and a service sub-scene₁。

Furthermore, because the role and mechanism information of the parameter administrator is stored in each setting, the relation mapping M of the business sub-scene, the user role and the mechanism where the business sub-scene is located is also established₂. And the basic parameter process mapping is completed, and a data basis is provided for visualization.

Referring to fig. 9, step 300 of the parameter configuration method based on the service scenario specifically includes:

step 30: and dividing the service sub-scenes based on the actual service scenes.

Specifically, the mapping relation m is acquired in step 200₁The business sub-scenes in the actual scene can be further divided. By service sub-scene is meant several sets of parameters that are most commonly used in real scenes. Suppose a scene S that a role is involved in_ijThen for that scene j, there is a set of sub-scenes

It is the members of the set that need to be partitioned.

In the present application example, the actual input parameter vector is applied

As an index to measure the similarity before a parameter set. Therefore, forA set of parameter sets with o parameter sets (one parameter set for each point of the undirected graph) can be constructed as a directed graph G_j(V, E, w). Where V represents the set of parameter sets for the service scenario j (representing the set of points in the undirected graph), E represents the arcs between the points in the set of parameter sets, with

w represents the weight of the arc, with w ═ w_e|e∈E}。

For graph G_jDefining its weighted adjacency matrix A_jThe dimension is o × o. Matrix A_jThe element in (A) is_wvWhere w, V ∈ V, σ denotes the Gaussian kernel function parameter:

definition matrix D_jThe diagonal elements are:

the remaining elements are all 0. L is_jIs a drawing G_jOf Laplace matrix of L_j＝D_j-A_j。

The goal of spectral clustering is to cut a graph into k sub-graphs and to ensure that the sum of the interval weights connecting the subgraphs is minimal and the sum of the weights within the subgraphs is larger.

Suppose the graph is cut into two subgraphs, for subgraphs I and I

Assume that the connection path set between the two is E_cThe method comprises the following steps:

then the path set weight is W_cThe numerical values are:

the parameter configuration sub-scene division objective function based on spectral clustering is as follows:

here, the application example adopts a multi-path canonical cut set criterion to construct the identification model, which has higher execution efficiency, and the identification model is as follows:

after the model is established, two parameters to be optimized exist, one is a Gaussian kernel function sigma, and the other is the number K of the separation clusters.

Therefore, the constraint is:

wherein m is the iteration number, Te is the temperature threshold, and alpha is the temperature decay rate. By solving the model, the optimal sub-scene division of different service scenes under different roles can be realized.

Step 31: and correcting the intervals between the actual service scene and the minimum closed-loop parameter set and the theoretical maximum closed-loop configuration parameter set.

Specifically, the sub-scene of each service scene acquired in step 30 can be further used to modify

By length of the interval, i.e. correction

Such that the parameter set maintains the most appropriate dimensionAnd (4) degree. In general, for a specific sub-scene under a certain role, the configured parameter set must converge with time deduction, i.e. the minimum parameter set is presented

A single cluster that is a cluster center. They can be clustered using a simple k-means algorithm. In the early stage of a small amount of data, a plurality of cluster clusters may exist. Along with the continuous increase of the data quantity, the clustering center of the data continuously moves towards the minimum closed loop until a clustering center is formed, and the actual parameter configuration interval is

Since the validity of the parameter set of each parameter setting scenario has been checked in step 200, the actual parameter configuration interval obtained by the final convergence must exist:

by converging the parameter configuration interval, the number of the configuration intervals can be effectively reduced

The interval of (2) further reduces the calculation complexity and improves the calculation efficiency of practical application. Up to this step, mapping from the scene to the parameter set configuration interval has been achieved.

Step 32: and acquiring the mapping relation between the actual service scene and the user role.

Specifically, the mapping relation m is acquired in step 200₂It can be used to map the relationship between the scene and the user.

When the parameters of the service scene are set each time, the user role and mechanism information is provided. Therefore, the relationship between the user role, the mechanism and the actual parameter configuration result can be obtained only by traversing all roles. At the beginning of use, sub-scenarios may not be considered thoroughly. But the situation can be analyzed during data cleaning, and the defect of sub-scenes caused by human negligence is further compensated. To this end, step 300 completes the circulation from the user to the role and from the role to the parameter set, so as to realize the visual display.

The following description is based on the service royalty application. In step 100, the present application example sets forth the necessary and optional processes for the overall process of applying and approving the service premiums. Obviously, for the service scenario, the necessary links form a minimum closed loop, and the necessary links and all optional links form a theoretical maximum closed loop. And then, the mapping between the service scene and the minimum closed loop and the theoretical maximum closed loop is completed.

