WO2023233663A1

WO2023233663A1 - Processing device, processing method, and processing program

Info

Publication number: WO2023233663A1
Application number: PCT/JP2022/022675
Authority: WO
Inventors: 英毅小矢; 明片岡
Original assignee: 日本電信電話株式会社
Priority date: 2022-06-03
Filing date: 2022-06-03
Publication date: 2023-12-07

Abstract

This processing device (10) has: an operation log acquisition unit (152) which acquires an operation log of system operations by means of an operator; an index calculation unit (153) which calculates, as an index value pertaining to operation accuracy, a plurality of index values pertaining to rework on the basis of the operation log; and an operation accuracy calculation unit (154) which integrates the plurality of index values and calculates the operation accuracy according to the current work of the operator.

Description

Processing equipment, processing method and processing program

The present invention relates to a processing device, a processing method, and a processing program.

Human errors associated with system operation mistakes can sometimes have a major impact on business continuity. For example, if incorrect contents are set due to a mistake in system operation, the settings may be reflected. If a large-scale network failure or system failure occurs due to this incorrect setting, it will cause damage to customers and have a significant impact on the company's subsequent business continuity.

In order to prevent such human errors, it is important to understand the status of business workers (system operators) in work that involves system operations. Therefore, a method has been proposed in which the state (amount of stress) of a business worker (office worker) involved in system operations is calculated from a PC operation log (Non-Patent Document 1).

In the method described in Non-Patent Document 1, a correlation with the amount of stress of office workers is determined based on indicators such as the frequency of keyboard input errors, the number of times active windows are switched, and working hours.

For the purpose of preventing human errors, it is necessary to calculate the status of workers in their "current work" based on multiple indicators. Also, the important indicators change depending on the current business. For this reason, it is necessary to integrate multiple indicators to determine the status of workers.

However, in the method described in Non-Patent Document 1, only the correlation between each individual index and the state (stress amount) is determined. In addition, most of the indicators are related to the amount of operation (operation amount) regardless of the success or failure of the operation, and there is a lack of indicators related to rework or mistakes in the operation.

The present invention has been made in view of the above, and provides a processing device, a processing method, and a processing program that can appropriately obtain the operational accuracy of a business worker who is an operator in the work currently being performed. The purpose is to

In order to solve the above-mentioned problems and achieve the purpose, a processing device according to the present invention includes an acquisition unit that acquires an operation log of system operations by an operator, and an acquisition unit that acquires an operation log of system operations by an operator, and an index value regarding operation accuracy based on the operation log. , a first calculation unit that calculates a plurality of index values regarding rework; a second calculation unit that integrates the plurality of index values to calculate operation accuracy according to the operator's current work; It is characterized by having the following.

According to the present invention, it is possible to appropriately obtain the operational accuracy of a business worker who is an operator in a job currently being performed.

FIG. 1 is a diagram schematically showing an example of the configuration of a processing device according to an embodiment. FIG. 2 is a diagram showing an example of the data structure of the rework detection table. FIG. 3 is a diagram showing an example of the data structure of the typo detection table. FIG. 4 is a diagram showing an example of the data structure of the active window switching detection table. FIG. 5 is a diagram illustrating the classification process of rework operations. FIG. 6 is a diagram illustrating the classification process of rework operations. FIG. 7 is a diagram illustrating a hierarchical neural network (NN) employed by the operation accuracy calculation unit. FIG. 8 is a flowchart showing the processing procedure of the operation accuracy calculation process according to the embodiment. FIG. 9 is a flowchart illustrating an example of the processing procedure of the index calculation process. FIG. 10 is a flowchart showing another example of the processing procedure of the index calculation process. FIG. 11 is a flowchart showing another example of the processing procedure of the index calculation process. FIG. 12 is a diagram explaining the conventional method. FIG. 13 is a diagram illustrating a processing method according to the embodiment. FIG. 14 is a diagram illustrating an example of a computer that implements a processing device by executing a program.

Hereinafter, one embodiment of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to this embodiment. In addition, in the description of the drawings, the same parts are denoted by the same reference numerals.

[Embodiment]
In this embodiment, a processing device and a processing method for acquiring the operational precision of a business worker who is an operator of a system in a business that is currently being performed will be described.

