Business process information prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a business process information prediction method and device, electronic equipment and a storage medium, belongs to the technical field of process monitoring and prediction, and is used for solving the problem of low prediction accuracy of a related business process information prediction technology. The method comprises the following steps: acquiring historical business process processing data; wherein the historical business process processing data is related data for processing the business process in a business system by a user; based on the historical business process processing data, determining a similar user set corresponding to a target user through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation conditions with respect to the business process; on the basis of the historical business process processing data corresponding to the similar user set, business process information is obtained through prediction; wherein the business process information is information related to processing of the business process by a target user.

Description

Technical Field

[0001] The present application belongs to the technical field of business process management, and specifically relates to a method, device, electronic device and storage medium for predicting business process information. Background Art

[0002] Nowadays, Business Process Management (BPM) is widely used, especially the rapid development of big data has laid the foundation for the development of business process management. Business process refers to the standardization, optimization and automation of the workflow of an enterprise or organization to achieve efficient, smooth and sustainable development of work. By analyzing historical process log data, business process mining technology can extract valuable knowledge. The use of this knowledge can not only improve work efficiency and quality, but also reduce risks, improve employee satisfaction, etc., thereby promoting the sustainable development and innovation of enterprises or organizations.

[0003] Predictive monitoring of business processes is one of the subfields of business process mining. By predicting the quantifiable indicators of the process instances being executed, timely information is provided to relevant personnel so that proactive corrective measures can be taken to improve process performance and reduce process risks. At the same time, the predicted results of business processes (information) can help enterprises improve the performance indicators of related businesses. Predicting business process information can provide useful information to relevant personnel. For example, by predicting the remaining time of the process, the priority of the process instance execution can be adjusted according to the remaining time of the process to avoid the execution of some process instances exceeding their deadlines.

[0004] The prediction technology of related business process information generally determines the business process similar to the business process to be predicted, and then predicts the business process according to the historical business process processing data corresponding to the similar business process, so as to obtain the business process information of the business process to be predicted. However, since it does not take into account the influence of different users on the processing of business processes, the prediction results of related business process prediction technology are less accurate.

[0005] In other words, the prediction technology of relevant business process information has the problem of low prediction accuracy. Summary of the invention

[0006] The embodiments of the present application provide a method, device, electronic device and storage medium for predicting business process information, which can solve the problem of low prediction accuracy in related business process prediction technologies.

[0007] In a first aspect, an embodiment of the present application provides a method for predicting business process information, the method comprising: obtaining historical business process processing data; wherein the historical business process processing data is relevant data of the user's processing of the business process in the business system; based on the historical business process processing data, determining a set of similar users corresponding to a target user through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; based on the historical business process processing data corresponding to the similar user set, predicting business process information; wherein the business process information is information related to the target user's processing of the business process.

[0008] In a second aspect, an embodiment of the present application provides a method for predicting a web page, the method comprising: obtaining historical business process processing data in a business system, historical data of a user's web page click stream, and a current web page of a target user; wherein the historical business process processing data is relevant data of a user's processing of a business process in the business system; based on the historical business process processing data, a set of similar users corresponding to the target user is determined through a pre-trained prediction model; wherein the users in the similar user set have similar participation in the business process as the target user; based on the next web page corresponding to the current web page in the historical data of the web page click stream corresponding to the similar user set, the next web page that the target user needs to visit is predicted, so as to display the next web page that the target user needs to visit to the target user.

[0009] In a third aspect, an embodiment of the present application provides a device for predicting business process information, the device comprising: an acquisition module for acquiring historical business process processing data; wherein the historical business process processing data is relevant data of the user processing the business process in the business system; a determination module for determining a set of similar users corresponding to a target user based on the historical business process processing data through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; a prediction module for predicting business process information based on the historical business process processing data corresponding to the similar user set; wherein the business process information is information related to the target user processing the business process.

[0010] In a fourth aspect, an embodiment of the present application provides a web page prediction device, the device comprising: a data acquisition module, used to acquire historical business process processing data in a business system, historical data of web page click streams of users, and current web page of a target user; wherein the historical business process processing data is relevant data of the user processing the business process in the business system; a set determination module, used to determine a set of similar users corresponding to the target user based on the historical business process processing data through a pre-trained prediction model; wherein the users in the similar user set have similar participation in the business process as the target user; a web page prediction module, used to predict the next web page that the target user needs to visit based on the next web page corresponding to the current web page in the historical data of web page click streams corresponding to the similar user set, so as to display the next web page that the target user needs to visit to the target user.

[0011] In a fifth aspect, an embodiment of the present application provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions are configured to be executed by the processor, and the executable instructions include instructions for executing a method for predicting business process information as described in the first aspect, or executing a method for predicting a web page as described in the second aspect.

[0012] In a sixth aspect, an embodiment of the present application provides a storage medium, which is used to store computer-executable instructions, and the computer-executable instructions enable a computer to execute the method for predicting business process information as described in the first aspect, or to execute the method for predicting a web page as described in the second aspect.

[0013] In the seventh aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the business process information prediction method as described in the first aspect, or to execute the web page prediction method as described in the second aspect.

[0014] In an eighth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for predicting business process information as described in the first aspect, or executes the method for predicting a web page as described in the second aspect.

[0015] In an embodiment of the present application, historical business process processing data is obtained; wherein the historical business process processing data is relevant data on the user's processing of the business process in the business system; based on the historical business process processing data, a similar user set corresponding to the target user is determined through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; then based on the historical business process processing data corresponding to the similar user set, business process information is predicted; wherein the business process information is information related to the target user's processing of the business process. Compared with the prediction technology of related business process information, which only predicts based on the corresponding historical business process processing data of similar business processes to obtain the business process information of the business process to be predicted, the present application determines the users whose participation in the business process is similar to that of the target user, that is, the set of similar users corresponding to the target user, through a pre-trained prediction model, and then predicts the business process information based on the historical business process processing data corresponding to the similar user set, thereby generating corresponding prediction results (business process information) for different users processing business processes, taking into account the personalized characteristics of the target users, and realizing personalized prediction services for the target users, so that the prediction results are more accurately fitted to the target users, thereby improving the accuracy of the predicted business process information, and solving the problem of low prediction accuracy of the prediction technology of related business process information. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of a method for predicting business process information provided by an embodiment of the present application; Figure 2 It is a flowchart of another method for predicting business process information provided by an embodiment of the present application; Figure 3 A schematic diagram of a flow chart of a web page prediction method provided in an embodiment of the present application; Figure 4 It is a structural diagram of a business process information prediction device provided in an embodiment of the present application; Figure 5 It is a structural schematic diagram of a web page prediction device provided in an embodiment of the present application; Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0019] The following, in conjunction with the accompanying drawings, describes in detail the business process information prediction method, device, electronic device and storage medium provided by the embodiments of the present application through specific embodiments and their application scenarios.