Further, based on the data of the service scene actually configured by the parameter configuration administrator in actual production as a training set, the similarity between the parameter configured each time and each sub-scene in the service scene is calculated, and the value range [0,1] is taken. On this basis, a similarity threshold is trained until the accuracy reaches TPR close to 1. At this time, the closed loop setting set meeting the condition establishes a relationship with the sub-scene of the service scene. Meanwhile, the association of the parameter set and the role is realized by associating the mechanism where the configuration administrator is located.

On this basis, for a closed-loop parameter set meeting the conditions to divide a molecular scene, the flow after division is assumed to have the following two flows:

(1) department responsible person approves- > returning department approves- > financial auditor- > accounting department responsible person;

(2) the department responsible person examines and approves- > return to the mouth department examines and approves- > financial auditor- > finance department responsible person- > return to the mouth of higher-level line- > higher-level line auditor- > higher-level line department responsible person- > higher-level line organization responsible person.

At this time, for the service scenario of applying for the premiums, the interval of the closed loop link is the union of the two links. That is, the actual parameter closed-loop interval of the service hospitality fee application scenario is the union of two sub-scenarios. Meanwhile, each parameter setting can be hooked with the mechanism and the role of the configuration manager, so that the two are also linked. At this point the calculation is complete.

After the data calculation is completed, the step of configuring the visualization parameters is further illustrated, and as shown in fig. 10 in detail, the following is explained:

step 41: selecting an approval category; recommending the sub-scene information most probably configured to a parameter manager according to the mapping relation between the prior role and the sub-scene

Step 42: displaying a closed loop process; the system sets a sub-scene visualization display closed-loop process according to the currently selected parameters of the user.

Step 43: configuring a process environment; the closed-loop flow comprises some skipped links, and a user can select whether to skip the flow links during execution according to actual requirements in the line or increasing judgment conditions.

Step 44: configuring link parameters; the mouse is placed on a link to display a parameter branch needing to be configured, the parameter is clicked to jump to a corresponding parameter table page, and the parameter is configured and then returned to the flow page.

Step 45: checking the process; after all links and parameters are configured, clicking a check button, and confirming whether the flow is closed or not and whether the parameters are set completely or not by the system under each condition, thereby ensuring the successful execution of the flow.

Specifically, as shown in fig. 11, taking the admission service approval scenario introduced in step 100 as an example, the parameter configuration interface specifically includes the following steps:

firstly, a user (a parameter configuration manager) needs to configure the admission charge application approval process of the department, firstly clicks an approval process configuration menu, and selects an expense category as the admission charge application. The system will present a recommendation for the current role to configure the hospitality application approval process according to steps 100-300.

Further, the user selects one of the recommendation schemes, assuming that the process is department responsible person examination and approval- > returning department examination and approval- > financial auditor- > finance department responsible person, after the user clicks and opens the configuration interface, the steps are displayed in a flow chart mode, and meanwhile, a plus sign is arranged at the expandable node and used for adding unselected configurable links.

After the link is configured, the user only needs to move the mouse to the position above the module of the department responsible person approval link in the process, a yellow circle of the person approval character pops up on the right side of the module, the user jumps to a parameter table of the person approval character after clicking, clicks and adds and fills information such as a person number, a mechanism, effective time and the like, and then clicks and submits the information to wait for double rechecking. When the approval link of the gate returning department is configured, approval conditions can be filled in the module, for example, the amount of money applied by a user is more than 10000 Yuan, after filling, when the amount of the branch condition is more than 10000 Yuan, the approval link of the gate returning department is needed, and similarly, the condition of the link of a person in charge of the gate returning department is modified to 50000 Yuan. And clicking a verification button after the other link parameters are matched once, popping up a prompt financial accounting department responsible person link personnel to examine and approve the role parameters and indicating that the verification fails by popping up a red round box in the module. And clicking and submitting after the resetting is completed and clicking and checking, and taking effect after rechecking.

After the configuration link and the parameters are completed, the ordinary user can initiate the workflow according to the set flow and realize the whole flow of the examination and approval when applying for the hospitalizing.

Fig. 13 is a schematic diagram illustrating comparison of configuration time between an existing parameter setting mode and a service approval parameter configuration method according to the present application in an example, where the service approval parameter configuration method according to the present application uses a visual closed-loop parameter setting mode, and as can be seen from fig. 13, compared with the existing parameter setting mode, the service approval parameter configuration method according to the present application can significantly reduce configuration time and improve parameter configuration efficiency. Fig. 14 is a schematic diagram illustrating a comparison between a single approval pass rate of a service approval parameter configuration method according to the present application and a conventional parameter setting mode, and as can be seen from fig. 14, compared with the conventional parameter setting mode, the service approval parameter configuration method according to the present application can significantly improve the single approval pass rate.