In the embodiment, a plurality of index values related to rework, which are directly linked to operation accuracy, are calculated based on the operation log, and the operation accuracy is derived by integrating these plurality of index values. As a result, in the embodiment, operation accuracy is obtained that includes an index value indicating that an operation related to rework (for example, an operation error) that is directly related to operation accuracy has occurred.

Furthermore, in the embodiment, in deriving operational accuracy by integrating index values, various index values are weighted based on the current work situation of the worker, so that operational accuracy is derived according to the work situation. Realize.

[Processing device]
A processing device according to an embodiment will be described. FIG. 1 is a diagram schematically showing an example of the configuration of a processing device according to an embodiment. As shown in FIG. 1, the processing device 10 includes an input section 11, an output section 12, a communication section 13, a storage section 14, and a control section 15.

The input unit 11 is realized using input devices such as a keyboard, a mouse, and a microphone, and receives input operations from a business worker who is a system operator. The input unit 11 inputs various instruction information such as starting processing to the control unit 15 in response to the received input operation. Further, the output unit 12 is realized by a display device (desktop) such as a liquid crystal display, a printing device such as a printer, a speaker, and the like.

The communication unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between an external device and the control unit 15 via a telecommunication line such as a LAN (Local Area Network) or the Internet.

The storage unit 14 is a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or an optical disk. Note that the storage unit 14 may be a data-rewritable semiconductor memory such as a RAM (Random Access Memory), a flash memory, or an NVSRAM (Non Volatile Static Random Access Memory). In the storage unit 14, a processing program for operating the processing device 10, data used during execution of the processing program, and the like are stored in advance, or are temporarily stored each time processing is performed. Note that the storage unit 14 may be configured to communicate with the control unit 15 via the communication unit 13.

The storage unit 14 includes a business system operation log 141 by a business worker who is a system operator, and a detection table 142 in which mistakes detected from the operation log are registered. The detection table 142 includes, for example, a rework detection table 1421, a typo detection table 1422, and an active window switching detection table 1423.

In the rework detection table 1421, the times at which rework operations occur are registered. FIG. 2 is a diagram showing an example of the data structure of the rework detection table 1421. As shown in FIG. 2, the rework detection table 1421 has a configuration in which line numbers of operation logs classified as rework operations are associated with occurrence times of the rework operations.

In the typo detection table 1422, the time of occurrence of a key input and the input key are registered. FIG. 3 is a diagram showing an example of the data structure of the typo detection table 1422. As shown in FIG. 3, the typo detection table 1422 has a configuration in which line numbers of the operation log, key input generation times, and input keys are associated with each other.

In the active window switching detection table 1423, information indicating the time when active window switching occurred and the switched active window is registered. FIG. 4 is a diagram showing an example of the data structure of the active window switching detection table 1423. As shown in FIG. 4, it has a configuration in which the line number of the operation log, the time at which switching of the active window occurs, and the identification information of the switched active window are associated.

The control unit 15 controls the entire processing device 10. The control unit 15 includes, for example, electronic circuits such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), and a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), and an FPGA (Field Programmable Gate). Array) etc. It is an integrated circuit.

Further, the control unit 15 has an internal memory for storing programs and control data that define various processing procedures, and executes each process using the internal memory. Further, the control unit 15 functions as various processing units by running various programs. For example, the control unit 15 includes a business system 151 used and operated by a business worker, an operation log acquisition unit 152 (acquisition unit), an index calculation unit 153 (first calculation unit), and an operation accuracy calculation unit 154 (second calculation unit). calculation unit).

The operation log acquisition unit 152 detects and acquires operation logs of system operations by business workers. The operation log acquisition unit 152 stores the acquired operation log in the storage unit 14.

Based on the operation log, the index calculation unit 153 calculates a plurality of index values regarding rework as an index regarding operation accuracy. Rework is considered to be an operation that makes the final result incorrect (different from the intended state). The index calculation unit 153 at least calculates, as a plurality of index values related to rework, the frequency of occurrence of rework operations, the frequency of occurrence of typographical errors, the frequency of switching active windows without operation and/or reference, and the duration of the current task. Two or more of these are calculated as index values.

Calculation of the frequency of occurrence of rework operations will be explained. For example, if the "OK" or "Cancel" confirmation dialog is displayed and the "Cancel" button is pressed, it is predicted that a rework operation has occurred, such as trying to execute a process once and then stopping. can. Similarly, if a button such as ``Back'' or ``Cancel'' is pressed on the system screen, it can be predicted that a reworked operation has occurred, where the user attempted to execute a process once and then stopped. The index calculation unit 153 estimates processing similar to rework operations from the operation log and calculates the frequency of occurrence of operation errors (rework operations) (index value P ₁ ) by determining the number of times these operations occur.