[0020] Figure 1 A method for predicting business process information provided by an embodiment of the present invention is shown. The method can be executed by an electronic device, and the electronic device may include: a server and / or a terminal device, wherein the terminal device may be, for example, a vehicle-mounted terminal or a mobile phone terminal. In other words, the method can be executed by software or hardware installed in the electronic device, and the method includes the following steps: S102: Acquire historical business process processing data.

[0021] The historical business process processing data refers to the data related to the user's processing of the business process in the business system.

[0022] In actual applications, the historical business process processing data can be obtained from the process log data recorded in the background of the business system.

[0023] S104: Based on the historical business process processing data, a similar user set corresponding to the target user is determined through a pre-trained prediction model.

[0024] Among them, the users in the similar user set and the target user have similar participation in the business process.

[0025] The users in the similar user set and the target user have similar participation in the business process, that is, the users in the similar user set and the target user have similar work scopes.

[0026] Specifically, the business process participation status may be related to the business process in which the user participates and the time of participating in the business process.

[0027] S106: Based on the historical business process processing data corresponding to the similar user set, business process information is predicted.

[0028] The business process information is information related to the business process of the target user.

[0029] The target user is any user in the business system.

[0030] Optionally, the business process information may include but is not limited to the total process running time, remaining process time, decision passing information of the decision nodes of the business process processed by the target user, and evaluation information of the process nodes of the business process processed by the target user.

[0031] It should be noted that the business process information may also be other information related to the business process of the target user, and is not limited to the information listed above.

[0032] Optionally, it is possible to pre-set a prediction of one business process information or multiple business process information, and predict the one business process information or multiple business process information each time; considering that only predicting a certain business process information does not meet the needs of some users, and predicting multiple business process information each time may include business process information that the user does not need, thereby resulting in a waste of computing resources, therefore, multiple prediction tasks can also be pre-set, and the user selects the prediction task to obtain the target prediction task, or the target prediction task is automatically triggered by monitoring the page in the business system, and then the corresponding prediction is performed according to the target prediction task. Specifically, S102 can be executed as follows: obtaining the target prediction task indicating the predicted business process information; obtaining the historical business process processing data corresponding to the target prediction task; correspondingly, S106 can be executed as follows: based on the historical business process processing data corresponding to the target prediction task corresponding to the similar user set, predicting the business process information corresponding to the target prediction task; wherein the target prediction task includes but is not limited to the first prediction task, the second prediction task, the third prediction task and the fourth prediction task, etc. The first prediction task indicates the total process running time of the business process processed by the predicted target user; the second prediction task indicates the remaining process time of the business process processed by the predicted target user; the third prediction task indicates the decision passing information of the decision node of the business process processed by the predicted target user; the fourth prediction task indicates the evaluation information of the process node of the business process processed by the predicted target user.

[0033] The method for predicting business process information provided by an embodiment of the present invention obtains historical business process processing data; wherein the historical business process processing data is related data on the user's processing of the business process in the business system; based on the historical business process processing data, a similar user set corresponding to the target user is determined through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; and then based on the historical business process processing data corresponding to the similar user set, business process information is predicted; wherein the business process information is information related to the target user's processing of the business process. Compared with the prediction technology of related business process information, which only predicts based on the corresponding historical business process processing data of similar business processes to obtain the business process information of the business process to be predicted, the present application determines the users whose participation in the business process is similar to that of the target user, that is, the set of similar users corresponding to the target user, through a pre-trained prediction model, and then predicts the business process information based on the historical business process processing data corresponding to the similar user set, thereby generating corresponding prediction results (business process information) for different users processing business processes, taking into account the personalized characteristics of the target users, and realizing personalized prediction services for the target users, so that the prediction results are more accurately fitted to the target users, thereby improving the accuracy of the predicted business process information, and solving the problem of low prediction accuracy of the prediction technology of related business process information.

[0034] In one implementation, based on historical business process processing data, a similar user set corresponding to the target user is determined through a pre-trained prediction model (ie, S104), and the following steps A1 to A2 may be specifically performed: Step A1, based on the historical business process processing data, the historical business process processing data is processed through the pre-trained prediction model to obtain the process participation matrix.

[0035] The elements in the process participation matrix are determined based on the business processes in which the user participates and the time of participating in the business processes, and are used to characterize the user's participation in the business process.

[0036] In actual applications, historical business process processing data may include the business processes in which users participated and the time of participating in the business processes. For example, user A processed process node a of business process 1 on January 1, 2024. Specifically, historical business process processing data may include, but is not limited to, one or more of the following: user identity document (ID), business process ID, timestamp (i.e., time of participating in the business process), process node ID, and information about user operations on the business process; wherein, information about user operations on the business process includes one or more of the following: information about user operations and type information of user operations (e.g., the first type of information of selecting consent or the second type of information of disapproval at the decision node).

[0037] Exemplarily, the process participation matrix may include user dimension and business process dimension, m rows represent m users, n columns represent n business processes, and the element UP (i, j) in the i-th row and j-th column represents the participation of user i in business process j. The m and n are determined according to the number of users and the number of business processes in the historical business process processing data, respectively, and are not specifically limited. The process participation matrix is ​​shown in the following table:

[0038] Step A2, through the pre-trained prediction model, determine the similarity between the element corresponding to the target user in the process participation matrix and the element corresponding to the user other than the target user in the process participation matrix, and obtain the similar user set of the target user based on the similarity and preset conditions.

