CN111815169B

CN111815169B - Service approval parameter configuration method and device

Info

Publication number: CN111815169B
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: 2023-08-11
Anticipated expiration: 2040-07-09
Also published as: CN111815169A

Abstract

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

Description

Service 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 flows need to be customized and developed, wherein parameters are configured as core links in the process of customized and developed approval flows, and the trend of the flows is dynamically controlled. Therefore, the integrity 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 business process is complex, and the configuration is difficult: at present, many business approvals are required, not only are the authorized persons of the mechanism at the level required to carry out the approval, but also the authorized persons of the mechanism at the upper level or even higher level are required to carry out the approval, so that the configuration of relevant parameters of the approval process is based on the dynamics, and is difficult to be compatible by a set of fixed configuration methods within a certain interval range. Environmental failures due to parameter mismatching are therefore liable to occur.

(2) The mechanism is complex, and the parameter categories are many: large-scale companies often have the right to meet the own characteristics of specific service settings at headquarters, provincial first-level branches and municipal first-level branches, and do not violate the parameter tables of the upper-level institutions. Some business scenes even allow the sub-mechanism to set characteristic parameters, so that the complex mechanism and parameter types often generate problems of low efficiency, missed configuration and misplacement during configuration, and the actual business functions are influenced, thereby influencing the production efficiency.

(3) The parameter configuration process is complicated, time-consuming and labor-consuming: when parameters are configured, the parameters are configured by adopting the processes of parameter searching, parameter inputting and parameter checking, so that the efficiency is low, the parameters can be possibly omitted, and the production efficiency is influenced.

Disclosure of Invention

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

In order to solve the technical problems, the application provides the following technical scheme:

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

obtaining multiple groups of approval parameter sets corresponding to a target business scene, wherein the approval parameter sets comprise: a plurality of approval parameters and association relations among the approval parameters;

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

Further, before the applying the preset spectral clustering model and each approval parameter set to determine the multiple target approval sub-scenes corresponding to the target service scene, the method further includes: acquiring a historical user information group corresponding to each examination and approval parameter group, wherein the historical user information group comprises: historical user role information and organization information; correspondingly, when the parameter configuration request of the target auditor is received, determining the target approval sub-scene corresponding to the parameter configuration request comprises the following steps: receiving a parameter configuration request of a target auditor, wherein the parameter configuration request comprises the following steps: role information and mechanism information of target auditors; determining a historical user information group matched with role information and organization information of the target auditor; and determining a target approval sub-scene corresponding to the target auditor based on the approval parameter set corresponding to the matched historical user information set, and outputting and displaying each approval parameter set corresponding to the target approval sub-scene.

Further, the obtaining multiple sets of approval parameter sets corresponding to the target service scene includes: acquiring a plurality of groups of history parameter groups corresponding to a target service scene, wherein each group of history parameter groups corresponds to a history parameter vector group; respectively applying a preset scene parameter mapping matrix to calculate the similarity with each historical parameter vector group, 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 set corresponding to the target parameter vector set as the approval parameter set.

Further, before similarity calculation is performed between the preset scene parameter mapping matrix and each of the historical parameter vector sets, the method further includes: the iterative steps are performed: applying a preset similarity optimization model, an initial similarity threshold and each history parameter set to obtain an updated initial similarity threshold, wherein the similarity optimization model is a machine learning model based on an L-BFGS algorithm, which is obtained through training in advance; and acquiring a historical parameter vector group with the similarity calculation result being larger than an updated initial similarity threshold value 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 smaller than or equal to a proportion threshold value, if so, executing an iteration step again by using the updated initial similarity threshold value, and if not, stopping executing the iteration step and taking the current initial similarity threshold value as the optimal similarity threshold value.

Further, the preset spectral clustering model is a machine learning model based on a spectral clustering algorithm, which is obtained through training in advance, and is used for classifying the approval parameter sets.

Further, the preset spectral clustering model includes: gaussian kernel function and partition cluster number; correspondingly, before the determining of the multiple target approval sub-scenes corresponding to the target business scene, the method further comprises: 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 service approval parameter configuration device, including:

the first acquisition module is used for acquiring a plurality of groups of approval parameter groups corresponding to the target business scene, wherein the approval parameter groups comprise: a plurality of approval parameters and association relations among the approval parameters;

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

Further, the service approval parameter configuration device further includes: the second obtaining module is configured to obtain historical user information sets corresponding to each of the approval parameter sets, where the historical user information sets include: historical user role information and organization information; correspondingly, the determining module is used for executing the following contents: receiving a parameter configuration request of a target auditor, wherein the parameter configuration request comprises the following steps: role information and mechanism information of target auditors; determining a historical user information group matched with role information and organization information of the target auditor; and determining a target approval sub-scene corresponding to the target auditor based on the approval parameter set corresponding to the matched historical user information set, and outputting and displaying each approval parameter set corresponding to the target approval sub-scene.

Further, the first acquisition module is configured to perform the following: acquiring a plurality of groups of history parameter groups corresponding to a target service scene, wherein each group of history parameter groups corresponds to a history parameter vector group; respectively applying a preset scene parameter mapping matrix to calculate the similarity with each historical parameter vector group, 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 set corresponding to the target parameter vector set as the approval parameter set.

Further, the service approval parameter configuration device further includes: the iteration module is used for executing the iteration steps: applying a preset similarity optimization model, an initial similarity threshold and each history parameter set to obtain an updated initial similarity threshold, wherein the similarity optimization model is a machine learning model based on an L-BFGS algorithm, which is obtained through training in advance; and the optimal similarity threshold determining module is used for acquiring a historical parameter vector group with the similarity calculation result larger 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 smaller than or equal to a proportion threshold, if so, executing the iteration step again by using the updated initial similarity threshold, 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: gaussian kernel function and partition cluster number; correspondingly, the service approval parameter configuration device further comprises: and the optimizing module is used for applying a simulated annealing algorithm to optimize the Gaussian kernel function and the number of the separation clusters.

