A process management method and device based on decision tree model

Abstract

The present application discloses a process management method and device based on a decision tree model, which obtains corresponding service data by analyzing the service process, obtains process parameters corresponding to the service data in combination with the configured database, and uses the decision tree model to perform intelligent prediction based on the service data and process parameters, so as to determine whether to automatically allocate the service process based on the prediction results. This method not only avoids the influence of subjective factors caused by human participation, but also automatically determines the allocated users through the configured database, effectively improving the overall management efficiency and the operational efficiency of the enterprise.

Description

Technical Field

[0001] The present application belongs to the field of information processing technology, and in particular relates to a process management method and device based on a decision tree model. Background Art

[0002] With the development of information technology, the demand for digital and intelligent business processes is increasing. Modern enterprise management has put forward new requirements for office automation, especially for enterprises with a wide range of business types and complex business processes. Among them, business approval is a prerequisite for carrying out business activities. The automation and intelligence of business approval are of great significance to improving office efficiency, enhancing the standardization of enterprise operations, and enhancing the transparency of business processes.

[0003] However, the existing process management methods of enterprises mostly rely on pre-defined management models, which have poor flexibility. In addition, the level of manual participation is too high, which is prone to being mixed with too many subjective factors, thus affecting the overall management efficiency and the operational efficiency of the enterprise. Summary of the Invention

[0004] This application aims to address the technical issues mentioned above, such as the existing enterprise process management methods mostly relying on predefined management models, which are less flexible, and the high degree of manual involvement, which is easily mixed with too many subjective factors, thus affecting the overall management efficiency and the operational efficiency of the enterprise. A process management method and device based on a decision tree model are proposed. The technical solution is as follows:

[0005] In a first aspect, an embodiment of the present application provides a process management method based on a decision tree model, comprising:

[0006] When receiving the service process distributed by the server, determining first service data including the target product and the target service according to the service process;

[0007] Determining first process parameters in a first database configured by the server based on the target product and the target service;

[0008] Obtaining a prediction result corresponding to the first service data according to the target product, the target service, the first process parameter, and a preset decision tree model;

[0009] When the prediction result corresponding to the first service data exceeds a preset threshold, determining a first user corresponding to the service process in a second database configured by the server;

[0010] The service process is allocated to a target terminal corresponding to the first user, so that the target terminal manages the service process, and a management result fed back by the target terminal is received.

[0011] In an optional solution of the first aspect, determining the first process parameter in a first database configured by the server based on the target product and the target service includes:

[0012] Input the target product into a preset word embedding model to obtain a product set including the target product; wherein the product set includes at least two product types, and the preset word embedding model is trained by historical process data stored in the server;

[0013] Determining, in a first database configured by the server, product process parameters corresponding to all product types in the product set;

[0014] Inputting the target service into a preset word embedding model to obtain a service set including the target service; wherein the service set includes at least two service types;

[0015] The service process parameters corresponding to all service types in the service set are determined in the first database, and the product process parameters and the service process parameters are used as first process parameters.

[0016] In another optional solution of the first aspect, obtaining a prediction result corresponding to the first service data based on the target product, the target service, the first process parameter, and a preset decision tree model includes:

[0017] Input all product types and product process parameters in the product set into a preset decision tree model to obtain a first prediction result corresponding to each product type;

[0018] When it is detected that the number of identical first prediction results exceeds a preset number threshold, determining the first prediction result corresponding to the target product;

[0019] Input all service types and service process parameters in the service set into a preset decision tree model to obtain a second prediction result corresponding to each service type;

[0020] When it is detected that the number of identical second prediction results exceeds a preset number threshold, determining the second prediction result corresponding to the target service;

[0021] A weighted summation process is performed on the first prediction result and the second prediction result to obtain a prediction result corresponding to the first service data.

[0022] In another optional solution of the first aspect, determining the first user corresponding to the service process in a second database configured by the server includes:

[0023] In a second database configured by the server, a set of users having authority to manage the target service is sequentially determined;

[0024] The user set is randomly arranged, and a first user corresponding to the service process is determined from the processed user set.

[0025] In yet another optional solution of the first aspect, determining the first user corresponding to the service process in a second database configured by the server further includes:

[0026] Distributing a service flow management request to all corresponding user terminals in a second database configured by the server;

[0027] When confirmation requests fed back by at least two user terminals are received within a preset time interval, obtaining the management authority of each user terminal based on the second database;

[0028] When the management authority of any user terminal includes the authority to manage the target service, a first user corresponding to the service process is determined according to the user terminal.

[0029] In another optional solution of the first aspect, before determining the first user corresponding to the service process in the second database configured by the server, the method further includes:

[0030] Determining second service data including a second user and a target service according to the service process, and determining second process parameters in the first database based on the second user and the target service;

[0031] Obtaining a prediction result corresponding to the second service data according to the second user, the target service, the second process parameter, and a preset decision tree model;

[0032] Determining a first user corresponding to the service process in a second database configured by the server includes:

[0033] When the prediction result corresponding to the second service data exceeds a preset threshold, a first user corresponding to the service process is determined in a second database configured by the server.

[0034] In another optional solution of the first aspect, after receiving the management result fed back by the target terminal, the method further includes:

[0035] The service process, the first user corresponding to the service process, and the management result are updated to a preset management database, and the management information of the first user is obtained according to the updated preset management database.

