Process business index data analysis method and device and computer equipment

Abstract

The invention relates to the technical field of intelligent analysis of process business index data, and discloses a process business index data analysis method and device and computer equipment, and the method comprises the steps: obtaining various historical process business data used for training a process business index data analysis model: carrying out the preprocessing of the various historical process business data; extracting a process business characteristic variable set from the preprocessed various historical process business data, and inputting the process business characteristic variable set into the initial process business index data analysis model to obtain a trained process business index data analysis model; obtaining to-be-analyzed process business data; and inputting the to-be-analyzed process business data into the process business index data analysis model to obtain a business index analysis result corresponding to the to-be-analyzed process business data, and finally, when facing a large amount of process business data, the method does not need to manually detect each process node one by one, so that the time consumption of the process business index data is reduced, and the efficiency is improved. And the cost is also reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent analysis of process business indicator data, and in particular to a method, device and computer equipment for analyzing process business indicator data. Background Art

[0002] In the rapidly developing information age, enterprises gradually rely on complex business processes to support daily operations. Business indicators in process business data are often used to measure the implementation of the business. Relevant staff within the enterprise can update the company's products, operation strategies, etc. according to business indicators and their changes to improve the implementation effect of the corresponding business. For example, if the efficiency indicators in the current process business data are low, it cannot meet the needs of the process business.

[0003] In related technologies, process business data is generally analyzed manually to gradually analyze the failure rate indicators, efficiency execution indicators, and usage time indicators of each process node. However, when faced with a large amount of process business data, it is very time-consuming and costly to manually detect each process node one by one. Summary of the invention

[0004] In view of this, the present invention provides a method, device and computer equipment for analyzing process business indicator data to solve the problem that when faced with a large amount of process business data, it is very time-consuming and costly to manually detect each process node one by one.

[0005] According to a first aspect, an embodiment of the present disclosure provides a method for analyzing process business indicator data, the method comprising:

[0006] Obtain various historical process business data for training process business indicator data analysis models:

[0007] Pre-process various historical process business data;

[0008] Extracting a process business characteristic variable set from the pre-processed multiple historical process business data, and inputting the process business characteristic variable set into the initial process business indicator data analysis model to obtain a trained process business indicator data analysis model;

[0009] Obtain the business data of the process to be analyzed;

[0010] Input the process business data to be analyzed into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed.

[0011] In some optional implementations, a variety of historical process business data: process task completion time, process task error rate, process task node click count;

[0012] Preprocess various historical process business data, including:

[0013] The missing value processing, duplication removal and data integration processing are carried out on various historical process business data in turn.

[0014] In some optional implementations, a process business characteristic variable set is extracted from the pre-processed multiple historical process business data, and the process business characteristic variable set is input into the initial process business indicator data analysis model to obtain a trained process business indicator data analysis model, including:

[0015] Step A1, obtaining preset parameters of each characteristic variable in the process business characteristic variable set;

[0016] Step A2, sorting multiple historical process business characteristic variables based on preset parameters of each characteristic variable;

[0017] Step A3, selecting a feature variable with the highest ranking from the process business feature variable set, and using the feature variable with the highest ranking as the first feature variable;

[0018] Step A4, calculating the correlation coefficient between the first characteristic variable and the second characteristic variable, wherein the second characteristic variable is the remaining characteristic variables of the process business characteristic variable set excluding the first characteristic variable;

[0019] Step A5, deleting feature variables whose correlation coefficients are greater than a first threshold from the process business feature variable set, thereby obtaining an initial feature variable set of the first feature variable;

[0020] Step A6, obtaining the lowest-ranked feature variable from the initial feature variable set, and calculating the variance inflation factor value of the lowest-ranked feature variable;

[0021] Step A7, when the variance inflation factor value is greater than the second threshold, deleting the feature variable with the lowest ranking level from the initial feature variable set, and when the variance inflation factor is less than the second threshold, retaining the feature variable with the lowest ranking level in the initial feature variable set;

[0022] Step A8, repeating the above steps A6 to A7 for each feature variable in the initial feature variable set, thereby obtaining a first feature variable set of the first feature variable;

[0023] Step A9, repeating the above steps A3 to A7 for the second characteristic variable in the process business characteristic variable set, thereby obtaining multiple characteristic variable sets;

[0024] Step A10, generating a trained process business indicator data analysis model based on each feature variable set.