[0039] Optionally, the preset condition may be that the similarity is greater than a first preset threshold, in which case the similar user set includes users whose similarity is greater than the first preset threshold; the preset condition may also be a preset number, in which case the users are sorted in descending order according to their corresponding similarities to obtain a queue of corresponding users, and the similar user set includes the preset number of users selected from the head of the queue.

[0040] In this embodiment, the pre-trained prediction model is used to achieve: constructing a matrix of historical business process processing data to obtain a process participation matrix, and mining the nearest neighbors based on the process participation matrix. This enables a more accurate set of similar users of the target user to be obtained (users in the similar user set have similar participation in the business process as the target user).

[0041] In one implementation, the historical business process processing data (ie, S106) may be obtained by specifically performing the following step B1: Step B1, obtaining historical business process processing data within a preset time range.

[0042] Optionally, the preset time range may be a fixed preset value, or may be a time range customized by the user.

[0043] Exemplarily, the preset time range may be 12 months, and relevant data on the user's processing of the business process in the business system in the most recent year is obtained. It should be noted that the preset time range is only an example and does not constitute a specific limitation on the preset time range.

[0044] Based on the historical business process processing data, the historical business process processing data is processed through the pre-trained prediction model to obtain the process participation matrix (i.e. step A1), which can be specifically executed as steps a1 to a2: Step a1: Use the pre-trained prediction model to process data based on historical business processes and determine the frequency factor and timeliness factor.

[0045] Among them, the frequency factor is the number of times the user participates in the business process within the preset time period, and the timeliness factor is determined based on the preset time period to which the time point when the user participates in the business process belongs, the current preset time period, and the preset time period to which the start time of the preset time range of historical business process processing data belongs.

[0046] Specifically, the preset time range includes one or more preset time periods.

[0047] Step a2, determining elements based on the frequency factor and the timeliness factor to determine a process participation matrix including a plurality of elements.

[0048] Exemplarily, the preset time period may be one month, and the frequency factor F(i, j, t) is the number of times user i participates in business process j in month t. Wherein, t represents the month in which user i participates in business process j. Specifically, t may be the month in which user i completes processing of business process j.

[0049] It should be noted that if the pending tasks of a business process remain under the account of user i and have not been processed, they will not be counted in the count of the number of times the user has participated in the business process. In addition, as long as the user has participated in any process node in the business process (including the initiating node and the process node in the process), he can be regarded as having participated in the business process. If the same business process flows through user i multiple times, for example, user i submits the business process to the next process node and is rejected, and returns to the process node where user i is located, the number of times the user has participated in the business process is still counted as 1, and the number of times the user has participated in the business process is not repeated.

[0050] Continuing with the above example, the time factor can be calculated by the following formula based on the preset time period to which the user participates in the business process, the current preset time period, and the preset time period to which the start time of the preset time range of the historical business process processing data belongs. :

[0051] Among them, T0 is the month of the start time of the preset time range of historical business process processing data; T1 is the current month. The numerator and denominator are added by 1 to prevent the numerator or denominator from being equal to 0. It can be seen that the later the user participates in the business process, the stronger the timeliness of the data and the greater the timeliness factor.

[0052] In practical applications, the element may be determined by using a frequency factor and a timeliness factor corresponding to one or more preset time periods.

[0053] Continuing with the above example, based on the frequency factor and timeliness factor corresponding to the preset time period included in the preset time range, the element UP (i, j) of user i for business process j is determined as follows: =

[0054] Wherein, Z represents all months within the above preset time range.

[0055] By determining the elements of each user for each business process corresponding to the historical business process processing data, a process participation matrix including multiple elements is obtained.

[0056] Since the element UP (i, j) represents the participation of user i in business process j, if the element of a user for a business process is 0 (or an empty element value), it means that the user does not participate in the business process.

[0057] For example, the above-mentioned pre-trained prediction model is used to determine the similarity between the element corresponding to the target user in the process participation matrix and the element corresponding to the user other than the target user in the process participation matrix (i.e., step B2). Correlation can be used to measure the similarity between users. The similarity calculation formula can be as follows:

[0058] in, A set of elements representing a business process in which user i and user j participate together; , Respectively represent the participation of user i and user j in business process k; , represents the average participation of user i and user j respectively, and the average value of all non-zero elements corresponding to user i is taken as ; Take the average value of all non-zero elements corresponding to user j as .

[0059] It should be noted that the similarity algorithm preset in the above-mentioned pre-trained prediction model is only an example, and other similarity algorithms may also be preset. Therefore, the similarity algorithm is not specifically limited.

[0060] In this embodiment, by introducing the frequency factor and the timeliness factor, the user's participation in the business process can be determined more accurately, so that the similar user set corresponding to the target user output by the pre-trained prediction model is more accurate.

[0061] In one implementation, the business process information includes the total process running time of the business process processed by the target user; wherein the total process running time is the time from the initiation of the business process to the completion of the processing; the acquisition of historical business process processing data (ie, S102) can be specifically performed as follows: step C1: Step C1, obtaining historical business process processing data including the total process running time of the business process processed by the user.

[0062] The above-mentioned prediction of business process information based on the historical business process processing data corresponding to the similar user set (ie, S106) can be specifically performed as the following step C2: Step C2, based on the total process running time corresponding to the similar user set, determine the total process running time of the business process processed by the target user.

[0063] Specifically, the average value of the total process running time corresponding to the similar user set is determined as the prediction result of the total process running time of the business process processed by the target user.

[0064] In this embodiment, by predicting the total process running time of the business process handled by the target user, it helps the process participants to accurately grasp the next operation trend of the business process, guide the daily business development in a targeted manner, improve the efficiency of business process execution, and provide decision support for business process managers.

[0065] In one implementation, the business process information includes the remaining time of the business process processed by the target user; wherein the remaining time is the time from the current process node to the completion of the business process processing; the acquisition of historical business process processing data (i.e., S102) can be specifically performed as follows: step D1: Step D1, obtaining historical business process processing data including the remaining time of the business process processed by the user.

[0066] The above-mentioned prediction of business process information based on the historical business process processing data corresponding to the similar user set (ie, S106) can be specifically performed as the following step D2: Step D2, based on the process remaining time corresponding to the similar user set, determine the process remaining time of the business process processed by the target user.

[0067] Specifically, an average value of the remaining time of the process corresponding to the similar user set is determined as a prediction result of the remaining time of the process of the business process processed by the target user.