[0036] In a second aspect, an embodiment of the present application provides a process management device based on a decision tree model, comprising:

[0037] A first management module is configured to, upon receiving a service process distributed by the server, determine first service data including a target product and a target service according to the service process;

[0038] A second management module is configured to determine a first process parameter in a first database configured by the server based on the target product and the target service;

[0039] a third management module, configured to obtain a prediction result corresponding to the first service data based on the target product, the target service, the first process parameter, and a preset decision tree model;

[0040] a fourth management module, configured to determine a first user corresponding to the service process in a second database configured by the server when a prediction result corresponding to the first service data exceeds a preset threshold;

[0041] The fifth management module is configured to allocate the service process to a target terminal corresponding to the first user so that the target terminal manages the service process and receive a management result fed back by the target terminal.

[0042] In a third aspect, an embodiment of the present application further provides a process management device based on a decision tree model, comprising a processor and a memory;

[0043] The processor is connected to the memory;

[0044] a memory for storing executable program code;

[0045] The processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the process management method based on the decision tree model provided by the first aspect of the embodiment of the present application or any implementation method of the first aspect.

[0046] In a fourth aspect, an embodiment of the present application provides a computer storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, the process management method based on the decision tree model provided by the first aspect of the embodiment of the present application or any implementation method of the first aspect can be implemented.

[0047] In an embodiment of the present application, when performing process management, when a service process distributed by a server is received, first service data including a target product and a target service is determined according to the service process; based on the target product and the target service, first process parameters are determined in a first database configured by the server; a prediction result corresponding to the first service data is obtained according to the target product, the target service, the first process parameters, and a preset decision tree model; when the prediction result corresponding to the first service data exceeds a preset threshold, a first user corresponding to the service process is determined in a second database configured by the server; the service process is assigned to a target terminal corresponding to the first user, so that the target terminal manages the service process, and a management result fed back by the target terminal is received. By parsing the service process to obtain corresponding service data, combining the configured database to obtain process parameters corresponding to the service data, and using the decision tree model to perform intelligent prediction based on the service data and process parameters, it is determined whether to automatically assign the service process according to the prediction result. This not only avoids the influence of subjective factors caused by human participation, but also automatically determines the assigned user through the configured database, effectively improving the overall management efficiency and the operational efficiency of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 An overall flow chart of a process management method based on a decision tree model provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of the system architecture of a process management method based on a decision tree model provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of the structure of a process management device based on a decision tree model provided in an embodiment of the present application;

[0052] Figure 4 A schematic structural diagram of another process management device based on a decision tree model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0054] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application. Different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments described. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, even though the embodiment may not be clearly described in the following text.

[0055] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the elements described without departing from the scope of the present application. Various examples may appropriately omit, replace, or add various processes or components. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted, or combined. In addition, features described in some examples may be combined in other examples.

[0056] See also Figure 1 , Figure 1 The figure shows an overall flow chart of a process management method based on a decision tree model provided in an embodiment of the present application.

[0057] like Figure 1 As shown, the process management method based on the decision tree model may include at least the following steps:

[0058] Step 102: When a service process distributed by the server is received, first service data including a target product and a target service is determined according to the service process.

[0059] In embodiments of the present application, a process management method based on a decision tree model can be applied to, but is not limited to, a platform terminal. The platform terminal can be connected to a server and a user terminal, respectively, to send a corresponding process to a designated user terminal based on a service process issued by the server. For example, but not limited to, taking the service process type as an approval process, the server can be understood as the server corresponding to the enterprise system, the user terminal can be understood as all user terminals corresponding to all users with management authority in the enterprise system, and the platform terminal can be understood as a process approval terminal for managing the enterprise system. When the platform terminal receives the approval process sent by the server, the platform terminal can identify approval data containing approval features from the approval process, determine corresponding process parameters using a first database configured by the server, and combine the process parameters, approval features, and a preset decision tree model to obtain a prediction result corresponding to the approval process. It is understood that when the prediction result meets the approval requirements, the platform terminal can then combine the second database configured by the server to send the approval process to a user terminal with approval management authority, so that the user terminal can approve the approval process. Here, the first database configured by the server may be, but is not limited to, a database generated by the server based on all approval process records of the enterprise system, and the first database may be updated regularly; the second database configured by the server may be, but is not limited to, a database generated for the identity address information of all users with management authority in the enterprise system, and the second database may also be updated regularly.

[0060] Also see here Figure 2 The system architecture diagram of a process management method based on a decision tree model provided by an embodiment of the present application is shown as follows: Figure 2As shown, the system architecture may include at least a platform terminal 201, a server 202 corresponding to an enterprise system, and a user terminal 203 with management authority. Specifically, the user terminal 203 may be any user terminal with management authority in one or more enterprise systems. When the platform terminal 201 receives a service process distributed by the server 202, it determines first service data containing a target product and a target service based on the service process. Then, based on the target product and the target service, it determines first process parameters in a first database configured by the server 202. Then, based on the target product, the target service, the first process parameters, and a preset decision tree model, it obtains a prediction result corresponding to the first service data. Then, when the prediction result corresponding to the first service data exceeds a preset threshold, it determines a first user corresponding to the service process in a second database configured by the server 202, and assigns the service process to the target terminal 203 corresponding to the first user, so that the target terminal 203 can manage the service process, and receives feedback on the management result from the target terminal 203. By analyzing the service process to obtain the corresponding service data, combining the configured database to obtain the process parameters corresponding to the service data, and using the decision tree model to make intelligent predictions based on the service data and process parameters, it is determined whether to automatically allocate the service process based on the prediction results. This not only avoids the influence of subjective factors caused by human participation, but also automatically determines the allocated users through the configured database, effectively improving the overall management efficiency and the operational efficiency of the enterprise.