[0025] In some optional implementations, a variety of historical process business data for training the process business indicator data analysis model are obtained through user feedback and / or log files and / or business databases and / or monitoring systems.

[0026] In some optional implementations, the method for analyzing process business indicator data in the embodiment of the present disclosure further includes:

[0027] Based on the business indicator analysis results corresponding to the process business data to be analyzed, generate process business indicator optimization measures.

[0028] In some optional implementations, the process business data to be analyzed is input into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed, including:

[0029] Obtain the business indicator analysis results corresponding to the business data of the process to be analyzed;

[0030] Calculate the loss value between the business indicator analysis result and the true value label corresponding to the business indicator of the process business data to be analyzed, update the network parameters of the process business indicator data analysis model, and train the process business indicator data analysis model in a loop until the preset number of training times is reached and the training is terminated.

[0031] According to a second aspect, an embodiment of the present disclosure provides a device for analyzing process business indicator data, the device comprising:

[0032] The first acquisition module is used to acquire a variety of historical process business data for training the process business indicator data analysis model. The various historical process business data include:

[0033] Pre-processing module, used to pre-process various historical process business data;

[0034] A data training module is used to extract a process business characteristic variable set from a variety of pre-processed historical process business data, and input the process business characteristic variable set into an initial process business indicator data analysis model to obtain a trained process business indicator data analysis model;

[0035] The second acquisition module is used to acquire the business data of the process to be analyzed;

[0036] The data analysis module is used to input the process business data to be analyzed into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed.

[0037] According to a third aspect, an embodiment of the present disclosure provides a computer device, including:

[0038] The memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for analyzing process business indicator data in the first aspect or any implementation scheme of the first aspect by executing the computer instructions.

[0039] According to the fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the method for analyzing process business indicator data in the first aspect or any implementation of the first aspect.

[0040] According to a fifth aspect, an embodiment of the present disclosure provides a computer program product, including computer instructions, and the computer instructions are used to enable a computer to execute the method for analyzing process business indicator data in the first aspect or any implementation of the first aspect.

[0041] The technical solution of the present invention has the following advantages:

[0042] The disclosed embodiments disclose a method, apparatus and computer equipment for analyzing process business indicator data, wherein the method obtains a variety of historical process business data for training a process business indicator data analysis model: preprocesses the various historical process business data; extracts a process business feature variable set from the preprocessed various historical process business data, and inputs the process business feature variable set into an initial process business indicator data analysis model to obtain a trained process business indicator data analysis model; obtains process business data to be analyzed; inputs the process business data to be analyzed into the process business indicator data analysis model to obtain a business indicator analysis result corresponding to the process business data to be analyzed. Finally, when faced with a large amount of process business data, the disclosed embodiments do not need to manually detect each process node one by one, which not only reduces the time consumption of process business indicator data, but also reduces costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 is a flowchart of a method for analyzing process business indicator data according to an embodiment of the present invention;

[0045] Figure 2 is a simplified flowchart of another method for analyzing process business indicator data according to an embodiment of the present invention;

[0046] Figure 3 is a structural block diagram of a device for analyzing process business indicator data according to an embodiment of the present invention;

[0047] Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0049] According to an embodiment of the present invention, an embodiment of a method for analyzing process business indicator data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0050] In this embodiment, a method for analyzing process business indicator data is provided, which can be used in mobile terminals, such as mobile phones, tablet computers, etc. Figure 1 is a flowchart of a method for analyzing process business indicator data according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0051] Step S101, obtaining a variety of historical process business data for training a process business indicator data analysis model.

[0052] Specifically, process business refers to the process business data of systems used within different enterprises. For example, for an Internet of Vehicles enterprise, process business data may be the travel order business process for users to travel; for an e-commerce platform enterprise, process business data may be the order business process for users to purchase items; for a power grid enterprise, process business data may be the business process for maintenance personnel to detect power grid faults.