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 service approval parameters when executing the program.

In a fourth aspect, the present application provides a computer readable storage medium having stored thereon computer instructions that, when executed, implement the method of configuring business approval parameters.

As can be seen from the above technical schemes, the present application provides a method and apparatus for configuring service approval parameters. Wherein the method comprises the following steps: obtaining multiple groups of approval parameter sets corresponding to a target business scene, wherein the approval parameter sets comprise: a plurality of approval parameters and association relations among the approval parameters; and determining a plurality of target approval sub-scenes corresponding to the target business scene by applying a preset spectral clustering model and each approval parameter set, wherein each target approval sub-scene comprises: at least one group of examination and approval parameter groups is 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 the efficiency of parameter configuration can be improved, the accuracy of business examination and approval can be further improved, the intelligentization and the visualization degree of the parameter configuration can be improved, and the possibility of parameter mismatching can be reduced; based on the association relation between the service scene and the roles, personalized configuration of parameters can be realized; the method can solve the problems of complexity and variability in the parameter configuration process, reduce the labor and time cost, and improve the usability and maintainability of parameter configuration.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

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

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

fig. 3 is a schematic flow chart of steps S301 to S303 in the service approval parameter configuration method according to the embodiment of the present application;

fig. 4 is a schematic flow chart of step S401 and step S402 in the service approval parameter configuration method according to the embodiment of the present application;

FIG. 5 is a flow chart of a method for configuring parameters based on a business scenario in an application example of the present application;

fig. 6 is a schematic flow chart of steps 10 to 12 in the parameter configuration method based on the service scenario in the 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 flow chart of steps 20 to 22 in the parameter configuration method based on the service scenario in the application example of the present application;

fig. 9 is a schematic flow chart of steps 30 to 32 in a service scenario-based parameter configuration method in an application example of the present application;

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

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

FIG. 12 is a schematic diagram of a configuration device for service approval parameters according to an embodiment of the present application;

FIG. 13 is a schematic diagram illustrating a comparison of configuration time of an exemplary conventional parameter configuration mode and the service approval parameter configuration method of the present application;

FIG. 14 is a schematic diagram illustrating a comparison of single approval passing rates using the conventional parameter setting mode and the business approval parameter configuration method of the present application;

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

Detailed Description

In order to make the technical solutions in the present specification better understood by those skilled in the art, 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 some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

Based on this, in order to improve accuracy and efficiency of parameter configuration, the embodiment of the application is suitable for complex parameter configuration scenarios, and further improves accuracy and efficiency of business approval, and the embodiment of the application provides a business approval parameter configuration device, 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, intelligent wearing equipment can include intelligent glasses, intelligent wrist-watch and intelligent bracelet etc..

In practical applications, the portion for configuring the service approval parameters may be performed on the server side as described above, or all operations may be performed in the client device. Specifically, the selection may be made according to the processing capability of the client device, and restrictions of the use scenario of the user. The application is not limited in this regard. If all operations are performed in the client device, the client device may further include a processor.

The client device may have a communication module (i.e. a communication unit) and may be connected to a remote server in a communication manner, so as to implement data transmission with the server. The server may include a server on the side of the task scheduling center, and in other implementations may include a server of an intermediate platform, such as a server of a third party server platform having a communication link with the task scheduling center server. The server may include a single computer device, a server cluster formed by a plurality of servers, or a server structure of a distributed device.

Any suitable network protocol may be used for communication between the server and the client device, including those not yet developed on the filing date of the present application. The network protocols may include, for example, TCP/IP protocol, UDP/IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol ), REST protocol (Representational State Transfer, representational state transfer protocol), etc. used above the above-described protocol.

The following examples are presented in detail.

In order to improve accuracy and efficiency of parameter configuration, and apply to complex parameter configuration scenarios, and further improve accuracy and efficiency of service approval, the embodiment provides a service approval parameter configuration method in which an execution subject is a service approval parameter configuration device, as shown in fig. 1, the method specifically includes the following contents:

step S101: obtaining multiple groups of approval parameter sets corresponding to a target business scene, wherein the approval parameter sets comprise: and the association relation among the plurality of approval parameters and the approval parameters.

The target business scene can be a production scene which is used in actual production, has a complete flow and has various sub-scenes, such as business trip approval, business hospitality expense approval and the like.

The approval parameters comprise audit role information and audit authority information corresponding to each audit role information. And the association relation between the approval parameters represents the association relation between the auditing role information. The approval character information may be: department responsible person, financial approver and financial department responsible person information; the association relationship between the approval character information may be that a department responsible person, a financial approval person and a financial department responsible person are sequentially associated.

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

The preset spectral clustering model is a machine learning model based on a spectral clustering algorithm, which is obtained through training in advance, and is used for classifying the approval parameter sets. The spectral clustering model is suitable for processing sparse data and 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 multiple target approval sub-scenes, so that the target approval sub-scenes corresponding to each approval person can be configured, and each target sub-scene includes at least one group of approval parameter groups; in conclusion, the accuracy and the efficiency of parameter configuration can be improved, and the method is suitable for complex parameter configuration scenes, so that the accuracy and the efficiency of business approval are improved.

In one application example of the present application, step S102 includes: constructing a corresponding directed graph based on each approval parameter group; generating a weighted adjacent matrix and a degree matrix corresponding to the directed graph; obtaining a Laplace matrix based on the weighted adjacent matrix and the degree matrix; solving a feature vector corresponding to the minimum feature value of the preset number of the Laplace matrix, and constructing a feature vector space; clustering the feature vectors in the feature vector space by applying 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 parameters. The preset number can be set according to actual needs.

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

step S201: acquiring a historical user information group corresponding to each examination and approval parameter group, wherein the historical user information group comprises: role information and organization information of the history user.

Correspondingly, step S102 includes:

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

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

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 set corresponding to the matched historical user information set, and outputting and displaying each approval parameter set corresponding to the target approval sub-scene.