[0061] Specifically, when a platform terminal performs process management on an enterprise system, upon receiving a service process distributed by a server corresponding to the enterprise system, it indicates that the enterprise system has a process management requirement. Furthermore, first service data containing a target product and a target service may be generated based on, but is not limited to, the service process. This first service data may be understood as data obtained after feature process extraction processing has been performed on the service process. It is understood that a service process may be understood as a process in which a user with administrative authority in the enterprise system can execute a service. For example, but not limited to, an approval process for a user xx to apply for xx product xx transaction, this approval process must be approved by a user with approval process management authority in the enterprise system, and the result of the user's approval process may be, but is not limited to, approval or rejection. Here, the service process may include at least any two service parameters such as user name, product type, service type or service time, and taking the above-mentioned service process as the approval process of xx user applying for xx transaction for xx product as an example, the first service data determined from the service process may specifically be xx product applying for xx transaction (xx product may correspond to product type, and xx transaction may correspond to service type), or a framework statement containing xx product applying for xx transaction, and is not limited to this.

[0062] Step 104: Based on the target product and the target service, determine first process parameters in a first database configured by the server.

[0063] Specifically, after determining the first service data containing the target product and the target service from the service process, a first process parameter representing the historical occurrence frequency of the target product type recorded in the enterprise system and the historical occurrence frequency of the target service type recorded in the enterprise system can be determined in the first database configured by the server based on the target product type and the target service type. For example, but not limited to, the number of all processes with the target product type can be counted in the first database configured by the server based on the target product type, and the number of all processes with the target service type can also be counted in the first database configured by the server based on the target service type, and the number of all processes with the target product type and the number of all processes with the target service type can be used as the first process parameter. Of course, the proportion of the number of all processes with the target product type to the total number of processes can also be calculated in the first database configured by the server based on the target product type, and the proportion of the number of all processes with the target service type to the total number of processes can also be calculated in the first database configured by the server based on the target service type, and the examples are not limited thereto.

[0064] It is understandable that the first database configured by the server can be generated based on, but not limited to, all types of historical service processes recorded in the enterprise system, and can be updated at preset time intervals to ensure the accuracy and effectiveness of the first process parameters.

[0065] As an option in the embodiment of the present application, based on the target product and the target service, determining the first process parameter in the first database configured by the server includes:

[0066] Input the target product into a preset word embedding model to obtain a product set including the target product; wherein the product set includes at least two product types, and the preset word embedding model is trained by historical process data stored in the server;

[0067] Determining, in a first database configured by the server, product process parameters corresponding to all product types in the product set;

[0068] Inputting the target service into a preset word embedding model to obtain a service set including the target service; wherein the service set includes at least two service types;

[0069] The service process parameters corresponding to all service types in the service set are determined in the first database, and the product process parameters and the service process parameters are used as first process parameters.

[0070] In order to ensure the applicability of the first process parameters and the reliability of subsequent prediction results, it is also possible but not limited to obtaining approximate product types and synonymous product types corresponding to the target product type through semantic analysis processing, as well as obtaining approximate service types and synonymous service types corresponding to the target service type, and then determining the corresponding first process parameters by the first database configured by the server.

[0071] Specifically, during the process of determining the first process parameter in the first database configured by the server, the target product type may be input into a preset word embedding model, but is not limited to inputting the target product type into the model. The model then outputs all product types that are similar or synonymous with the target product type, and the target product and the target product are used as a product set. It is understood that to improve the accuracy of the word embedding model outputting similar or synonymous product types based on the target product type, all product types may be extracted from all types of historical service processes recorded in the enterprise system, but is not limited to, and the word embedding model may be trained using all product types.

[0072] Then, after obtaining the product set, the first database configured by the server can determine the historical occurrence frequency recorded in the enterprise system of all product types in the product set. For example, but not limited to, based on all product types in the product set, the number of processes with any one of all product types can be counted in the first database configured by the server, and the number of processes with any one of all product types can be used as a product process parameter.

[0073] Then, the target service type can also be input into the word embedding model mentioned above, but is not limited to it, so as to output all service types that are similar or synonymous with the target service type through the word embedding model, and all service types and the target service type are used as a service set. It is understandable that in order to improve the accuracy of the word embedding model outputting similar or synonymous service types according to the target service type, it is also possible but not limited to extracting all service types from all types of historical service processes recorded in the enterprise system, and training the word embedding model together with all the product types and all the service types mentioned above. Of course, a separate preset word embedding model can also be trained directly by all service types, that is, both product types and service types can correspond to preset word embedding models, and are not limited to this.