[0053] Furthermore, the process business indicator data analysis model is a general neural network model in machine learning. The process business indicator data analysis model is used to analyze the impact of various factors on process business indicators. The process business indicator data includes the failure rate indicator, efficiency execution indicator and usage time indicator of each process node.

[0054] In a specific example, there are various historical process business data: process task completion time, process task error rate, and process task node click count.

[0055] Specifically, the process task completion time, number of clicks on process task nodes, and process task error rate of users at each process task node are monitored to evaluate and identify which nodes are easy for users to execute and which may cause user confusion or delay. For example, if the average completion time of a process node is much lower than other process nodes and the error rate is low, then this process node may be a node that is easy for users to execute. On the contrary, if the average completion time of a process node is long, the number of clicks is high, and the error rate is high, then this process node may cause user confusion or delay.

[0056] Therefore, by collecting process business data related to process business in various dimensions, in order to further train the above-mentioned process business indicator data analysis model.

[0057] In another specific example, a variety of historical process business data for training a process business indicator data analysis model is obtained through user feedback and / or log files and / or business databases and / or monitoring systems.

[0058] Specifically, user feedback comes from questionnaires, user interviews, or user experience and opinions on the process. The log file comes from the system operation log, which records each step and time of the process execution. The business database is generated by extracting business data related to the process, such as task completion time, error rate, etc. The monitoring system uses process monitoring tools to obtain real-time data on process operation.

[0059] Step S102, pre-processing various historical process business data.

[0060] In another specific example, preprocessing is performed on a variety of historical process business data, including:

[0061] The missing value processing, duplication removal and data integration processing are carried out on various historical process business data in turn.

[0062] Specifically, in terms of missing value processing, the entire data set needs to be thoroughly checked first to identify whether there are missing values ​​in the data. If missing values ​​are found, the missing values ​​can be filled with the mean or median to complete the missing part of the data, making the data set more complete and reducing data bias.

[0063] Furthermore, outlier processing is performed on various historical training data after missing data processing. In terms of outlier processing, comprehensive detection and identification are also performed. Once outliers are found, corresponding processing measures are taken for these outliers according to specific business needs or data distribution characteristics. For example, outliers may be deleted, corrected, or retained in some cases. The specific operation depends on the potential impact of outliers on data analysis results.

[0064] Going a step further, data integration means fusing data from different sources to form a unified data set.

[0065] Step S103, extracting a process business characteristic variable set from the pre-processed multiple historical process business data, and inputting the process business characteristic variable set into the initial process business indicator data analysis model to obtain a trained process business indicator data analysis model.

[0066] Specifically, the above steps S101 and S102 are equivalent to splitting a variety of historical process business data into training sets and validation sets for building and verifying process business indicator data analysis models. In the process of training the process business indicator data analysis model, through step S103, a regression analysis combining single-factor characteristic variables with multi-factor characteristic variables is used to identify key factor characteristic variables that independently affect the target variables. By gradually removing single characteristic variables, the variance inflation factor statistical indicator is used to detect multicollinearity between variables, thereby optimizing the process business indicator data analysis model.

[0067] Step S104, obtaining the business data of the process to be analyzed;

[0068] Step S105 , inputting the process business data to be analyzed into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed.

[0069] The process business data to be analyzed may be consumer behavior process business or enterprise employee operation process business, etc. For example, the process business indicator data analysis model can be used to analyze the usage frequency index of the process business node, and the usage frequency index can reflect which specific process nodes are hot spots where users frequently interact and which specific process nodes are cold spots where users rarely visit.

[0070] In some optional implementations, the process business characteristic variable set is input into the initial process business indicator data analysis model to obtain a trained process business indicator data analysis model, including:

[0071] Step A1, obtaining preset parameters of each characteristic variable in the process business characteristic variable set.

[0072] The predetermined parameter may be the Gini index of each variable, wherein the Gini index represents the ability of the variable to distinguish sample classifications, and a larger Gini index indicates a stronger ability of the variable to distinguish.