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

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 approval sub-scene and the role information, the auditor can intuitively see the corresponding role and the parameter configuration scene under the mechanism, so that the role-to-service scene, the sub-scene, and the specific parameter can be penetrated, 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 comprises:

s211: obtaining a plurality of historical user corresponding recruitment approval parameter sets, wherein each approval parameter set comprises: and the plurality of business recruitment and approval roles, authority information of each recruitment and approval role and association relation among the approval roles.

The business hospitality expense approval role can comprise: department responsible, financial approver and financial department responsible; the association relationship between the approval roles may be that a department responsible person, a financial approval person and a financial department responsible person are sequentially associated.

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

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 recruitment expense approval parameter set in the target approval sub-scene.

S214: and receiving a request of a selected parameter set of the target auditor, and determining a hospitality expense approval parameter set corresponding to the target auditor according to the request of the selected parameter set so as to configure parameter values of all parameters in the hospitality expense approval parameter set.

S215: if a request for approving the hospitality fee of the target user is received, determining a parameter set of the hospitality fee approval corresponding to the request for approving the hospitality fee and parameter values of all parameters in the parameter set of the hospitality fee approval, so as to complete the approval process of the hospitality fee of the target user.

From the above description, in this example, parameter configuration of different target approval sub-scenes can be implemented, and the target approval sub-scenes corresponding to different auditors are determined.

In order to obtain the reliable set of approval parameters and further determine different target approval sub-scenarios using the reliable set of approval parameters, referring to fig. 3, in one embodiment of the present application, step S101 includes:

step S301: and obtaining a plurality of groups of history parameter groups corresponding to the target business scene and history parameter vector groups corresponding to the history parameter groups respectively.

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

Step S302: and respectively applying a preset scene parameter mapping matrix to calculate the similarity with each historical parameter vector group, 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.

Specifically, the scene parameter mapping matrix is a parameter and scene mapping matrix (Parameter Mapping Matrix on Scene, abbreviated as PMMS), abbreviated as a, the matrix is a matrix of z×j, wherein 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, parameters of each sub-scene are mapped under the length, that is, the row dimension represents the preset maximum closed-loop parameter in each preset service sub-scene, and the row dimension can be set according to actual needs. The matrix is used to characterize the specifics 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, and a standard PMMS matrix is as follows:

Step S303: and taking the historical parameter set corresponding to the target parameter vector set as the approval parameter set.

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 can be implemented, redundant data can be removed, and a reliable approval parameter set can be obtained, so that reliability and efficiency of parameter configuration can be improved.

In order to obtain the 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: the iterative steps are performed: and applying a preset similarity optimization model, an initial similarity threshold and each history parameter set to obtain an updated initial similarity threshold, wherein the similarity optimization model is a machine learning model based on an L-BFGS algorithm, which is obtained through training in advance.

Step S402: and acquiring a historical parameter vector group with the similarity calculation result being larger than an updated initial similarity threshold value 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 smaller than or equal to a proportion threshold value, if so, executing an iteration step again by using the updated initial similarity threshold value, and if not, stopping executing the iteration step and taking the current initial similarity threshold value as the optimal similarity threshold value.

The iteration step is executed again by applying the updated initial similarity threshold, and the updated initial similarity threshold is used as the initial similarity threshold in the iteration step; the obtaining the updated initial similarity threshold by applying a preset similarity optimization model, an initial similarity threshold and each history parameter set may include: obtaining a gradient and a self-conjugate matrix corresponding to the initial similarity threshold according to each history parameter set; and obtaining an updated initial similarity threshold according to the gradient and the self-conjugate matrix.

Specifically, an initial similarity threshold is set as gamma, a target is a preset value theta of a percentage TPR > of the number of parameters predicted to be positive and the number of parameters with positive results to be positive to the total number, an adopted iteration method is an L-BFGS algorithm, and a specific iteration process is as follows:

s41: an initial similarity threshold gamma is input, a sample set m is used as a history parameter set, and an output result is a threshold.

S42: when TPR is less than or equal to θ, step S43 to step S47 are performed, otherwise S48 is performed.

S43: calculating gamma gradient:

s44: calculating a Hessian matrix:

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

S46: computing and updating: Δγ≡H ^-1 g。

S47: application update: gamma++delta gamma.

S48: outputting a result: gamma.

As can be seen from the above description, in this embodiment, by efficiently and accurately obtaining the optimal similarity threshold, filtering of the historical parameter vector set can be achieved by applying the optimal similarity threshold, so as to obtain a reliable target parameter vector set.

In order to obtain an efficient and reliable spectral clustering model, grouping the approval parameter sets by applying the spectral clustering model to obtain a plurality of target approval sub-scenes and the approval parameter sets in each target approval sub-scene; in one embodiment of the present application, the preset spectral clustering model includes: gaussian kernel function and partition cluster number; 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 partition clusters, the reliability and efficiency of the spectral clustering model can be improved, so that the accuracy and efficiency of obtaining the target approval sub-scene 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 provision of a related method. The application example comprises module disassembly and sample display from the aspects of functions and architecture on the application side, but does not comprise specific implementation details such as detailed design, table structure design and the like on the application side.

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

The detailed development steps are set forth below 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, and as shown in fig. 5, the method includes the following contents:

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

The step provides a basis for establishing a parameter and scene mapping matrix and checking the whole-flow basic data in step 200. The service scenarios all refer to an actual and complete service flow scenario: such as hospitality and business approval. For such a business scenario, there is a minimum necessary flow that can meet the scenario flow, and a maximum flow, called minimum closed loop and theoretical maximum closed loop.

For business scenarios, the following is set forth in the context of business hospitality fee approval. Based on different circumstances, the following essential steps and optional steps are shared:

the essential steps are as follows:

(1) Department responsible personnel approves, and personnel approval roles need to be determined;

(2) The financial auditor needs to determine the audit range of the financial accounting department and the auditor;

(3) The accounting department responsible person needs to determine the personnel approval roles and the department responsible person control parameter list.