In terms of software, in order to improve the accuracy and efficiency of parameter configuration and further the accuracy and efficiency of parameter configuration, the present application provides an embodiment of a service approval parameter configuration apparatus for implementing all or part of the contents in the service approval parameter configuration method, referring to fig. 12, where the service approval parameter configuration apparatus specifically includes the following contents:

a first obtaining module 121, configured to obtain multiple sets of approval parameter sets corresponding to a target service scene, where the approval parameter sets include: a plurality of approval parameters and the incidence relation among the approval parameters;

a determining module 122, configured to apply a preset spectral clustering model and each approval parameter group to determine a plurality of target approval sub-scenes corresponding to the target service scene, where each target approval sub-scene includes: and at least one group of examination and approval parameter groups are used for determining a target examination and approval sub-scene corresponding to a parameter configuration request when the parameter configuration request of a target auditor is received.

The preset spectral clustering model is a machine learning model which is obtained by pre-training and based on a spectral clustering algorithm, and is used for classifying the approval parameter group.

In an embodiment of the present application, the device for configuring service approval parameters further includes:

a second obtaining module, configured to obtain a historical user information group corresponding to each group of the approval parameter groups, where the historical user information group includes: role information and organization information of historical users;

correspondingly, the determining module is configured to perform the following:

receiving a parameter configuration request of a target auditor, wherein the parameter configuration request comprises: role information and organization information of a target auditor;

determining a historical user information group matched with the role information and the organization information of the target auditor;

and determining a target approval sub-scene corresponding to the target auditor based on the approval parameter group corresponding to the matched historical user information group, and outputting and displaying each approval parameter group corresponding to the target approval sub-scene.

In an embodiment of the present application, the first obtaining module is configured to perform the following:

acquiring a plurality of sets of historical parameter sets corresponding to a target service scene and historical parameter vector sets corresponding to the historical parameter sets respectively;

respectively applying a preset scene parameter mapping matrix and each historical parameter vector group to carry out similarity calculation, and taking the historical parameter vector group with the similarity calculation result larger than the optimal similarity threshold value as a target parameter vector group;

and taking the historical parameter group corresponding to the target parameter vector group as the approval parameter group.

an iteration module for performing the iteration step: obtaining an updated initial similarity threshold by applying a preset similarity optimization model, an initial similarity threshold and each historical parameter group, wherein the similarity optimization model is a machine learning model which is obtained by pre-training and is based on an L-BFGS algorithm;

and the optimal similarity threshold determining module is used for acquiring a historical parameter vector group of which the similarity calculation result is greater than the updated initial similarity threshold as an intermediate parameter vector group, judging whether the ratio of the number of the intermediate parameter vector group to the total number of the historical parameter vector group is less than or equal to a proportional threshold, if so, applying the updated initial similarity threshold to execute the iteration step again, and if not, stopping executing the iteration step and taking the current initial similarity threshold as the optimal similarity threshold.

In an embodiment of the present application, the preset spectral clustering model includes: a gaussian kernel function and a number of separation clusters; correspondingly, the service approval parameter configuration device further comprises:

and the optimization module is used for optimizing the Gaussian kernel function and the number of the separation clusters by applying a simulated annealing algorithm.

The embodiment of the service approval parameter configuration apparatus provided in this specification may be specifically configured to execute the processing flow of the embodiment of the service approval parameter configuration method, and the function of the embodiment is not described herein again, and reference may be made to the detailed description of the embodiment of the service approval parameter configuration method.

According to the description, the method and the device for configuring the service approval parameters can improve the accuracy and efficiency of parameter configuration, and further can improve the accuracy and efficiency of service approval. The method comprises the steps of defining a compliance closed-loop sub-scenario of a business scenario, so that parameter configuration can be carried out under the compliance sub-scenario, and the possibility of missing configuration is reduced. Through the incidence relation between the business sub-scenes and the roles, the method can determine which compliant sub-scenes are commonly used by different users in corresponding roles and organizations in China according to specific parameter configuration scenes. The communication from roles to business scenes, from the business scenes to sub-scenes and then to specific parameters can be realized. By visualizing the parameter configuration, the problems of complexity and variability of the configuration parameter setting process can be solved, the consumption of manpower and time cost in the core link of the system is reduced, and the usability and maintainability of the parameter configuration process are improved.

In terms of hardware, in order to improve accuracy and efficiency of parameter configuration, and to be applicable to a complex parameter configuration scenario, and further improve accuracy and efficiency of service approval, the present application provides an embodiment of an electronic device for implementing all or part of contents in the service approval parameter configuration method, where the electronic device specifically includes the following contents:

a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission between the service approval parameter configuration device and the related equipment such as the user terminal; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the electronic device may be implemented with reference to the embodiment for implementing the method for configuring the service approval parameter and the embodiment for implementing the device for configuring the service approval parameter, which are incorporated herein, and repeated details are not repeated herein.