[0068] In this embodiment, by predicting the remaining time of the business process handled by the target user, it helps the process participants to accurately grasp the next operation trend of the business process, guide the daily business development in a targeted manner, improve the efficiency of business process execution, and provide decision support for business process managers.

[0069] In one implementation, the business process information includes decision passing information of a decision node of a business process processed by a target user; wherein the decision passing information includes the probability of the business process being approved at the decision node, and / or target reason information of the business process not being approved at the decision node; the above-mentioned acquisition of historical business process processing data (i.e., S102) may be specifically performed as the following step E1: Step E1, when the next process node of the current process node is a decision node, obtain historical business process processing data including decision information of the business process processed by the user.

[0070] The decision information includes approval result information indicating whether the business process is approved at the decision node, and / or reason information indicating why the business process is not approved at the decision node.

[0071] In actual applications, reason information representing the reason why the business process was not approved at the decision node can be set in advance at the decision node of the business system for users to choose. Then, the background of the business system can record data related to the reason information of the business process processed by the user, and accordingly, historical business process processing data that also includes the reason information of the business process processed by the user can be obtained.

[0072] The above-mentioned prediction of business process information based on the historical business process processing data corresponding to the similar user set (ie, S106) can be specifically performed as the following step E2: Step E2, based on the decision information corresponding to the similar user set, determine the decision passing information of the decision node of the business process processed by the target user, so as to provide the decision passing information to the target user.

[0073] Specifically, the number of target approval result information corresponding to the similar user set can be divided by the total number of approval result information corresponding to the similar user set to obtain the probability that the business process is approved at the decision node, and use it as the decision passing information of the decision node of the business process processed by the target user. The target approval result information represents the approval result information of the business process being approved at the decision node; the reason information corresponding to the similar user set can be sorted in descending order according to the frequency of occurrence to determine the target reason information of the business process not being approved at the decision node. The target reason information is a preset number of reason information, or reason information with a frequency of occurrence greater than a second preset threshold.

[0074] Exemplarily, when the target user i processes a process node a of a business process q instance, it is assumed that the next process node b of a is a decision node (for example, process node b is a leadership review node, which may or may not be approved). Determine the similar user set of the target user i, calculate the probability that the business process q instance participated by all users in the similar user set is approved at the decision node b, and provide it to the target user i as the decision pass information corresponding to the decision node b. Furthermore, if a rejection reason enumeration value (reason information representing the reason why the business process was not approved at the decision node) is pre-set at the process decision node b for the user to choose, then the rejection reason enumeration value options at the decision node b of the business process q instance participated by all users corresponding to the similar user set can be counted, arranged in descending order according to the frequency of occurrence, and provided to the target user i.

[0075] In this embodiment, by predicting the decision passing information corresponding to the decision node to be processed by the target user (the probability of the business process being approved at the decision node), it helps the process participants to accurately grasp the next operation trend of the business process, can guide the daily business development in a targeted manner, improve the efficiency of business process execution, and provide decision support for business process managers. Furthermore, predicting the decision passing information corresponding to the decision node to be processed (the target reason information of the business process not being approved at the decision node) and providing the target reason information to the target user can enable the target user to see the target reason information of the business process not being approved at the decision node, avoid it in advance, thereby improving the passing rate at the decision node b, avoiding repeated rejection and modification, and then improving the overall efficiency of the business process and shortening the process running time of the business.

[0076] In one implementation, the business process information includes evaluation information of process nodes of the business process processed by the target user; wherein the evaluation information is used to characterize the relationship between the process node processing time corresponding to the target user and the average value of the process node processing time corresponding to the similar user set; the acquisition of historical business process processing data (i.e., S102) can be specifically performed as the following step F1: Step F1, obtaining historical business process processing data including process node processing time of process nodes of business processes processed by users.

[0077] The process node processing time is the time from the arrival of the process node to the completion of the process node processing.

[0078] The above-mentioned prediction of business process information based on the historical business process processing data corresponding to the similar user set (ie, S106) can be specifically performed as the following step F2: Step F2, based on the process node processing time corresponding to the similar user set, determine the evaluation information of the process node of the target user processing the business process.

[0079] In practical applications, the average value of the process node processing time corresponding to the similar user set is first determined; then the relationship between the process node processing time corresponding to the target user and the average value is determined to obtain the evaluation information of the process node of the business process processed by the target user. Specifically, if the process node processing time corresponding to the target user is greater than the average value, it is determined that the process node of the business process processed by the target user is below the average level, that is, it is processed slower than the average level, thereby determining the corresponding evaluation information; if the process node processing time corresponding to the target user is less than the average value, it is determined that the process node of the business process processed by the target user is above the average level, that is, it is processed faster than the average level, thereby determining the corresponding evaluation information.

[0080] Optionally, the evaluation information may be information representing the difference between the process node processing time corresponding to the target user and the average value, or evaluation information comparing the target user's average processing level, or other information related to the relationship between the process node processing time corresponding to the target user and the average value, without specific limitation.

[0081] In this embodiment, by predicting the evaluation information of the process nodes of the target user's business process processing, the process processing efficiency of the target user can be intuitively reflected, which reflects the work efficiency of the target user to a certain extent and can be used as an evaluation method to measure the "process execution performance" of the target user.

[0082] Figure 2 FIG. 1 is a flow chart of another method for predicting business process information provided by an embodiment of the present application. Figure 2As shown, the method includes: Step 202: Acquire historical business process processing data within a preset time range.

[0083] The historical business process processing data refers to the data related to the user's processing of the business process in the business system. The historical business process processing data may include, but is not limited to, the business process in which the user participated and the time of participating in the business process, as well as one or more of the following: The total process running time of the business processes handled by the user; The remaining time of the business process handled by the user; Decision information about the business processes handled by users; Process node processing time of the process node of the business process that the user processes.

[0084] The total process running time is the time from the initiation to the completion of the business process processing; the remaining time of the process is the time from the current process node to the completion of the business process processing; the decision information includes the approval result information indicating whether the business process is approved at the decision node, and / or the reason information indicating why the business process is not approved at the decision node; the process node processing time is the time from the arrival of the process node to the completion of the process node processing.