The optional steps are as follows:

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

1) The approval of the return department requires to determine the approval roles of the return department and personnel;

2) The responsible person of the return department needs to determine the role of personnel approval of the return department and the responsible person of the return department.

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

3) A line length, a business line length approval mode and a right person need to be determined;

4) Reporting the upper level (upper level return to the mouth, financial accounting), needing to confirm the upper level return to the mouth, personnel approve the role, return to the mouth department responsible person;

5) A financial audit is needed to determine a financial audit interrogation standard;

6) The method comprises the steps of applying for account reporting, and determining an invoice receiving and approving mode of a general switch parameter list;

7) Department responsible personnel approves and confirms personnel approval roles;

8) The return department approves, and confirms the return department and personnel approves roles;

9) The person in charge of the return department confirms the role of personnel approval of the return department and the person in charge of the return department;

10 A financial accounting auditor confirms the audit scope of the financial accounting department and the auditor;

11 A financial department responsible person, a personnel approval role, a department responsible person control parameter table;

12 Line length, confirming business line length approval mode and authorized person;

13 Reporting the upper level (upper level return, financial accounting), upper level return, personnel approving role, return department responsible person.

Specifically, the parameter set of the service scene is a parameter set of all the matched required configurations according to different possible service flows in the actual service system. The minimum closed-loop parameter set refers to a compliance parameter set with the minimum configuration parameters, which can realize closed-loop approval of the service scene, and is the minimum closed-loop parameter set from the step (1) to the step (3) aiming at the service hospitality expense scene. The theoretical maximum closed-loop configuration parameter set refers to a parameter set in which part links are added on the basis of the minimum closed-loop parameter set so that the minimum closed-loop parameter set becomes a subset of the minimum closed-loop parameter set, and for a business hospitality fee scene, the theoretical maximum closed-loop configuration parameter set is added in the steps 1) to 13) on the basis of the steps (1) to (3) (approval rejection is ignored). It is worth noting that: in fact, for some business processes of the partial business system, it is possible to do in fact "dead-loop", i.e. always circulate between the added parts. The theoretical maximum closed-loop parameter set here is therefore in fact a "bounded" extension of the flow, the case considered being based on a judgment of the actual traffic flow situation. After the minimum and maximum sets are determined, the following can be concluded:

For a set of parameter setsWhere i represents a user role and j represents a business scenario j.

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

Defining the additional newly added parameter set asThere is->Where k represents the kth parameter in the additional parameter set, λ represents whether the parameter is present, and λ assumes the value {0,1}. Thus, for the minimum closed loop parameter set and the theoretical maximum closed loop configuration parameter set, there is a relationship between:

in step 100, a traffic scenario j and a minimum closed-loop parameter set are established primarilyAnd theoretical maximum closed-loop configuration parameter set +.>Depending in part on the abstract capabilities of the business personnel, business product manager, and the accuracy and precision of the decision-making of the associated parameters.

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

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

In the use of the actual business system, the mechanism and the role of the parameter configuration manager need to be recorded, and the parameter set, namely the actual historical data, of each closed loop parameter setting is recorded asAssume that the set of all parameters is +.>Wherein->Representing the mth parameter in the business scenario j, there is a parameter set +.>Wherein z is _j Representing the maximum number of parameters of the traffic scenario. Note that two parameters of the same presence name and type exist in different traffic scenarios. Defining the total number of parameters as Z, there is +.>A mapping matrix a=a of the parameters and the traffic scenario can be constructed here _pq Wherein element a _pq The value rule of (2) is as follows:

the dimension of the mapping matrix is Z x J. For each business scenario, a dimension z can be constructed _j I.e. the column vector formed by the theoretical maximum closed loop configuration parameter set.

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

By using different thresholds, it is apparent that different probabilities can be obtained. Here, a true rate (TPR) is defined, which refers to a ratio of positive prediction and positive result (i.e., TP number) to total number, and the higher the ratio, the better the prediction accuracy. The TRP is made to approach 1 by obtaining the most appropriate threshold. At this time, a mapping relationship between actual parameter closed loop setting history data and actual sub-scenes can be established. Furthermore, each piece of history data has information of the roles of the parameter manager, so that the mapping relation between the sub-scene and the roles of the user can be obtained through simple clustering. As the underlying data for the next step.

Step 300: carrying out service sub-scene division on an actual service scene by using a training set 1, and correcting the widths of a minimum closed-loop parameter set and a theoretical maximum closed-loop configuration parameter set; and (3) carrying out configuration recommendation on administrators with different parameters according to the mapping relation between the actual service scene and the user role, which is obtained by the training set 2, namely prompting the administrators about the common sub-scene of the role.

Specifically, the training set 1 is applied to complete the division of the common sub-scenes of the actual service scene, namely the service scene, and the intervals of the actual service scene, the minimum closed-loop parameter set and the environment of 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 is achieved for different parameter administrators, namely closed-loop parameter setting commonly used by roles of the administrators is prompted, and a data base is provided for visual parameter configuration in step 400.

Based on the calculation result of step 200, training set 1 and training set 2 may be obtained. For the training set 1, the method can be used for dividing the common service sub-scene and correcting 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 scene. In step 100, it can be seen that: for each business scene j, the initialization interval of taking the parameters isHowever, the interval may deviate from the actual interval to some extent, and thus, correction is required to ensure the accuracy of the interval under the corresponding role. Therefore, what is actually required to be corrected is +.>Let us assume +.>The collected confirmation is a parameter configuration set of scene j under role i, and the collection can be used for converging an initialization interval so as to obtain an optimal interval.

After the optimal interval is determined, the relationship between the common sub-scene of the service scene and the user role is further required to be matched. It is worth noting that the parameters obtained in fact contain the roles and the organization information i, so that classification can be realized only by using a simple algorithm, mapping of the service sub-scene to the roles is realized, final closed-loop mapping from the roles to the service sub-scene and then to the specific parameter set is realized, and full-flow data connection and circulation are realized.