Fig. 15 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 15, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 15 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In one or more embodiments of the present application, the business approval parameter configuration function may be integrated into the central processor 9100. The central processor 9100 may be configured to control as follows:

As can be seen from the above description, the electronic device provided in the embodiment of the present application can improve accuracy and efficiency of parameter configuration, is suitable for a complex parameter configuration scenario, and can further improve accuracy and efficiency of service approval.

In another embodiment, the service approval parameter configuration apparatus may be configured separately from the central processor 9100, for example, the service approval parameter configuration apparatus may be configured as a chip connected to the central processor 9100, and the service approval parameter configuration function is realized through the control of the central processor.

As shown in fig. 15, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 15; further, the electronic device 9600 may further include components not shown in fig. 15, which can be referred to in the related art.

As shown in fig. 15, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.

The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.

The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.

The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.

An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the service approval parameter configuration method in the foregoing embodiment, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements all the steps of the service approval parameter configuration method in the foregoing embodiment, for example, when the processor executes the computer program, the processor implements the following steps:

As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application can improve accuracy and efficiency of parameter configuration, is suitable for a complex parameter configuration scenario, and can further improve accuracy and efficiency of service approval.

In the present application, each embodiment of the method is described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. Reference is made to the description of the method embodiments.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the present application are explained by applying specific embodiments in the present application, and the description of the above embodiments is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A method for configuring service approval parameters is characterized by comprising the following steps:

2. The method for configuring service approval parameters according to claim 1, wherein before the step of determining a plurality of target approval sub-scenes corresponding to the target service scene by applying a preset spectral clustering model and each approval parameter group, further comprising:

obtaining historical user information groups corresponding to the examination and approval parameter groups respectively, wherein the historical user information groups comprise: role information and organization information of historical users;

correspondingly, when a parameter configuration request of a target auditor is received, determining a target approval sub-scene corresponding to the parameter configuration request includes:

3. The method according to claim 1, wherein the obtaining of the multiple sets of approval parameter sets corresponding to the target service scenario includes:

4. The method according to claim 3, wherein before the applying the preset scene parameter mapping matrix and the similarity calculation of each historical parameter vector group, the method further comprises:

performing an iteration step: obtaining an updated initial similarity threshold by applying a preset similarity optimization model, an initial similarity threshold and each historical parameter group, wherein the similarity optimization model is a machine learning model which is obtained by pre-training and is based on an L-BFGS algorithm;

and acquiring a historical parameter vector group of which the similarity calculation result is greater than the updated initial similarity threshold as an intermediate parameter vector group, judging whether the ratio of the number of the intermediate parameter vector group to the total number of the historical parameter vector group is less than or equal to a proportional threshold, if so, applying the updated initial similarity threshold to execute the iteration step again, otherwise, stopping executing the iteration step and taking the current initial similarity threshold as the optimal similarity threshold.

5. The method of claim 1, wherein the configuration of the business approval parameters,

the preset spectral clustering model is a machine learning model which is obtained by pre-training and is based on a spectral clustering algorithm, and is used for classifying the approval parameter group.

6. The business approval parameter configuration method of claim 1, wherein the preset spectral clustering model comprises: a gaussian kernel function and a number of separation clusters;

correspondingly, before the determining of the plurality of target approval sub-scenes corresponding to the target service scene, the method further includes:

and optimizing the Gaussian kernel function and the number of the separation clusters by using a simulated annealing algorithm.

7. A business approval parameter configuration device is characterized by comprising:

8. The apparatus for configuring approval parameters for business as claimed in claim 7, further comprising:

correspondingly, the determining module is configured to perform the following:

9. The apparatus for configuring approval parameters for business as claimed in claim 7, wherein said first obtaining module is configured to perform the following steps:

10. The apparatus for configuring approval parameters for business as claimed in claim 9, further comprising:

11. The device of claim 7, wherein the predetermined spectral clustering model is a pre-trained spectral clustering algorithm-based machine learning model, and is configured to classify the sets of approval parameters.

12. The business approval parameter configuration device of claim 7, wherein the preset spectral clustering model comprises: a gaussian kernel function and a number of separation clusters;

correspondingly, the service approval parameter configuration device further comprises:

13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for configuring a service approval parameter of any one of claims 1 to 6 when executing the program.

14. A computer-readable storage medium having stored thereon computer instructions, wherein the instructions, when executed, implement the business approval parameter configuration method of any one of claims 1 to 6.