[0085] Step 204 , using the pre-trained prediction model, based on historical business process processing data, determines the frequency factor and timeliness factor.

[0086] Among them, the frequency factor is the number of times the user participates in the business process within the preset time period, and the timeliness factor is determined based on the preset time period to which the time point when the user participates in the business process belongs, the current preset time period, and the preset time period to which the start time of the preset time range of historical business process processing data belongs.

[0087] Step 206 , determining elements based on the frequency factor and the timeliness factor through the pre-trained prediction model to determine a process participation matrix including multiple elements.

[0088] The elements in the process participation matrix are used to represent the user's participation in the business process.

[0089] Step 208, using the pre-trained prediction model, determines the similarity between the element corresponding to the target user in the process participation matrix and the element corresponding to users other than the target user in the process participation matrix, and obtains a set of similar users of the target user based on the similarity and preset conditions.

[0090] Step 210: predicting and obtaining business process information based on the historical business process processing data corresponding to the similar user set.

[0091] Among them, the business process information is information related to the business process processed by the target user. The business process information may include, but is not limited to, one or more of the following: the total process running time of the business process processed by the target user, the remaining process time, and the decision passing information of the decision node of the business process processed by the target user, and the evaluation information of the process node of the business process processed by the target user. The decision passing information includes the probability of the business process being approved at the decision node, and / or the target reason information of the business process not being approved at the decision node; the evaluation information is used to characterize the relationship between the process node processing time corresponding to the target user and the average value of the process node processing time corresponding to the set of similar users.

[0092] The specific process from step 202 to step 210 has been described in detail in the above embodiment and will not be repeated here.

[0093] In this embodiment, historical business process processing data is obtained; wherein the historical business process processing data is related data on user processing of business processes in a business system; based on the historical business process processing data, a similar user set corresponding to a target user is determined through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; then based on the historical business process processing data corresponding to the similar user set, business process information is predicted; wherein the business process information is information related to the target user processing the business process. Compared with the prediction technology of related business process information, which only predicts based on the corresponding historical business process processing data of similar business processes to obtain the business process information of the business process to be predicted, the present application determines the users whose participation in the business process is similar to that of the target user, that is, the set of similar users corresponding to the target user, through a pre-trained prediction model, and then predicts the business process information based on the historical business process processing data corresponding to the similar user set, thereby generating corresponding prediction results (business process information) for different users processing business processes, taking into account the personalized characteristics of the target users, and realizing personalized prediction services for the target users, so that the prediction results are more accurately fitted to the target users, thereby improving the accuracy of the predicted business process information, and solving the problem of low prediction accuracy of the prediction technology of related business process information.

[0094] Corresponding to the above Figure 1 to Figure 2 The business process information prediction method described above is based on the same technical concept. The embodiment of the present application also provides a web page prediction method. Figure 3This is a flow chart of a webpage prediction method provided in an embodiment of the present application. The method can be executed by an electronic device, wherein the electronic device may include: a server and / or a terminal device, wherein the terminal device may be, for example, a vehicle-mounted terminal or a mobile phone terminal. In other words, the method can be executed by software or hardware installed in the electronic device, and the method includes the following steps: S302: Acquire historical business process processing data in the business system, historical data of user's web page click stream, and current web page of the target user.

[0095] The historical business process processing data refers to the data related to the user's processing of the business process in the business system.

[0096] Specifically, the historical business process processing data may include, but is not limited to, the business processes in which the user participated and the time of participating in the business processes.

[0097] The target user is any one of the above users who is currently accessing the web page.

[0098] S304: Based on the historical business process processing data, a similar user set corresponding to the target user is determined through a pre-trained prediction model.

[0099] Among them, the users in the similar user set and the target user have similar participation in the business process.

[0100] In one implementation, S304 can be specifically executed as steps G1 to G2: Step G1, based on historical business process processing data, the historical business process processing data is processed through a pre-trained prediction model to obtain a process participation matrix; wherein the elements in the process participation matrix are determined based on the business processes in which the user participates and the time of participating in the business processes, and are used to characterize the user's participation in the business process; the historical business process processing data includes the business processes in which the user participates and the time of participating in the business process; Step G2, through a pre-trained prediction model, determine the similarity between the elements corresponding to the target user in the process participation matrix and the elements corresponding to users other than the target user in the process participation matrix, and obtain a set of similar users of the target user based on the similarity and preset conditions.

[0101] In one implementation, the historical business process processing data obtained in S302 is the historical business process processing data within a preset time range; step G1 can be specifically performed as follows: determining a frequency factor and a time factor based on the historical business process processing data through a pre-trained prediction model; wherein the frequency factor is the number of times a user participates in a business process within a preset time period, and the time factor is determined based on the preset time period to which the time point at which the user participates in the business process belongs, the current preset time period, and the preset time period to which the start time of the preset time range of the historical business process processing data belongs; determining elements based on the frequency factor and the time factor to determine a process participation matrix including multiple elements.

[0102] It should be noted that the historical business process processing data and the specific process of step S304 have been described in detail in the embodiment of the business process information prediction method described above, and will not be repeated here.

[0103] S306: Based on the next web page corresponding to the current web page in the web page click stream history data corresponding to the similar user set, the next web page that the target user needs to visit is predicted, so as to display the next web page that the target user needs to visit to the target user.

[0104] Specifically, there is no specific limit on the number of web pages included in the next web page that the target user needs to visit, and it can be one or more. The display form can be displayed in the form of a hyperlink or in other forms, and there is no specific limit on this. For example, when target user i is visiting a web page h, search for a similar user set corresponding to target user i, analyze the web page click stream history data of all users in the similar user set, filter out the web page click stream history data containing web page h, count the occurrence frequency of the next web page visited by these users after visiting web page h (i.e., the next web page), sort these next web pages in descending order of occurrence frequency, and recommend them to target user i as the web pages that target user i may visit next. For example, display "web pages you may want to visit next" in the current web page h, and display the top three web pages with the highest occurrence frequency as hyperlinks, so that users can directly enter the web page after clicking the hyperlink.