Step 400: the method is characterized in that a closed-loop parameter setting module based on visualization is designed, and the visualized parameter management configuration is realized by dynamically expanding the closed-loop parameter setting module to a theoretical maximum closed-loop configuration parameter set upwards based on a minimum closed-loop parameter set, and the function of automatically checking whether closed loops and parameter values are in compliance is realized.

It can be understood that after all inputs are completed, whether the closed loop is automatically checked and whether the parameter setting is compliant is automatically checked. This section is not only the embodiment of the calculation results of steps 100 to 300, but also the important transition from theory to application. From an architecture perspective, the modules are divided into a database module, a background module, and a front-end display module.

The database module mainly stores required relevant basic data, calculation results of the optimization part and all required relevant parameters, and is currently developed through an ORACLE database. The background module has three main functions: (1) The method comprises the steps of interacting with a database to obtain required data information, wherein 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 the related calculation and optimization; (3) a front-end interaction module: the module is generally used for responding to an API request initiated by the 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 mainly has three functions: (1) a preview module: displaying the minimum link of possible configuration of the bin well currently done by the user, wherein the user can select the most satisfactory configuration without starting 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 link parameters conveniently; (3) a checking module: the main function is to verify whether the whole flow is closed loop or not, and whether the parameter setting is correct or not, so that errors caused by flow configuration are reduced. The front-end technology was developed using an open source framework vue.

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

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

First, before starting to delineate the minimum closed-loop parameter set, the parameter configuration scenario under all roles needs to be first delineated in detail. Assume that the set of all business scenarios is S _i ＝{s _ij I=1, 2, 3..n }, whereini. The meaning of j is consistent with the above, and N represents a common keratin number. Then for each character S _i There is a set of business scenarios that may have the potential to repeat under different roles, but that will repeat in the set, such that the different roles will not share the piece of data. The business scene data is generally determined through communication between the business and a product manager, a detailed principle is maintained in the process, the business scene of any role is not omitted, and the reliability of the quality of the basic data is ensured. The information theory should be embodied in the demand analysis, detailed design of the business system, or in the product report.

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

After the set of traffic scenarios is determined in step 10, a minimum closed-loop parameter set for these traffic scenarios needs to be determined. Taking the basic business trip application as an example, as shown in fig. 7, the minimum closed loop includes the basic steps of business trip person application, line manager approval and department principal approval. However, the minimum closed loop refers to the problem that the approval is completed once from the business trip to the department responsible person, and no more processes and no approval refusal circulation are involved. At this point, it is apparent that this is the simplest step that can accomplish this flow. And thus is the lower limit set for 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 is that: the business applicant initiates the application, the application is transferred to the straight line manager for approval, when the straight line approver finishes the approval and transfers to the department leader for approval, the application is refused for a certain reason and returned to the business person, and at the moment, the business applicant needs to revise part of information according to the requirement to reinitiate the application. The situation at this time is not just that the minimum closed loop can be solved, and upward expansion based on the minimum closed loop is required.

However, a general service system does not allow a certain flow to flow infinitely, i.e. never ends. In this case, it is necessary to manually set the termination condition. Assuming that a business trip application cannot be approved and returned for more than three times, the process is automatically closed as long as the business trip application is approved and returned for more than three times by different levels, so that the applicant is required to initiate a new process again; as shown in fig. 7, for the theoretical maximum closed loop: the application can be returned by the department leader, the line manager and the department leader in sequence, and the application cannot pass until the application is submitted for the fourth time.

Taking the data in fig. 7 as an example, the minimum closed-loop parameter set isThe relevant parameters of the steps 1 to 3 are included; theoretical maximum closed-loop configuration parameter set +.>The relevant parameters of the steps 1 to 9 are included; the reasonable closed loop, i.e. the reasonable closed loop parameter set, comprises the relevant parameters of the steps 1 to 5. Therefore, it is the additional newly added parameter set that needs to be contracted in step 300 +.>Step 4 to step 9 in (a).

As shown in fig. 8, the method for configuring parameters based on a service scenario specifically includes:

step 20: and establishing a matrix of 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 association vectors.

For data extraction, firstly, a parameter set corresponding to a user and under a corresponding scene is taken out from a databaseWherein each element->All comprising oneA cursor, representing its position in the total parameter column. It was mentioned in step 200 that the total parameter list of the service scenario is set as ψ. While the parameter set of each sub-scene is phi ^j The following relationship exists between the two:

Ψ＝φ ¹ ∪φ ² ∪φ ³ ∪...∪φ ^J

if, for a certain history, a set of parameters is configuredThe presence is:

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 it is confirmed that no missing condition exists, the input is dirty data, and a training set needs to be cleaned; (2) If consider the missing situation that human exhausts may exist, the data existence is in fact a potential compliance scene. Then store the data in the candidate set ψ _po As an alternative to further screening. If parameter setSatisfying the condition of equations 1-2 indicates that it satisfies the input requirement from a dimensional point of view, and is extracted as an input for the next processing.

A parameter and scene mapping matrix (Parameter Mapping Matrix on Scene, PMMS for short) a, which is a z×j matrix, wherein the row dimension represents parameters and the column dimension represents compliance sub-scenes in a traffic scene. The matrix is used to characterize the specifics 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, and a standard PMMS matrix is as follows:

the correlation Vector (RV) characterizes a certain configuration parameterAssociation with each sub-scene, assume a configuration scenario +.>Is [1 1 0 0 ]] ^T This configuration is shown to use the parameters 1, 2 in the total parameter sequence, and not the parameters 3, 4. The method for calculating the association vector is as follows:

χ _RV ＝A×φ _in

therefore, according to the vector operation rule, the result is a J×1 column vector, and the symbol is gamma, the value gamma of each dimension of the vector _j The degree of similarity of the parameter set to sub-scene j is indicated. Further, the vector is normalized, specifically:

thereby obtaining a standardized similarity vector gamma ^std As 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-scene through the similarity, and obtaining the optimal similarity threshold through training of a training set.