[0073] Step A2: sorting the various historical process business characteristic variables based on the preset parameters of each characteristic variable.

[0074] Specifically, for example, after calculating the Gini index of each feature variable, the plurality of feature variables are sorted in descending order of the absolute value of the Gini index.

[0075] Step A3: Select a feature variable with the highest ranking from the process business feature variable set, and use the feature variable with the highest ranking as the first feature variable.

[0076] Specifically, taking the sorting of multiple feature variables based on the Gini index as an example, the variable with the largest absolute value of the Gini index is selected first. For example, assuming that the process business feature variable set contains 10 feature variables, and after sorting, they are: feature variable 1, feature variable 2, ..., feature variable 10, then feature variable 1 is selected first.

[0077] Step A4, calculating the correlation coefficient between the first characteristic variable and the second characteristic variable, wherein the second characteristic variable is the remaining characteristic variables of the process business characteristic variable set excluding the first characteristic variable.

[0078] Specifically, for example, the first characteristic variable is C, the second characteristic variable is D, and the correlation coefficient between the first characteristic variable C and the second characteristic variable D is calculated as shown in the following formula:

[0079]

[0080] Among them, Cov(C,D) is the covariance of C and D, E(C) and E(D) are the variances of C and D respectively.

[0081] Step A5, deleting characteristic variables whose correlation coefficients are greater than a first threshold from the process business characteristic variables, thereby obtaining an initial characteristic variable set of the first characteristic variables.

[0082] Specifically, through the above steps A3 to A5, an initial feature variable set based on the first feature variable is constructed. For example, the initial variable set is denoted as S0, and it is assumed that it includes feature variable 1, feature variable 5, feature variable 6 and feature variable 9.

[0083] Step A6, obtaining the lowest-ranked feature variable from the initial feature variable set, and calculating the variance inflation factor value of the lowest-ranked feature variable.

[0084] Specifically, the variance inflation factor value is used to determine whether there is multicollinearity in the variables. The larger the variance inflation factor value, the more serious the multicollinearity. That is to say, first select the least important variable in the initial variable set. For example, based on the Gini index sorting, select the variable with the smallest Gini index in the initial variable set. In the above example, variable 9 in the initial feature variable set S0 is recorded as the second feature variable (feature variable B).

[0085] Specifically, the variance inflation factor value of feature variable B is calculated by taking feature variable B as the dependent variable, performing linear regression fitting on the remaining feature variables (feature variable 1, feature variable 3, feature variable 5 and variable 6) in the initial feature variable set S0, and then calculating the determination coefficient based on the fitting results. The specific calculation process is shown in the following formula:

[0086]

[0087] Among them, x i is the true value of the feature variable B, is the estimated value of variable B by linear fitting, and is the mean value of variable B. In addition, the variance inflation factor value VIFA of feature variable B is shown as follows:

[0088]

[0089] Step A7, when the variance inflation factor value is greater than the second threshold, the feature variable with the lowest ranking level is deleted from the initial feature variable set, and when the variance inflation factor is less than the second threshold, the feature variable with the lowest ranking level is retained in the initial variable set.

[0090] Specifically, for example, in the above example, if the variance inflation factor value coefficient of feature variable 9 is greater than the second threshold value, feature variable 9 is deleted from feature variable set S0. Correspondingly, if the variance inflation factor value of feature variable 9 is less than the second threshold value, feature variable 9 is still retained in the initial variable set S0.

[0091] Step A8, repeating the above steps A6 to A7 for each feature variable in the initial feature variable set, thereby obtaining a first feature variable set of the first feature variable.

[0092] Specifically, the above steps A6 and A7 are repeated for each feature variable in the initial feature variable set to obtain a first feature variable set relative to the first feature variable. For example, in the above example, if feature variable 9 is deleted, a linear regression fit is performed on feature variable 6 using feature variable 1, feature variable 3, and feature variable 5. If feature variable 9 is retained, a linear regression fit is performed on feature variable 6 using feature variable 1, feature variable 3, feature variable 5, and feature variable 9. Then, it is determined whether the variance inflation factor value of feature variable 6 is greater than the second threshold. Next, the above steps are repeated for feature variable 5, feature variable 3, and feature variable 1 to obtain a first feature variable set relative to the first feature variable. For example, a first feature variable set V0 based on the first feature variable is obtained, assuming that it includes feature variable 1, feature variable 3, and feature variable 5.