[0105] In this embodiment, by obtaining historical business process processing data in the business system, historical data of user's webpage click stream and current webpage of the target user; wherein the historical business process processing data is the relevant data of the user's processing of the business process in the business system; based on the historical business process processing data, the similar user set corresponding to the target user is determined through the pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; based on the next webpage corresponding to the current webpage in the webpage click stream historical data corresponding to the similar user set, the next webpage that the target user needs to visit is predicted, so as to display the next webpage that the target user needs to visit to the target user. This helps users to achieve quick access, reduce redundant webpage access paths, reduce the number of user clicks, improve user access efficiency, and enhance user experience.

[0106] Corresponding to the business process information prediction method provided in the above embodiment, based on the same technical concept, the embodiment of the present invention also provides a business process information prediction device. Figure 4 is a schematic diagram of the structure of a business process information prediction device according to an embodiment of the present invention, wherein the business process information prediction device is used to perform Figure 1 to Figure 2 Describe the prediction method of business process information, such as Figure 4 As shown, the prediction device for business process information includes: an acquisition module 410 , a determination module 420 and a prediction module 430 .

[0107] The acquisition module 410 is used to acquire historical business process processing data.

[0108] The historical business process processing data refers to the data related to the user's processing of the business process in the business system.

[0109] The determination module 420 is used to process data based on historical business processes and determine a set of similar users corresponding to the target user through a pre-trained prediction model.

[0110] Among them, the users in the similar user set and the target user have similar participation in the business process.

[0111] The prediction module 430 is used to predict the business process information based on the historical business process processing data corresponding to the similar user set.

[0112] The business process information is information related to the business process of the target user.

[0113] In one implementation, the determination module 420 includes: The matrix unit is used to process the historical business process processing data based on the historical business process processing data through the pre-trained prediction model to obtain the process participation matrix.

[0114] The elements in the process participation matrix are determined based on the business processes in which the user participates and the time of participating in the business processes, and are used to characterize the user's participation in the business process; the historical business process processing data includes the business processes in which the user participates and the time of participating in the business process.

[0115] The set determination unit is used to determine the similarity between the elements corresponding to the target user in the process participation matrix and the elements corresponding to users other than the target user in the process participation matrix through a pre-trained prediction model, and obtain a similar user set of the target user based on the similarity and preset conditions.

[0116] In one implementation, the acquisition module 410 is specifically configured to: Get historical business process processing data within a preset time range.

[0117] The matrix unit is specifically used for: Through pre-trained prediction models, data is processed based on historical business processes to determine frequency factors and timeliness factors; Among them, the frequency factor is the number of times the user participates in the business process within the preset time period, and the timeliness factor is determined based on the preset time period to which the time point when the user participates in the business process belongs, the current preset time period, and the preset time period to which the start time of the preset time range of historical business process processing data belongs.

[0118] Based on the frequency factor and the timeliness factor, the elements are determined to determine a process participation matrix including a plurality of elements.

[0119] In one implementation, the business process information includes the total process running time of the business process processed by the target user; wherein the total process running time is the time from the initiation of the business process to the completion of the processing; the acquisition module 410 is specifically used to: Get historical business process processing data that also includes the total process run time of the business processes processed by the user.

[0120] The prediction module 430 is specifically used for: Based on the total process running time corresponding to the similar user set, the total process running time of the business process handled by the target user is determined.

[0121] In one implementation, the business process information includes the remaining time of the business process processed by the target user; wherein the remaining time of the process is the time corresponding to the completion of the business process from the current process node; the acquisition module 410 is specifically used to: The historical business process processing data including the process remaining time of the business process processed by the user is obtained.

[0122] The prediction module 430 is specifically used for: Based on the process remaining time corresponding to the similar user set, the process remaining time of the business process processed by the target user is determined.

[0123] In one implementation, the business process information includes decision passing information of a decision node of a business process processed by a target user; wherein the decision passing information includes the probability of the business process being approved at the decision node, and / or target reason information of the business process not being approved at the decision node; the acquisition module 410 is specifically used to: When the next process node of the current process node is a decision node, historical business process processing data including decision information of the business process processed by the user is obtained.

[0124] The decision information includes approval result information indicating whether the business process is approved at the decision node, and / or reason information indicating why the business process is not approved at the decision node.

[0125] The prediction module 430 is specifically used for: Based on the decision information corresponding to the similar user set, the decision passing information of the decision node of the business process processed by the target user is determined to provide the decision passing information to the target user.

[0126] In one implementation, the business process information includes evaluation information of a process node of a business process processed by a target user; wherein the evaluation information is used to characterize the relationship between the process node processing time corresponding to the target user and the average value of the process node processing time corresponding to a set of similar users; the acquisition module 410 is specifically used to: The historical business process processing data including the process node processing time of the process node of the business process processed by the user is obtained.

[0127] The process node processing time is the time from the arrival of the process node to the completion of the process node processing.

[0128] The prediction module 430 is specifically used for: Based on the process node processing time corresponding to the similar user set, the evaluation information of the process node of the target user processing the business process is determined.

[0129] Those skilled in the art should understand that the above-mentioned business process information prediction device can be used to implement the business process information prediction method mentioned above, and the detailed description thereof should be similar to the description of the method part mentioned above, and will not be repeated here to avoid repetition.

[0130] In this embodiment, historical business process processing data is obtained; wherein the historical business process processing data is related data on user processing of business processes in a business system; based on the historical business process processing data, a similar user set corresponding to a target user is determined through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; then based on the historical business process processing data corresponding to the similar user set, business process information is predicted; wherein the business process information is information related to the target user processing the business process. Compared with the prediction technology of related business process information, which only predicts based on the corresponding historical business process processing data of similar business processes to obtain the business process information of the business process to be predicted, the present application determines the users whose participation in the business process is similar to that of the target user, that is, the set of similar users corresponding to the target user, through a pre-trained prediction model, and then predicts the business process information based on the historical business process processing data corresponding to the similar user set, thereby generating corresponding prediction results (business process information) for different users processing business processes, taking into account the personalized characteristics of the target users, and realizing personalized prediction services for the target users, so that the prediction results are more accurately fitted to the target users, thereby improving the accuracy of the predicted business process information, and solving the problem of low prediction accuracy of the prediction technology of related business process information.