The standard similarity vector gamma obtained by step 20 ^std The similarity between the closed-loop parameter set and each sub-scene can be known. However, only one sub-scene may be set per closed loop setting, so that the matching degree of the sub-scene can be determined according to the value of the similarity. TPR and FPR are introduced, respectively, as the percentage of the total number of TP and FP. It is apparent that a larger TPR indicates a better result. For a certain thresholdThe value delta, when the TPR is close to the required accuracy, indicates that at this threshold, all inferred results from similarity are nearly exactly identical to the actual results.

Step 22: when the optimal similarity threshold is obtained, a mapping relation M between actual parameter closed loop setting and business sub-scene is established ₁ 。

Further, because the role and the organization information of the parameter manager are stored in each setting, the relation mapping M of the service sub-scene and the user role and the organization is also established ₂ . The basic parameter flow mapping is completed, and a data basis is provided for visualization.

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

step 30: the business sub-scenarios are partitioned based on the actual business scenarios.

Specifically, the mapping relation M is obtained in step 200 ₁ The traffic sub-scenario in the actual scenario may be further partitioned. By business sub-scenario is meant several parameter sets most commonly used in real scenarios. Assume that a scene S related to a character _ij Then for this scene j, there is a sub-scene setAll that needs to be partitioned is the members of the set.

In the present application example, the actual input parameter vector is appliedAs an indicator of similarity before the parameter set. Thus, for a set of o parameter sets (one parameter set corresponding to each point of the undirected graph), a directed graph G can be constructed _j = (V, E, w). Wherein V represents a set of parameter sets of the business scene j (representing a set of points in the undirected graph), E represents an arc between points in the set of parameter sets, there is ≡>w represents an arcWeight, w= { w _e |e∈E}。

For graph G _j Defining a weighted adjacency matrix A thereof _j Its dimension is o×o. Matrix A _j The element in (a) is a _wv Wherein w, V ε V, σ represents the Gaussian kernel parameter:

definition matrix D _j The diagonal elements are:

the remaining elements are all 0.L (L) _j Is a graph G _j Laplace matrix of (C), have L _j ＝D _j -A _j 。

The goal of spectral clustering (spectral clustering) is to cut the graph into k sub-graphs and ensure that the interval weights and the minimum of the connected sub-graphs, and the weights and the large within the sub-graphs.

Assume that the graph is cut into two subgraphs, for subgraph i andassume that the connection path set between the two is E _c The method comprises the following steps:

the path set weight is W _c The numerical values are as follows:

the parameters based on spectral clustering configure the sub-scene division objective function as follows:

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

after the model is built, two parameters to be optimized exist, one is a Gaussian kernel function sigma, the other is the number K of separation clusters, and in order to determine the optimal value, an optimization algorithm based on simulated annealing and a historical configuration parameter set are provided for optimizing the two parameter values.

Thus, the constraints are:

where m is the number of iterations, te is the temperature threshold, and α 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 interval 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 obtained in step 30 can be further used for correctionOf the interval length, i.e. correction->Such that the parameter set maintains the most suitable dimension. In general, for a particular sub-scene under a role, the configured parameter sets must converge with time deduction, i.e. appear +_ with the smallest parameter set>Is a single cluster of cluster centers. It can be clustered using a simple k-means algorithm. In the early stages of smaller data volumes, multiple clusters may exist. Along with the continuous increase of the data volume, the clustering center of the data is continuously moved to the minimum closed loop until a clustering center is formed, and the actual parameter configuration interval is +.>Since the validity check has been performed on the parameter set of each parameter setting scenario in step 200, there must be:

by means of the convergent parameter configuration interval, the number of the sections can be effectively reducedFurther reduces the calculation complexity and improves the calculation efficiency of practical application. By this step, mapping of the scene to the parameter set configuration interval has been achieved.

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

Specifically, the mapping relation M is obtained in step 200 ₂ May be used to map the relationship between the scene and the user.

And when the parameters of the service scene are set each time, the user role and the mechanism information are carried. Therefore, the relation between the user role, the mechanism and the actual parameter configuration result can be obtained only by traversing all roles. At the initial stage of use, there may be a case where the sub-scene is considered to be incomplete. But the situation can be analyzed when the data is cleaned, so that the deficiency of the sub-scene caused by human negligence is further compensated. Thus, step 300 completes the circulation from the user to the character and from the character to the parameter set, and visual display is realized.

The following is a description based on a business application for a fee. In step 100, the present application example sets forth the overall flow necessary and optional for business application and approval. Obviously, for the service scene, the necessary links form the minimum closed loop, and the necessary links and all the optional combinations form the theoretical maximum closed loop. And thus, mapping of the service scene and the minimum closed loop and theoretical maximum closed loop is completed.

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

On the basis, sub-scenes are divided for closed-loop parameter sets meeting the conditions, and the divided flow is assumed to have the following two types:

(1) Department responsible person approves- > returns department approves- > financial auditors- > financial accounting department responsible person;

(2) Department responsible person approves- > return department approves- > financial auditor- > financial accounting department responsible person- > return of superior line- > superior line auditor- > superior line department responsible person- > superior line organization responsible person.

At this time, for the service scenario of the application for the recruitment, 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 recruitment application scene is the union of the two sub-scenes. Meanwhile, each parameter setting can be hooked with the organization and the role of the configuration manager, so that the two are also connected. At this time, the calculation is completed.

After the data calculation is completed, the steps of the visual parameter configuration are further illustrated, and as shown in fig. 10, the following explanation is provided:

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

Step 42: displaying a closed loop flow; the system sets the sub-scene visual display closed-loop flow according to the parameters selected by the user currently.

Step 43: configuring a flow environment; the closed loop flow comprises a plurality of links which can be skipped, and a user can select whether to skip the flow links when executing according to the actual requirements or the increasing judgment conditions in the line.

Step 44: configuring link parameters; placing the mouse on the link will display the parameter branches to be configured, clicking the parameters will jump to the corresponding parameter list page, and returning to the flow page after configuring the parameters.

Step 45: checking the flow; after all links and parameters are configured, clicking a check button, and the system confirms whether the flow is closed-loop or not under each condition, and whether the parameters are set completely or not, so that the success of the execution of the flow is ensured.