[0093] Step A9: repeat the above steps A3 to A7 for the second characteristic variable in the process business characteristic variable set, and then obtain multiple characteristic variable sets.

[0094] Specifically, for variables other than the first feature variable set among the multiple feature variables, the above steps A3 to A7 are repeated to obtain multiple feature variable sets. Similarly, according to the above example, when calculating the correlation, feature variables 2, feature variables 4, feature variables 7, feature variables 8 and feature variables 10 are excluded from the feature variable set S0, and when calculating the variance inflation factor value, feature variables 6 and feature variables 9 are excluded from the first feature variable set, then the feature variables other than the first feature variable set include feature variables 2, feature variables 4, feature variables 7, feature variables 8, feature variables 10, feature variables 9 and feature variable 6. For example, the above feature variables are re-sorted according to the absolute value of the Gini index, which are feature variables 2, feature variables 4, feature variables 6, feature variables 7, feature variables 8, feature variables 9 and feature variables 10. Repeat the process of steps A3 to A7, assuming that the acquired feature variable set V1, for example, includes feature variables 2, feature variables 6 and feature variables 8. Then, for the remaining feature variables 4, feature variables 7, feature variables 9 and feature variables 10, repeat steps A3 to A7, and finally obtain multiple feature variable sets V0, V1, ..., VK-1, dividing the feature variable space into K mutually non-overlapping subspaces.

[0095] Step A10, generating a trained process business indicator data analysis model based on each feature variable set.

[0096] Specifically, multiple classifiers are generated based on each feature variable set, and the multiple classifiers are integrated into a final classifier to obtain a trained process business indicator data analysis model.

[0097] The disclosed embodiment adopts regression analysis combining single-factor characteristic variables with multi-factor characteristic variables to identify key factor characteristic variables that independently affect the target variable, and optimizes the process business indicator data analysis model by gradually removing single characteristic variables and using the variance inflation factor statistical indicator to detect multicollinearity between variables.

[0098] In some optional implementations, the method for analyzing process business indicator data in the embodiment of the present disclosure further includes:

[0099] Based on the business indicator analysis results corresponding to the process business data to be analyzed, generate process business indicator optimization measures.

[0100] Specifically, the process task completion time, number of clicks on process task nodes, and process task error rate of users at each process task node are monitored to evaluate and identify which nodes are easy for users to execute and which may cause user confusion or delays. For example, if the average completion time of a process node is much lower than other process nodes and the error rate is low, then this process node may be a node that is easy for users to execute. Conversely, if the average completion time of a process node is long, the number of clicks is high, and the error rate is high, then this process node may cause user confusion or delays. For a process node with a long average completion time, a high number of clicks, and a high error rate, supervision and training guidance measures are carried out to achieve the purpose of optimizing efficiency and reducing error rates.

[0101] In some optional implementations, the process business data to be analyzed is input into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed, including:

[0102] Step B1, obtaining the business indicator analysis results corresponding to the business data of the process to be analyzed;

[0103] Step B2, calculate the loss value between the business indicator analysis result and the true value label corresponding to the business indicator of the process business data to be analyzed, update the network parameters of the process business indicator data analysis model, and train the process business indicator data analysis model in a loop until the preset number of training times is reached and the training is terminated.

[0104] Specifically, in the disclosed embodiment, it is preferred to use the normalized root mean square error (NRMSE) as an indicator to calculate the loss value of the model, perform back propagation, adjust the parameters, and update the parameters of the process business indicator data analysis model. The optimization algorithm used is the Adaptive Moment Estimation method (ADAM).

[0105] like Figure 2 , which is a flow chart of a method for analyzing process business indicator data in an embodiment of the present disclosure.