[0131] Corresponding to the web page prediction method provided in the above embodiment, based on the same technical concept, the embodiment of the present invention also provides a web page prediction device. Figure 5 is a schematic diagram of the structure of a web page prediction device according to an embodiment of the present invention, wherein the business process information prediction device is used to perform Figure 3 The prediction method of the web page described, such as Figure 5 As shown, the web page prediction device includes: a data acquisition module 510 , a set determination module 520 , and a web page prediction module 530 .

[0132] The data acquisition module 510 is used to acquire historical business process processing data in the business system, historical data of user's web page click stream and current web page of the target user.

[0133] The historical business process processing data refers to the data related to the user's processing of the business process in the business system.

[0134] The set determination module 520 is used to process data based on historical business processes and determine a similar user set corresponding to the target user through a pre-trained prediction model.

[0135] Among them, the users in the similar user set and the target user have similar participation in the business process.

[0136] The web page prediction module 530 is used to predict the next web page that the target user needs to visit based on the next web page corresponding to the current web page in the web page click stream history data corresponding to the similar user set, so as to display the next web page that the target user needs to visit to the target user.

[0137] In one implementation, the set determination module 520 includes: The processing unit is used to process the historical business process processing data based on the historical business process processing data through the pre-trained prediction model to obtain the process participation matrix.

[0138] The elements in the process participation matrix are determined based on the business processes in which the user participates and the time of participating in the business processes, and are used to characterize the user's participation in the business process; the historical business process processing data includes the business processes in which the user participates and the time of participating in the business process.

[0139] The determination unit is used to determine the similarity between the element corresponding to the target user in the process participation matrix and the element corresponding to the user other than the target user in the process participation matrix through a pre-trained prediction model, and obtain a similar user set of the target user based on the similarity and preset conditions.

[0140] In one implementation, the data acquisition module 510 is specifically configured to: Get historical business process processing data within a preset time range.

[0141] The processing unit is specifically used for: Through pre-trained prediction models, data is processed based on historical business processes to determine frequency factors and timeliness factors.

[0142] Among them, the frequency factor is the number of times the user participates in the business process within the preset time period, and the timeliness factor is determined based on the preset time period to which the time point when the user participates in the business process belongs, the current preset time period, and the preset time period to which the start time of the preset time range of historical business process processing data belongs.

[0143] Based on the frequency factor and the timeliness factor, the elements are determined to determine a process participation matrix including a plurality of elements.

[0144] Those skilled in the art should understand that the web page prediction device described above can be used to implement the web page prediction method described above, and the detailed description thereof should be similar to the description of the method described above, and will not be repeated here to avoid repetition.

[0145] In this embodiment, by obtaining historical business process processing data in the business system, historical data of user's webpage click stream and current webpage of the target user; wherein the historical business process processing data is the relevant data of the user's processing of the business process in the business system; based on the historical business process processing data, a similar user set corresponding to the target user is determined through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; based on the next webpage corresponding to the current webpage in the webpage click stream historical data corresponding to the similar user set, the next webpage that the target user needs to visit is predicted, so as to display the next webpage that the target user needs to visit to the target user. This helps users to achieve quick access, reduce redundant webpage access paths, reduce the number of user clicks, improve user access efficiency, and enhance user experience.

[0146] Based on the same technical concept, an embodiment of the present application further provides an electronic device, which is used to execute the above-mentioned method for predicting business process information or the above-mentioned method for predicting web pages. Figure 6 A schematic diagram of the structure of an electronic device for implementing various embodiments of the present application. The electronic device may have relatively large differences due to different configurations or performances, and may include a processor (processor) 610, a communication interface (Communications Interface) 620, a memory (memory) 630 and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call a computer program stored in the memory 630 and executable on the processor 610 to perform the following steps: Obtain historical business process processing data; wherein the historical business process processing data is relevant data on the processing of business processes in the business system by users; Based on historical business process processing data, a pre-trained prediction model is used to determine a set of similar users corresponding to the target user; wherein the users in the similar user set have similar participation in the business process as the target user; Based on the historical business process processing data corresponding to the similar user set, the business process information is predicted; wherein the business process information is information related to the business process processed by the target user.

[0147] Alternatively, follow these steps: Obtain historical business process processing data in the business system, historical data of user's web page click stream, and current web page of the target user; wherein the historical business process processing data is the relevant data of the user's processing of the business process in the business system; Based on historical business process processing data, a pre-trained prediction model is used to determine a set of similar users corresponding to the target user; wherein the users in the similar user set have similar participation in the business process as the target user; Based on the next web page corresponding to the current web page in the web page click stream history data corresponding to the similar user set, the next web page that the target user needs to visit is predicted to display the next web page that the target user needs to visit to the target user.

[0148] In this embodiment, historical business process processing data is obtained; wherein the historical business process processing data is related data on user processing of business processes in a business system; based on the historical business process processing data, a similar user set corresponding to a target user is determined through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; then based on the historical business process processing data corresponding to the similar user set, business process information is predicted; wherein the business process information is information related to the target user processing the business process. Compared with the prediction technology of related business process information, which only predicts based on the corresponding historical business process processing data of similar business processes to obtain the business process information of the business process to be predicted, the present application determines the users whose participation in the business process is similar to that of the target user, that is, the set of similar users corresponding to the target user, through a pre-trained prediction model, and then predicts the business process information based on the historical business process processing data corresponding to the similar user set, thereby generating corresponding prediction results (business process information) for different users processing business processes, taking into account the personalized characteristics of the target users, and realizing personalized prediction services for the target users, so that the prediction results are more accurately fitted to the target users, thereby improving the accuracy of the predicted business process information, and solving the problem of low prediction accuracy of the prediction technology of related business process information.

[0149] Alternatively, by obtaining historical business process processing data in the business system, historical data of user's web page click stream and current web page of the target user; wherein the historical business process processing data is the relevant data of the user's processing of the business process in the business system; based on the historical business process processing data, the similar user set corresponding to the target user is determined through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; based on the next web page corresponding to the current web page in the web page click stream historical data corresponding to the similar user set, the next web page that the target user needs to visit is predicted, so as to display the next web page that the target user needs to visit to the target user. This helps users to achieve quick access, reduce redundant web page access paths, reduce user click times, improve user access efficiency, and enhance user experience.