Specifically, as shown in fig. 11, taking the approval scenario of the hospitality fee service introduced in step 100 as an example, the parameter configuration process specifically includes the following:

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

Further, the user selects one of the recommended schemes, and the process is assumed to be department responsible person approval- > department return approval- > financial auditor- > financial accounting department responsible person, after the user clicks the configuration interface to open, the steps are displayed in a flow chart mode, and meanwhile "+" is arranged at the expandable node and used for adding unselected configurable links.

After the links are configured, a user only needs to move a mouse above a module of a department responsible person examination and approval link in the process, a yellow round frame of a person examination and approval role is popped up on the right side of the module, clicking is skipped to a person examination and approval role parameter table, clicking is performed to add and fill in information such as personnel numbers, institutions, effective time and the like, clicking is performed to submit, and double persons are waited to review. When the approval link of the return department is configured, approval conditions can be filled in the module, if the user applies that the sum of money is more than 10000 yuan, the approval link of the return department is required when the sum of the branch condition is more than 10000 yuan after filling, and similarly, the condition of the responsible link of the return department is 50000 yuan. And after the other link parameters are matched once, clicking a check button, popping up a system to prompt personnel responsible for the financial department to examine and approve the character parameters not to be set, and popping up a red round box in a module to indicate that the check fails. Click submission after resetting and click verification is completed, and the verification is effective after rechecking.

After the configuration links and parameters are finished, the ordinary user can initiate workflow according to the set flow and realize the full flow of approval when applying for the request for the approval.

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, wherein the service approval parameter configuration method according to the present application adopts 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 the configuration time and improve the efficiency of parameter configuration. Fig. 14 is a schematic diagram illustrating a comparison of a single approval passing rate using an existing parameter setting mode and a service approval parameter configuration method according to the present application, and as can be seen from fig. 14, the service approval parameter configuration method according to the present application can significantly improve the single approval passing rate compared to the existing parameter setting mode.

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

the first obtaining module 121 is configured to obtain multiple sets of approval parameter sets corresponding to a target service scenario, where the approval parameter sets include: a plurality of approval parameters and association relations among the approval parameters;

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

The preset spectral clustering model is a machine learning model based on a spectral clustering algorithm, which is obtained through training in advance, and is used for classifying the approval parameter sets.

In one embodiment of the present application, the service approval parameter configuration device further includes:

the second obtaining module is configured to obtain historical user information sets corresponding to each of the approval parameter sets, where the historical user information sets include: historical user role information and organization information;

correspondingly, the determining module is used for executing the following contents:

receiving a parameter configuration request of a target auditor, wherein the parameter configuration request comprises the following steps: role information and mechanism information of target auditors;

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

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

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

acquiring a plurality of groups of history parameter groups corresponding to a target service scene, wherein each group of history parameter groups corresponds to a history parameter vector group;

respectively applying a preset scene parameter mapping matrix to calculate the similarity with each historical parameter vector group, 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 set corresponding to the target parameter vector set as the approval parameter set.

the iteration module is used for executing the iteration steps: applying a preset similarity optimization model, an initial similarity threshold and each history parameter set to obtain an updated initial similarity threshold, wherein the similarity optimization model is a machine learning model based on an L-BFGS algorithm, which is obtained through training in advance;

and the optimal similarity threshold determining module is used for acquiring a historical parameter vector group with the similarity calculation result larger 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 smaller than or equal to a proportion threshold, if so, executing the iteration step again by using the updated initial similarity threshold, and if not, stopping executing the iteration step and taking the current initial similarity threshold as the optimal similarity threshold.

In one embodiment of the present application, the preset spectral clustering model includes: gaussian kernel function and partition cluster number; correspondingly, the service approval parameter configuration device further comprises:

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

The embodiment of the service approval parameter configuration device provided in the present disclosure may be specifically used to execute the process flow of the embodiment of the service approval parameter configuration method, and the functions thereof are not described herein in detail, and reference may be made to the detailed description of the embodiment of the service approval parameter configuration method.

As can be seen from the above description, the method and the device for configuring the service approval parameters provided by the application can improve the accuracy and the efficiency of parameter configuration, and further can improve the accuracy and the efficiency of service approval. And defining a compliance closed-loop sub-scene of the service scene, so that parameter configuration can be performed under the compliance sub-scene, and the possibility of missed configuration is only reduced. Through the association relation between the service sub-scene and the roles, the method can determine which sub-scenes are commonly used in the corresponding own roles and institutions of different users aiming at specific parameter configuration scenes. The role-to-business scene, the business scene-to-sub scene and the specific parameter can be communicated. 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 a system core link is reduced, and the usability and maintainability of the parameter configuration process are improved.

In order to improve accuracy and efficiency of parameter configuration and be suitable for complex parameter configuration scenes and further improve accuracy and efficiency of business approval, the application provides an embodiment of an electronic device for realizing all or part of contents in a business approval parameter configuration method, wherein the electronic device specifically comprises 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 communication with each other through the bus; the communication interface is used for realizing information transmission between the service approval parameter configuration device and related equipment such as a user terminal; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, etc., and the embodiment is not limited thereto. In this embodiment, the electronic device may be implemented with reference to an embodiment for implementing the method for configuring the service approval parameter and an embodiment for implementing the device for configuring the service approval parameter, and the contents thereof are incorporated herein, and are not repeated here.

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 may 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 structures to implement telecommunications functions or other functions.

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

From the above description, it can be seen that the electronic device provided by the embodiment of the present application can improve accuracy and efficiency of parameter configuration, and is suitable for complex parameter configuration scenarios, so as to improve accuracy and efficiency of business approval.

In another embodiment, the service approval parameter configuration device may be configured separately from the central processor 9100, for example, the service approval parameter configuration device may be configured as a chip connected to the central processor 9100, and the service approval parameter configuration function is implemented by 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 need not include all of the components shown in fig. 15; in addition, the electronic device 9600 may further include components not shown in fig. 15, and reference may be made to the related art.