[0106] The method for analyzing process business indicator data in the embodiment of the present disclosure obtains a variety of historical process business data for training a process business indicator data analysis model: preprocesses the various historical process business data; extracts a process business feature variable set from the preprocessed various historical process business data, and inputs the process business feature variable set into the initial process business indicator data analysis model to obtain a trained process business indicator data analysis model; obtains the process business data to be analyzed; inputs the process business data to be analyzed into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed. Finally, when faced with a large amount of process business data, the embodiment of the present disclosure does not need to manually detect each process node one by one, which not only reduces the time consumption of process business indicator data, but also reduces costs.

[0107] In this embodiment, a device for analyzing process business indicator data is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0108] This embodiment provides a device for analyzing process business indicator data, such as Figure 3 As shown, including:

[0109] The first acquisition module 31 is used to acquire a variety of historical process business data for training the process business indicator data analysis model. The various historical process business data include:

[0110] A pre-processing module 32 is used to pre-process various historical process business data;

[0111] The data training module 33 is used to extract a process business characteristic variable set from the pre-processed various historical process business data, and input the process business characteristic variable set into the initial process business indicator data analysis model to obtain a trained process business indicator data analysis model;

[0112] The second acquisition module 34 is used to acquire the process business data to be analyzed;

[0113] The data analysis module 35 is used to input the process business data to be analyzed into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed.

[0114] In some optional implementations, a variety of historical process business data: process task completion time, process task error rate, process task node click count;

[0115] The pre-processing module pre-processes various historical process business data, including: performing missing value processing, deduplication processing, and data integration processing on various historical process business data in turn.

[0116] In some optional implementations, the data training module 33 includes:

[0117] The first training submodule obtains preset parameters of each feature variable in the process business feature variable set;

[0118] The second training submodule ranks multiple historical process business characteristic variables based on preset parameters of each characteristic variable;

[0119] The third training submodule selects the feature variable with the highest ranking from the process business feature variable set, and uses the feature variable with the highest ranking as the first feature variable;

[0120] The fourth training submodule calculates the correlation coefficient between the first characteristic variable and the second characteristic variable, wherein the second characteristic variable is the remaining characteristic variables of the process business characteristic variable set excluding the first characteristic variable;

[0121] A fifth training submodule deletes feature variables with correlation coefficients greater than a first threshold from the process business feature variable set, thereby obtaining an initial feature variable set of the first feature variable;

[0122] The sixth training submodule obtains the lowest-ranked feature variable from the initial feature variable set, and calculates the variance inflation factor value of the lowest-ranked feature variable;

[0123] a seventh training submodule, when the variance inflation factor value is greater than a second threshold, deleting the feature variable with the lowest ranking level from the initial feature variable set, and when the variance inflation factor is less than the second threshold, retaining the feature variable with the lowest ranking level in the initial feature variable set;

[0124] An eighth training submodule, repeating the sixth training submodule and the seventh training submodule for each feature variable in the initial feature variable set, thereby obtaining a first feature variable set of the first feature variable;

[0125] A ninth training submodule, for the second characteristic variable in the process business characteristic variable set, repeating the third training submodule to the seventh training submodule, thereby obtaining multiple characteristic variable sets;

[0126] The tenth training submodule generates a trained process business indicator data analysis model based on each feature variable set.

[0127] In some optional implementations, a variety of historical process business data for training the process business indicator data analysis model are obtained through user feedback and / or log files and / or business databases and / or monitoring systems.

[0128] In some optional implementations, it also includes: an optimization module, which is used to generate process business indicator optimization measures based on the business indicator analysis results corresponding to the process business data to be analyzed.

[0129] In some optional embodiments, the data analysis module includes:

[0130] The data acquisition submodule is used to obtain the business indicator analysis results corresponding to the business data of the process to be analyzed;

[0131] The data calculation submodule is used to calculate the loss value between the business indicator analysis results and the true value label corresponding to the business indicator of the process business data to be analyzed, update the network parameters of the process business indicator data analysis model, and cyclically train the process business indicator data analysis model until the preset number of training times is reached and the training is terminated.

[0132] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0133] The analysis device for process business indicator data in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0134] The embodiment of the present invention further provides a computer device having an analysis device for process business indicator data.