[0074] Then, after obtaining the service set, the first database configured by the server can also determine the historical occurrence frequency recorded in the enterprise system of all service types in the service set. For example, but not limited to, based on all service types in the service set, the number of processes with any one of all service types can be counted in the first database configured by the server, and the number of processes with any one of all service types can be used as a service process parameter.

[0075] Step 106: Obtain a prediction result corresponding to the first service data based on the target product, the target service, the first process parameter, and the preset decision tree model.

[0076] Specifically, after determining the first process parameter from the first database, the first process parameter, the target product type, and the target service type can be input into a preset decision tree model, but is not limited to, so as to predict the prediction result corresponding to the target product type and the prediction result corresponding to the target service type through the decision tree model, and the prediction result corresponding to the target product type and the prediction result corresponding to the target service type can be combined to determine the prediction result corresponding to the first service data. In the process of inputting the first process parameter, the target product type, and the target service type into the preset decision tree model, the process parameter corresponding to the target product type and the target product type in the first process parameter can be input into the preset decision tree model, so as to predict the management result for characterizing the user of the target product, and then the process parameter corresponding to the target service type and the target service type in the first process parameter can be input into the preset decision tree model, so as to predict the management result for characterizing the user of the target service by the decision tree model. Here, the preset decision tree model can be, but is not limited to, trained by multiple service processes in the enterprise system that are marked with actual management results and historical process times, and the decision tree model can also predict the management results used to characterize the user's target service to the target product based on the commonly input first process parameters, target product type, and target service type, and is not limited to this.

[0077] It can be understood that when the prediction result corresponding to the target product type and the prediction result corresponding to the target service type are consistent, the prediction result corresponding to the target product type or the prediction result corresponding to the target service type can be, but is not limited to, directly used as the prediction result corresponding to the first service data; when the prediction result corresponding to the target product type and the prediction result corresponding to the target service type are inconsistent, it indicates that the result of the prediction made by the decision tree model at this time may be abnormal, and then the user with the authority to manage the service process can be directly determined in the second database configured by the server to send the service process to the user's corresponding terminal, that is, the service process is directly managed by the user.

[0078] As another option of the embodiment of the present application, obtaining a prediction result corresponding to the first service data according to the target product, the target service, the first process parameter, and a preset decision tree model includes:

[0079] Input all product types and product process parameters in the product set into a preset decision tree model to obtain a first prediction result corresponding to each product type;

[0080] When it is detected that the number of identical first prediction results exceeds a preset number threshold, determining the first prediction result corresponding to the target product;

[0081] Input all service types and service process parameters in the service set into a preset decision tree model to obtain a second prediction result corresponding to each service type;

[0082] When it is detected that the number of identical second prediction results exceeds a preset number threshold, determining the second prediction result corresponding to the target service;

[0083] A weighted summation process is performed on the first prediction result and the second prediction result to obtain a prediction result corresponding to the first service data.

[0084] Specifically, in the process of obtaining the prediction result corresponding to the first service data, it is also possible but not limited to inputting all the product types and product process parameters in the above-mentioned product set into a preset decision tree model, so that the decision tree model can respectively predict the management results used to characterize the user's different product types. For example, the product types A1, A2 and A3 and the product process parameter a are input into the decision tree model, so that the decision tree model can predict the first prediction results B1, B2 and B3 corresponding to A1, A2 and A3 respectively. When it is detected that the number of identical prediction results in B1, B2 and B3 exceeds the preset number threshold, it indicates that the decision tree model's prediction results for the product set as a whole are relatively consistent, and then the first prediction result corresponding to the target product can be determined from all the prediction results. It can be understood that the preset number threshold can be, but is not limited to, determined based on the number of all product types in the product set. For example, but not limited to, the preset number threshold is equal to the product of the number of all product types in the product set and a preset proportional coefficient. The preset proportional coefficient can be any value in the range of 0.5-0.8. The preset number threshold can be any number greater than 1, and is not limited to this.

[0085] It should be noted that when it is detected that the number of identical first prediction results does not exceed the preset number threshold, it indicates that the prediction results of the decision tree model for the entire product set are relatively inconsistent. The target product and product process parameters can be input into the decision tree model multiple times to obtain multiple prediction results corresponding to the target product. When the multiple prediction results are consistent, the prediction result can be used as the first prediction result corresponding to the target product, and is not limited to this.

[0086] Then, it is also possible, but not limited to, to input all the service types and service process parameters in the above-mentioned service set into a preset decision tree model, so that the decision tree model can respectively predict the management results used to characterize the user's different service types. For example, the service types and service process parameters c, namely C1, C2 and C3, are input into the decision tree model, so that the decision tree model can respectively predict the second prediction results D1, D2 and D3 corresponding to C1, C2 and C3. When it is detected that the number of identical prediction results in D1, D2 and D3 exceeds the number threshold mentioned above, it indicates that the prediction results of the decision tree model for the service set as a whole are relatively consistent, and then the second prediction result corresponding to the target service can be determined from all the prediction results.

[0087] It should be noted that when it is detected that the number of identical second prediction results does not exceed the preset number threshold, it indicates that the prediction results of the decision tree model for the entire service set are relatively inconsistent. The target service and service process parameters can be input into the decision tree model multiple times to obtain multiple prediction results corresponding to the target service. When the multiple prediction results are consistent, the prediction result can be used as the second prediction result corresponding to the target service, and is not limited to this.