[0150] The specific execution steps can refer to the various steps of the above-mentioned prediction method for business process information and the above-mentioned prediction method for web pages, and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0151] It should be noted that the electronic devices in the embodiments of the present application include: servers, terminals, or other devices except terminals.

[0152] The above electronic device structure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, the input unit may include a graphics processing unit (GPU) and a microphone, and the display unit may be configured with a display panel in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit includes a touch panel and at least one of other input devices. The touch panel is also called a touch screen. Other input devices may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0153] The memory can be used to store software programs and various data. The memory may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory may include a volatile memory or a non-volatile memory, or the memory may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DRRAM).

[0154] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor.

[0155] An embodiment of the present application also provides a storage medium having computer executable instructions stored thereon. When the computer executable instructions are executed by a processor, the various processes of the above-mentioned business process information prediction method embodiment or the above-mentioned web page prediction method embodiment can be implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0156] The processor is the processor in the electronic device described in the above embodiment. The storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0157] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned business process information prediction method embodiment or the above-mentioned web page prediction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0158] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0159] An embodiment of the present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the various processes of the above-mentioned business process information prediction method embodiment or the above-mentioned web page prediction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0160] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include multitasking and parallel processing according to the functions involved, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0161] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0162] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for predicting business process information, characterized in that: The method comprises: Acquire historical business process processing data; wherein the historical business process processing data is relevant data of the user processing the business process in the business system; Based on the historical business process processing data, a similar user set corresponding to the target user is determined through a pre-trained prediction model; wherein the users in the similar user set and the target user have similar participation in the business process; Based on the historical business process processing data corresponding to the similar user set, business process information is predicted; wherein the business process information is information related to the target user processing the business process.

2. The method according to claim 1, characterized in that The determining, based on the historical business process processing data and using a pre-trained prediction model, a set of similar users corresponding to the target user includes: Based on the historical business process processing data, the historical business process processing data is processed by a pre-trained prediction model to obtain a process participation matrix; wherein the elements in the process participation matrix are determined based on the business process in which the user participates and the time of participating in the business process, and are used to characterize the user's participation in the business process; the historical business process processing data includes the business process in which the user participates and the time of participating in the business process; Through the pre-trained prediction model, the similarity between the element corresponding to the target user in the process participation matrix and the element corresponding to the user other than the target user in the process participation matrix is ​​determined, and based on the similarity and preset conditions, the similar user set of the target user is obtained.

3. The method according to claim 2, characterized in that The obtaining of historical business process processing data includes: Acquire the historical business process processing data within a preset time range; The historical business process processing data is processed based on the historical business process processing data by using a pre-trained prediction model to obtain a process participation matrix, including: Determine a frequency factor and a time factor based on the historical business process processing data through a pre-trained prediction model; wherein the frequency factor is the number of times the user participates in the business process within a preset time period, and the time factor is determined based on the preset time period to which the time point of the user's participation in the business process belongs, the preset time period to which the current time belongs, and the preset time period to which the start time of the preset time range of the historical business process processing data belongs; Based on the frequency factor and the timeliness factor, the element is determined to determine the process participation matrix including a plurality of the elements.

4. The method according to claim 1, characterized in that: The business process information includes the total process running time of the business process processed by the target user; wherein the total process running time is the time from the initiation of the business process to the completion of the processing; the acquisition of historical business process processing data includes: Acquiring the historical business process processing data further including the total process running time of the business process processed by the user; The predicting business process information based on the historical business process processing data corresponding to the similar user set includes: The total process running time of the business process processed by the target user is determined based on the total process running time corresponding to the similar user set.

5. The method according to claim 1, characterized in that The business process information includes the remaining time of the business process processed by the target user; wherein the remaining time is the time from the current process node to the completion of the business process; the acquisition of historical business process processing data includes: Acquiring the historical business process processing data further including the process remaining time of the business process processed by the user; The predicting business process information based on the historical business process processing data corresponding to the similar user set includes: The remaining time of the business process processed by the target user is determined based on the remaining time of the process corresponding to the similar user set.

6. The method according to claim 1, characterized in that The business process information includes decision passing information of the decision node of the business process processed by the target user; wherein the decision passing information includes the probability of the business process being approved at the decision node, and / or the target reason information of the business process not being approved at the decision node; The obtaining of historical business process processing data includes: In the case where the next process node of the current process node is the decision node, the historical business process processing data including the decision information of the business process processed by the user is obtained; wherein the decision information includes approval result information indicating whether the business process is approved at the decision node, and / or reason information indicating why the business process is not approved at the decision node; The predicting business process information based on the historical business process processing data corresponding to the similar user set includes: Based on the decision information corresponding to the similar user set, the decision passing information of the decision node of the business process processed by the target user is determined to provide the decision passing information to the target user.

7. The method according to claim 1, characterized in that The business process information includes evaluation information of the process nodes of the business process processed by the target user; wherein the evaluation information is used to characterize the relationship between the process node processing time corresponding to the target user and the average value of the process node processing time corresponding to the similar user set; The obtaining of historical business process processing data includes: Acquire the historical business process processing data further including the process node processing time of the process node of the business process processed by the user; wherein the process node processing time is the time from the arrival of the process node to the completion of the processing of the process node; The predicting business process information based on the historical business process processing data corresponding to the similar user set includes: Based on the process node processing time corresponding to the similar user set, the evaluation information of the process node of the business process processed by the target user is determined.

8. A business process information prediction device, characterized in that: The device comprises: An acquisition module is used to acquire historical business process processing data; wherein the historical business process processing data is relevant data of the user processing the business process in the business system; A determination module, configured to determine a set of similar users corresponding to a target user based on the historical business process processing data and through a pre-trained prediction model; wherein the users in the set of similar users and the target user have similar participation in the business process; A prediction module is used to predict business process information based on the historical business process processing data corresponding to the similar user set; wherein the business process information is information related to the target user processing the business process.

9. An electronic device, characterized in that: include: processor; as well as A memory arranged to store computer executable instructions, wherein the executable instructions are configured to be executed by the processor, and the executable instructions include instructions for executing the business process information prediction method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is used to store computer-executable instructions, and the computer-executable instructions enable a computer to execute the method for predicting business process information according to any one of claims 1 to 7.

Images