[0135] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0136] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0137] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0138] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0139] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0140] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0141] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0142] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0143] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for analyzing process business indicator data, characterized in that: The method comprises: Obtain various historical process business data for training process business indicator data analysis models: Preprocessing the various historical process business data; Extracting a process business characteristic variable set from the pre-processed multiple historical process business data, and inputting the process business characteristic variable set into the initial process business indicator data analysis model to obtain the trained process business indicator data analysis model; Obtain the business data of the process to be analyzed; The process business data to be analyzed is input into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed.

2. The method according to claim 1, characterized in that: The various historical process business data: process task completion time, process task error rate, and process task node click times; Preprocessing the various historical process business data includes: The various historical process business data are processed in sequence including missing value processing, deduplication processing, and data integration processing.

3. The method according to claim 1, characterized in that: Extracting a process business characteristic variable set from the preprocessed multiple historical process business data, and inputting the process business characteristic variable set into the initial process business indicator data analysis model to obtain the trained process business indicator data analysis model, including: Step A1, obtaining preset parameters of each characteristic variable in the process business characteristic variable set; Step A2, sorting the multiple historical process business characteristic variables based on the preset parameters of each characteristic variable; Step A3, selecting a feature variable with the highest ranking from the process business feature variable set, and using the feature variable with the highest ranking as the first feature variable; Step A4, calculating the correlation coefficient between the first characteristic variable and the second characteristic variable, wherein the second characteristic variable is the remaining characteristic variables of the process business characteristic variable set excluding the first characteristic variable; Step A5, deleting the feature variables whose correlation coefficients are greater than a first threshold from the process business feature variable set, thereby obtaining an initial feature variable set of the first feature variable; Step A6, obtaining the lowest-ranked feature variable from the initial feature variable set, and calculating the variance inflation factor value of the lowest-ranked feature variable; Step A7, when the variance inflation factor value is greater than a second threshold, deleting the feature variable with the lowest ranking level from the initial feature variable set, and when the variance inflation factor is less than the second threshold, retaining the feature variable with the lowest ranking level in the initial feature variable set; Step A8, repeating the above steps A6 to A7 for each feature variable in the initial feature variable set, thereby obtaining a first feature variable set of the first feature variable; Step A9, repeating the above steps A3 to A7 for the second characteristic variable in the process business characteristic variable set, thereby obtaining multiple characteristic variable sets; Step A10, generating a trained process business indicator data analysis model based on each feature variable set.

4. The method for analyzing process business indicator data according to claim 1, characterized in that: Through user feedback and / or log files and / or business databases and / or monitoring systems, a variety of historical process business data for training process business indicator data analysis models are obtained.

5. The method for analyzing process business indicator data according to claim 1, characterized in that: Also includes: Based on the business indicator analysis results corresponding to the process business data to be analyzed, process business indicator optimization measures are generated.

6. The method for analyzing process business indicator data according to claim 1, characterized in that: Inputting the process business data to be analyzed into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed, including: Obtaining the business indicator analysis results corresponding to the business data of the process to be analyzed; Calculate the loss value between the business indicator analysis result and the true value label corresponding to the business indicator of the process business data to be analyzed, update the network parameters of the process business indicator data analysis model, and train the process business indicator data analysis model in a loop until the preset training times are reached and the training is terminated.

7. A device for analyzing process business indicator data, characterized in that: The device comprises: A first acquisition module is used to acquire a variety of historical process business data for training a process business indicator data analysis model; A pre-processing module, used for pre-processing the various historical process business data; A data training module, used for extracting a process business characteristic variable set from the pre-processed multiple historical process business data, and inputting the process business characteristic variable set into the initial process business indicator data analysis model to obtain the trained process business indicator data analysis model; The second acquisition module is used to acquire the business data of the process to be analyzed; The data analysis module is used to input the process business data to be analyzed into the process business indicator data analysis model to obtain the business indicator analysis results corresponding to the process business data to be analyzed.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for analyzing process business indicator data according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for analyzing process business indicator data according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the method for analyzing process business indicator data according to any one of claims 1 to 6.

Images