[0088] Next, after obtaining the first prediction result corresponding to the target product and the second prediction result corresponding to the target service, the first and second prediction results may be weighted and summed to obtain the prediction result corresponding to the first service data. The weight values ​​corresponding to the first and second prediction results may be obtained by analyzing, but not limited to, processing multiple service processes in the enterprise system that are marked with actual management results, thereby effectively ensuring the rationality and reliability of the weight values.

[0089] Step 108: When the prediction result corresponding to the first service data exceeds a preset threshold, a first user corresponding to the service process is determined in a second database configured by the server.

[0090] Specifically, after obtaining the prediction result corresponding to the first service data, when it is detected that the prediction result exceeds a preset threshold, it indicates that the user is more likely to execute the service process when managing the service process. For example, but not limited to, when the service process type is an approval process, the prediction result exceeding the preset threshold can indicate that the user is more likely to approve the approval process, and then the first user with the authority to manage the service process can be determined in the second database configured by the server. It is understandable that the preset threshold can be, but not limited to, any number in the range of 0.5-0.8, and when it is detected that the prediction result does not exceed the preset threshold, it indicates that the user is less likely to execute the service process when managing the service process. For example, but not limited to, when the service process type is an approval process, the prediction result not exceeding the preset threshold can indicate that the user is less likely to approve the approval process. In order to improve overall management efficiency, information representing the low possibility of executing the service process can be fed back to the enterprise system so that the enterprise system can quickly process the service process.

[0091] As another optional embodiment of the present application, determining the first user corresponding to the service process in a second database configured by the server includes:

[0092] In a second database configured by the server, a set of users having authority to manage the target service is sequentially determined;

[0093] The user set is randomly arranged, and a first user corresponding to the service process is determined from the processed user set.

[0094] Specifically, to avoid excessive user management involvement in the service process, which can be easily contaminated by subjective management factors introduced by users, the identity and address information of all users with management rights for the target service can be determined in a second database configured by the server, and this identity and address information of all users can be used as a user set. The second database configured by the server can include, but is not limited to, the identity and address information of all users with management rights in the enterprise system. The user set can be obtained by filtering out the identity and address information of users with management rights for the target service type.

[0095] Next, after obtaining the set of users with the authority to manage the target service type, the set of users may be randomly arranged using, but not limited to, the Fisher-Yates algorithm. The algorithm logic is as follows:

[0096] Set the length of the approver array to be N as arrd, generate a random number i by the random function, replace the elements of arrd[N] ​​and arrd[i] to generate a scrambled array arrd(1), and repeat this process until the final scrambled array arrd(N-1) is obtained.

[0097] Next, after randomly permuting the user set, a specified number of user identity and address information pieces can be extracted from the processed user set as the first user, but is not limited to this. Here, the specified number can be understood as a positive integer greater than or equal to 2, which is less than the total number of user identity and address information pieces included in the user set. The order of extracting the specified number can be, but is not limited to, selecting the first n user identity and address information pieces in the user set as the first user, where n is the specified number.

[0098] As another optional embodiment of the present application, determining the first user corresponding to the service process in a second database configured by the server further includes:

[0099] Distributing a service flow management request to all corresponding user terminals in a second database configured by the server;

[0100] When confirmation requests fed back by at least two user terminals are received within a preset time interval, obtaining the management authority of each user terminal based on the second database;

[0101] When the management authority of any user terminal includes the authority to manage the target service, a first user corresponding to the service process is determined according to the user terminal.

[0102] Specifically, in the process of determining the first user corresponding to the service process, a service process management request can also be sent to the user terminals corresponding to all user identity address information in the second database, but is not limited to, to determine whether there is a user who can quickly execute process management. It is understood that when confirmation requests are received from at least two user terminals within a preset time interval, it indicates that there is currently a user who can quickly execute process management. It can then be determined whether the user identity address information corresponding to all user terminals that have feedback confirmation requests has the authority to manage the target service type. It is understood that when the management authority of any user terminal has the authority to manage the target service, in order to effectively ensure the efficiency of process management, the user identity address information corresponding to the user terminal can be directly used as the first user. Of course, in the embodiment of the present application, one user identity address information with the authority to manage the target service type can be used as the first user, and multiple user identity address information with the authority to manage the target service type can also be used as the first user. This is not limited to this.

[0103] Step 110: Allocate the service process to a target terminal corresponding to the first user, so that the target terminal manages the service process, and receives a management result fed back by the target terminal.

[0104] Specifically, after determining the first user who can perform service process management, the service process can be assigned to all target terminals corresponding to the first user, so that the target terminals can manage the service process. For example, but not limited to, when the service process type is an approval process, the target terminal can approve the approval process and receive the approval results fed back by the target terminal for corresponding analysis and processing to facilitate optimization of the overall process management process. It is understandable that the management results of the task process managed by the target terminal mentioned above can also be displayed to the client terminals corresponding to the identity address information of all users with the authority to manage the target service type, so as to reflect the transparency and traceability of the service process management.

[0105] As another optional embodiment of the present application, after receiving the management result fed back by the target terminal, the method further includes:

[0106] The service process, the first user corresponding to the service process, and the management result are updated to a preset management database, and the management information of the first user is obtained according to the updated preset management database.