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

The memory 9140 may 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 about failure may be stored, and a program for executing the information may be stored. And the central processor 9100 can execute the program stored in the memory 9140 to realize information storage or processing, and 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. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.

The memory 9140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, etc. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. The memory 9140 may also be some other type of device. The 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 storing application programs and function programs or a flow for executing operations of the electronic device 9600 by the central processor 9100.

The memory 9140 may also include a data store 9143, the data store 9143 for storing 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 of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).

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

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, etc., 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 to receive audio input from the microphone 9132 to implement usual telecommunications functions. The audio processor 9130 can include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100 so that sound can be recorded locally through the microphone 9132 and sound stored locally can be played through the speaker 9131.

As can be seen from the above description, the electronic device provided by the embodiment of the present application can improve accuracy and efficiency of parameter configuration, and is suitable for complex parameter configuration scenarios, so as to improve accuracy and efficiency of business approval.

The embodiment of the present application also provides a computer-readable storage medium capable of implementing all the steps in the service approval parameter configuration method in the above 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 in the service approval parameter configuration method in the above embodiment, for example, the processor implements the following steps when executing the computer program:

As can be seen from the above description, the computer readable storage medium provided by the embodiments of the present application can improve accuracy and efficiency of parameter configuration, and is suitable for complex parameter configuration scenarios, so as to improve accuracy and efficiency of business approval.

The embodiments of the method of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment mainly describes differences from other embodiments. For relevance, see the description of the method embodiments.

It will be appreciated by those skilled in the art that 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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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 principles and embodiments of the present application have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims

1. The business approval parameter configuration method is characterized by comprising the following steps:

obtaining multiple groups of approval parameter sets corresponding to a target business scene, wherein the approval parameter sets comprise: the method comprises the steps that a plurality of approval parameters and association relations among the approval parameters are included, the approval parameters comprise audit role information and audit authority information corresponding to the audit role information, the association relations among the approval parameters represent the association relations among the audit role information, and the approval role information comprises: department responsible person, financial approver and financial department responsible person information, the association between the approval role information includes: the department responsible person, the financial approver and the financial department responsible person are sequentially associated, and the approval parameter set is acquired based on the history parameter set;

Determining a plurality of target approval sub-scenes corresponding to the target business scene by applying a preset spectral clustering model and each approval parameter set, wherein the target approval sub-scenes correspond to each auditor, and each target approval sub-scene comprises: at least one group of examination and approval parameter groups is 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, and the parameter configuration request comprises: role information and mechanism information of target auditors;

before the preset spectral clustering model and each approval parameter set are applied to determine a plurality of target approval sub-scenes corresponding to the target business scene, the method further comprises the following steps:

acquiring a historical user information group corresponding to each examination and approval parameter group, wherein the historical user information group comprises: historical user role information and organization information;

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

2. The method for configuring service approval parameters according to claim 1, wherein the obtaining a plurality of sets of approval parameters corresponding to a target service scenario includes:

3. The method for configuring a business approval parameter according to claim 2, further comprising, before the applying the preset scene parameter mapping matrix to perform similarity calculation with each of the historical parameter vector sets, respectively:

The iterative steps are performed: applying a preset similarity optimization model, an initial similarity threshold and each history parameter set to obtain an updated initial similarity threshold, wherein the similarity optimization model is a machine learning model based on an L-BFGS algorithm, which is obtained through training in advance;

and acquiring a historical parameter vector group with the similarity calculation result being larger than an updated initial similarity threshold value 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 smaller than or equal to a proportion threshold value, if so, executing an iteration step again by using the updated initial similarity threshold value, and if not, stopping executing the iteration step and taking the current initial similarity threshold value as the optimal similarity threshold value.

4. The method for configuring traffic approval parameters according to claim 1, wherein,

the preset spectral clustering model is a machine learning model based on a spectral clustering algorithm and is obtained through training in advance and is used for classifying the approval parameter groups.

5. The method for configuring business approval parameters according to claim 1, wherein the preset spectral clustering model comprises: gaussian kernel function and partition cluster number;

Correspondingly, before the determining of the multiple target approval sub-scenes corresponding to the target business scene, the method further comprises:

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

6. A business approval parameter configuration device, comprising:

the first acquisition module is used for acquiring a plurality of groups of approval parameter groups corresponding to the target business scene, wherein the approval parameter groups comprise: the method comprises the steps that a plurality of approval parameters and association relations among the approval parameters are included, the approval parameters comprise audit role information and audit authority information corresponding to the audit role information, the association relations among the approval parameters represent the association relations among the audit role information, and the approval role information comprises: department responsible person, financial approver and financial department responsible person information, the association between the approval role information includes: the department responsible person, the financial approver and the financial department responsible person are sequentially associated, and the approval parameter set is acquired based on the history parameter set;

the determining module is configured to determine a plurality of target approval sub-scenes corresponding to the target service scene by applying a preset spectral clustering model and each approval parameter set, where the target approval sub-scenes correspond to each auditor, and each target approval sub-scene includes: at least one group of examination and approval parameter groups is 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, and the parameter configuration request comprises: role information and mechanism information of target auditors;

The service approval parameter configuration device further comprises:

7. The device for configuring approval parameters of a business according to claim 6, wherein the first acquisition module is configured to:

8. The traffic approval parameter configuration apparatus according to claim 7, further comprising:

9. The device for configuring parameters of business approval according to claim 6, wherein the preset spectral clustering model is a machine learning model based on a spectral clustering algorithm, which is obtained by training in advance, and is used for classifying the parameter sets of approval.

10. The business approval parameter configuration device according to claim 6, wherein the preset spectral clustering model comprises: gaussian kernel function and partition cluster number;

correspondingly, the service approval parameter configuration device further comprises:

11. 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 business approval parameter configuration method of any one of claims 1 to 5 when the program is executed by the processor.

12. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor implement the business approval parameter configuration method of any one of claims 1 to 5.