[0107] Specifically, after receiving the management results fed back by the target terminal, the management results for the user identity and address information corresponding to the target terminal can also be recorded and processed. Specifically, the service process, the first user corresponding to the service process, and the management results can be updated to a preset management database to reorganize the current management information for the user identity and address information corresponding to the target terminal, thereby facilitating the effective optimization of the overall process management process. Here, the management information can be understood as the specific management method for all service processes. For example, when all service processes are approval processes, the management information can correspond to the approval results executed for all approval processes.

[0108] As another optional embodiment of the present application, before determining the first user corresponding to the service process in the second database configured by the server, the method further includes:

[0109] Determining second service data including a second user and a target service according to the service process, and determining second process parameters in the first database based on the second user and the target service;

[0110] Obtaining a prediction result corresponding to the second service data according to the second user, the target service, the second process parameter, and a preset decision tree model;

[0111] Determining a first user corresponding to the service process in a second database configured by the server includes:

[0112] When the prediction result corresponding to the second service data exceeds a preset threshold, a first user corresponding to the service process is determined in a second database configured by the server.

[0113] Specifically, to further improve the accuracy of service process prediction, second service data including the second user and the target service can also be determined based on the service process, but is not limited to this. This second service data can be understood as data obtained after performing feature process extraction on the service process. It is understood that a service process can be understood as a process that can be executed by a user with administrative privileges in the enterprise system. For example, but not limited to, an approval process for user xx to apply for xx product for xx transaction requires approval by a user with approval process management privileges in the enterprise system. The result of the user's approval process can be, but is not limited to, approval or rejection. Here, a service process can include at least two service parameters, such as user name, product type, service type, or service time. Taking the aforementioned service process as an example of an approval process for user xx to apply for xx product for xx transaction, the second service data determined from this service process can specifically be user xx applying for xx transaction (user xx can correspond to the second user, and xx transaction can correspond to the service type), or a framework statement containing user xx applying for xx transaction, but is not limited to this.

[0114] Then, after determining the second service data, you can, but are not limited to, refer to one or more of the above-mentioned embodiments to obtain the prediction results corresponding to the second service data. When it is detected that the prediction results corresponding to the first service data exceed the preset threshold, and the prediction results corresponding to the second service data exceed the preset threshold, it indicates that the prediction results of the decision tree model are more accurate, and then the first user corresponding to the service process can be determined in the second database configured by the server. I will not go into details here.

[0115] See next Figure 3 , Figure 3 A structural diagram of a process management device based on a decision tree model provided in an embodiment of the present application is shown.

[0116] like Figure 3 As shown, the process management device based on the decision tree model may include at least a first management module 301, a second management module 302, a third management module 303, a fourth management module 304 and a fifth management module 305, wherein:

[0117] The first management module 301 is configured to, upon receiving a service process distributed by a server, determine first service data including a target product and a target service according to the service process;

[0118] A second management module 302 is configured to determine first process parameters in a first database configured by the server based on the target product and the target service;

[0119] The third management module 303 is configured to obtain a prediction result corresponding to the first service data based on the target product, the target service, the first process parameter, and a preset decision tree model;

[0120] The fourth management module 304 is configured to determine a first user corresponding to the service process in a second database configured by the server when the prediction result corresponding to the first service data exceeds a preset threshold;

[0121] The fifth management module 305 is configured to allocate the service process to a target terminal corresponding to the first user so that the target terminal manages the service process and receive a management result fed back by the target terminal.

[0122] In some possible embodiments, determining the first process parameter in a first database configured by the server based on the target product and the target service includes:

[0123] Input the target product into a preset word embedding model to obtain a product set including the target product; wherein the product set includes at least two product types, and the preset word embedding model is trained by historical process data stored in the server;

[0124] Determining, in a first database configured by the server, product process parameters corresponding to all product types in the product set;

[0125] Inputting the target service into a preset word embedding model to obtain a service set including the target service; wherein the service set includes at least two service types;

[0126] The service process parameters corresponding to all service types in the service set are determined in the first database, and the product process parameters and the service process parameters are used as first process parameters.

[0127] In some possible embodiments, obtaining a prediction result corresponding to the first service data based on the target product, the target service, the first process parameter, and a preset decision tree model includes:

[0128] Input all product types and product process parameters in the product set into a preset decision tree model to obtain a first prediction result corresponding to each product type;

[0129] When it is detected that the number of identical first prediction results exceeds a preset number threshold, determining the first prediction result corresponding to the target product;

[0130] Input all service types and service process parameters in the service set into a preset decision tree model to obtain a second prediction result corresponding to each service type;

[0131] When it is detected that the number of identical second prediction results exceeds a preset number threshold, determining the second prediction result corresponding to the target service;

[0132] A weighted summation process is performed on the first prediction result and the second prediction result to obtain a prediction result corresponding to the first service data.

[0133] In some possible embodiments, determining the first user corresponding to the service process in a second database configured by the server includes:

[0134] In a second database configured by the server, a set of users having authority to manage the target service is sequentially determined;

[0135] The user set is randomly arranged, and a first user corresponding to the service process is determined from the processed user set.

[0136] In some possible embodiments, determining the first user corresponding to the service process in a second database configured by the server further includes:

[0137] Distributing a service flow management request to all corresponding user terminals in a second database configured by the server;

[0138] When confirmation requests fed back by at least two user terminals are received within a preset time interval, obtaining the management authority of each user terminal based on the second database;

[0139] When the management authority of any user terminal includes the authority to manage the target service, a first user corresponding to the service process is determined according to the user terminal.

[0140] In some possible embodiments, before determining the first user corresponding to the service process in the second database configured by the server, the method further includes:

[0141] Determining second service data including a second user and a target service according to the service process, and determining second process parameters in the first database based on the second user and the target service;

[0142] Obtaining a prediction result corresponding to the second service data according to the second user, the target service, the second process parameter, and a preset decision tree model;

[0143] Determining a first user corresponding to the service process in a second database configured by the server includes:

[0144] When the prediction result corresponding to the second service data exceeds a preset threshold, a first user corresponding to the service process is determined in a second database configured by the server.

[0145] In some possible embodiments, after receiving the management result fed back by the target terminal, the method further includes:

[0146] The service process, the first user corresponding to the service process, and the management result are updated to a preset management database, and the management information of the first user is obtained according to the updated preset management database.

[0147] Those skilled in the art will clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently perform or cooperate with other components to perform specific functions, where the hardware can be, for example, a field-programmable gate array (FPGA) or an integrated circuit (IC).

[0148] See next Figure 4 , Figure 4 A structural diagram of another process management device based on a decision tree model provided in an embodiment of the present application is shown.

[0149] like Figure 4 As shown, the process management device 400 based on the decision tree model may include at least one processor 401 , at least one network interface 404 , a user interface 403 , a memory 405 and at least one communication bus 402 .

[0150] The communication bus 402 may be used to implement connection and communication among the above components.

[0151] The user interface 403 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0152] The network interface 404 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, and the like.

[0153] The processor 401 may include one or more processing cores. The processor 401 utilizes various interfaces and circuits to connect the various components within the process management device 400 based on the decision tree model. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 405, and calling data stored in the memory 405, the processor 401 executes various functions and processes data of the process management device 400 based on the decision tree model. Optionally, the processor 401 may be implemented in at least one hardware form selected from DSP, FPGA, and PLA. The processor 401 may integrate one or a combination of a CPU, a GPU, and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 401 and may be implemented separately via a single chip.

[0154] Among them, the memory 405 may include RAM and may also include ROM. Optionally, the memory 405 includes a non-transitory computer-readable medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 405 may also be optionally at least one storage device located away from the aforementioned processor 401. As Figure 4 As shown, the memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a process management application based on a decision tree model.

[0155] Specifically, the processor 401 may be configured to call a process management application based on a decision tree model stored in the memory 405 and specifically perform the following operations:

[0156] When receiving the service process distributed by the server, determining first service data including the target product and the target service according to the service process;

[0157] Determining first process parameters in a first database configured by the server based on the target product and the target service;

[0158] Obtaining a prediction result corresponding to the first service data according to the target product, the target service, the first process parameter, and a preset decision tree model;

[0159] When the prediction result corresponding to the first service data exceeds a preset threshold, determining a first user corresponding to the service process in a second database configured by the server;

[0160] The service process is allocated to a target terminal corresponding to the first user, so that the target terminal manages the service process, and a management result fed back by the target terminal is received.

[0161] In some possible embodiments, determining the first process parameter in a first database configured by the server based on the target product and the target service includes:

[0162] Input the target product into a preset word embedding model to obtain a product set including the target product; wherein the product set includes at least two product types, and the preset word embedding model is trained by historical process data stored in the server;

[0163] Determining, in a first database configured by the server, product process parameters corresponding to all product types in the product set;

[0164] Inputting the target service into a preset word embedding model to obtain a service set including the target service; wherein the service set includes at least two service types;

[0165] The service process parameters corresponding to all service types in the service set are determined in the first database, and the product process parameters and the service process parameters are used as first process parameters.

[0166] In some possible embodiments, obtaining a prediction result corresponding to the first service data based on the target product, the target service, the first process parameter, and a preset decision tree model includes:

[0167] Input all product types and product process parameters in the product set into a preset decision tree model to obtain a first prediction result corresponding to each product type;

[0168] When it is detected that the number of identical first prediction results exceeds a preset number threshold, determining the first prediction result corresponding to the target product;

[0169] Input all service types and service process parameters in the service set into a preset decision tree model to obtain a second prediction result corresponding to each service type;

[0170] When it is detected that the number of identical second prediction results exceeds a preset number threshold, determining the second prediction result corresponding to the target service;

[0171] A weighted summation process is performed on the first prediction result and the second prediction result to obtain a prediction result corresponding to the first service data.

[0172] In some possible embodiments, determining the first user corresponding to the service process in a second database configured by the server includes:

[0173] In a second database configured by the server, a set of users having authority to manage the target service is sequentially determined;

[0174] The user set is randomly arranged, and a first user corresponding to the service process is determined from the processed user set.

[0175] In some possible embodiments, determining the first user corresponding to the service process in a second database configured by the server further includes:

[0176] Distributing a service flow management request to all corresponding user terminals in a second database configured by the server;

[0177] When confirmation requests fed back by at least two user terminals are received within a preset time interval, obtaining the management authority of each user terminal based on the second database;

[0178] When the management authority of any user terminal includes the authority to manage the target service, a first user corresponding to the service process is determined according to the user terminal.

[0179] In some possible embodiments, before determining the first user corresponding to the service process in the second database configured by the server, the method further includes:

[0180] Determining second service data including a second user and a target service according to the service process, and determining second process parameters in the first database based on the second user and the target service;

[0181] Obtaining a prediction result corresponding to the second service data according to the second user, the target service, the second process parameter, and a preset decision tree model;

[0182] Determining a first user corresponding to the service process in a second database configured by the server includes:

[0183] When the prediction result corresponding to the second service data exceeds a preset threshold, a first user corresponding to the service process is determined in a second database configured by the server.

[0184] In some possible embodiments, after receiving the management result fed back by the target terminal, the method further includes:

[0185] The service process, the first user corresponding to the service process, and the management result are updated to a preset management database, and the management information of the first user is obtained according to the updated preset management database.

[0186] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0187] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0188] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0189] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0190] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0191] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0192] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

Claims

1. A process management method based on a decision tree model, characterized in that: include: When receiving a service process distributed by the server, determining first service data including a target product and a target service according to the service process; Determining first process parameters in a first database configured by the server based on the target product and the target service; Obtaining a prediction result corresponding to the first service data according to the target product, the target service, the first process parameter, and a preset decision tree model; When the prediction result corresponding to the first service data exceeds a preset threshold, determining a first user corresponding to the service process in a second database configured by the server; The service process is allocated to a target terminal corresponding to the first user, so that the target terminal manages the service process, and a management result fed back by the target terminal is received.

2. The method according to claim 1, characterized in that The determining, based on the target product and the target service, a first process parameter in a first database configured by the server includes: Inputting the target product into a preset word embedding model to obtain a product set including the target product; wherein the product set includes at least two product types, and the preset word embedding model is trained by historical process data stored in the server; Determining, in a first database configured by the server, product process parameters corresponding to all product types in the product set; Inputting the target service into the preset word embedding model to obtain a service set including the target service; wherein the service set includes at least two service types; The service process parameters corresponding to all service types in the service set are determined in the first database, and the product process parameters and the service process parameters are used as first process parameters.

3. The method according to claim 2, characterized in that Obtaining a prediction result corresponding to the first service data based on the target product, the target service, the first process parameter, and a preset decision tree model includes: Inputting all product types in the product set and the product process parameters into a preset decision tree model to obtain a first prediction result corresponding to each product type; When it is detected that the number of identical first prediction results exceeds a preset number threshold, determining the first prediction result corresponding to the target product; Inputting all service types in the service set and the service process parameters into the preset decision tree model to obtain a second prediction result corresponding to each service type; When it is detected that the number of the same second prediction results exceeds the preset number threshold, determining the second prediction result corresponding to the target service; A weighted summation process is performed on the first prediction result and the second prediction result to obtain a prediction result corresponding to the first service data.

4. The method according to claim 1, wherein The determining, in a second database configured by the server, a first user corresponding to the service process, includes: In a second database configured by the server, a set of users having authority to manage the target service is sequentially determined; The user set is randomly arranged, and a first user corresponding to the service process is determined from the processed user set.

5. The method according to claim 1, wherein The determining, in a second database configured by the server, a first user corresponding to the service process, includes: Distributing a management request for the service process to all corresponding user terminals in a second database configured by the server; When confirmation requests fed back by at least two user terminals are received within a preset time interval, obtaining the management authority of each of the user terminals based on the second database; When the management authority of any one of the user terminals includes the authority to manage the target service, a first user corresponding to the service process is determined according to the user terminal.

6. The method according to claim 1, characterized in that Before determining the first user corresponding to the service process in the second database configured by the server, the method further includes: determining second service data including a second user and the target service according to the service process, and determining second process parameters in the first database based on the second user and the target service; Obtaining a prediction result corresponding to the second service data according to the second user, the target service, the second process parameter, and the preset decision tree model; The determining, in a second database configured by the server, a first user corresponding to the service process, includes: When the prediction result corresponding to the second service data exceeds the preset threshold, a first user corresponding to the service process is determined in a second database configured by the server.

7. The method according to claim 1, characterized in that After receiving the management result fed back by the target terminal, the method further includes: The service process, the first user corresponding to the service process, and the management result are updated to a preset management database, and management information of the first user is obtained according to the updated preset management database.

8. A process management device based on a decision tree model, characterized in that: include: A first management module is configured to, upon receiving a service process distributed by a server, determine first service data including a target product and a target service according to the service process; a second management module, configured to determine a first process parameter in a first database configured by the server based on the target product and the target service; a third management module, configured to obtain a prediction result corresponding to the first service data based on the target product, the target service, the first process parameter, and a preset decision tree model; a fourth management module, configured to determine, in a second database configured by the server, a first user corresponding to the service process when a prediction result corresponding to the first service data exceeds a preset threshold; The fifth management module is configured to allocate the service process to a target terminal corresponding to the first user, so that the target terminal manages the service process, and receive a management result fed back by the target terminal.

9. A process management device based on a decision tree model, characterized in that: including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Images