First, the index calculation unit 153 acquires an operation log, and if the operation target operated by the worker indicated in the operation log is an executable GUI (Graphical User Interface), the information of the GUI element is , it is determined whether the operation is classified as a rework operation.

Conditions for executable GUI elements can be arbitrarily defined. For example, if the type of the GUI element is a "button" or if the GUI element has a "click event", it is defined as an executable GUI element.

Then, the index calculation unit 153 classifies whether the information on the GUI element is a rework operation. The classification method may be arbitrarily set, such as a method of performing a text pattern match between the displayed character string of the GUI element and a predefined list of character strings similar to rework operations.

FIGS. 5 and 6 are diagrams illustrating the classification process of rework operations. As shown in the menu M11 in FIG. 5, the index calculation unit 153 classifies the operation on the "Cancel" button U11 as a redo operation. Further, as shown in the menu M12 in FIG. 6, the index calculation unit 153 classifies the operation on the "back" button U12 as a redo operation.

The index calculation unit 153 registers the operation log classified as a rework operation in the rework detection table 1421. Specifically, the index calculation unit 153 inserts into the rework detection table 1421 row data that includes the line number of the operation log classified as having a rework operation and the time of occurrence of this operation log.

The index calculation unit 153 refers to the rework detection table 1421 and uses equation (1) to calculate the frequency of occurrence of rework operations (index value P ₁ ).

Next, calculation of the frequency of typographical errors will be explained. Typos are considered to be operations related to input errors during rework. The index calculation unit 153 acquires the operation log, and if the operation in the operation log is a keyboard input, the index calculation unit 153 generates line data including the line number of the operation log, the time of occurrence of this operation log, and the input key input from the keyboard. is inserted into the typo detection table 1422.

The index calculation unit 153 refers to the typo detection table 1422 and uses equation (2) to calculate the frequency of occurrence of typos (index value P ₂ ).

Next, calculation of the switching frequency of active windows without operation and/or reference will be explained.

Here, if the active window is switched without operation and/or reference, it can be predicted that a window that does not meet the purpose has been accessed. When accessing a window that does not meet the purpose, it is considered that an operation similar to rework was performed, such as opening a window that did not need to be operated or opening a window that did not display necessary information. Therefore, switching the active window without operation and/or reference is considered to be a rework related to misunderstanding (mixing up) the target.

The index calculation unit 153 estimates the frequency of active window switching without operation and/or reference ( An index value P ₃ ) is calculated.

First, the index calculation unit 153 acquires the operation log and determines for each operation whether the active window is different from the previous active window.

The index calculation unit 153 determines whether the active window is different from the previous active window, based on the window title, for example. Furthermore, the index calculation unit 153 may determine whether the active window is different from the previous active window using the process name, more detailed display value of the window, or the like.

If the active window is different from the previous active window, the index calculation unit 153 adds the line number of the operation log, the time of occurrence of this operation log, and the identification information of the switched active window to the active window switching detection table 1423. Insert row data containing. For example, as shown in FIG. 4, the index calculation unit 153 registers a window title as identification information of the active window.

The index calculation unit 153 refers to the active window switching detection table 1423 and uses equation (3) to calculate the frequency of active window switching without operation and/or reference (index value P ₃ ).

Note that equation (3) is based on an example in which no operation or reference is required when the window switching interval is short (less than or equal to a predetermined threshold). In addition to formula (3), the index calculation unit 153 may determine that no operation has occurred by detecting that no operation event has occurred within the window, or may determine that no operation has occurred by detecting that no operation event has occurred within the window, or may determine that no operation has occurred by It may be determined that the reference information does not exist by detecting .

Next, calculation of the duration of the current task will be explained. The index calculation unit 153 acquires an operation log. Then, the index calculation unit 153 refers to the operation log and the active window switching detection table 1423, and calculates the duration of the task (index value P ₄ ) using equation (4).

Note that equation (4) is based on an example in which the active window switching detection table 1243 is used to determine operations in the same window as the same task, and the duration of the most recent task is calculated. At this time, row data that is below a predetermined threshold, that is, row data that was temporarily operated on another window, is deleted as belonging to the main business. Furthermore, the index calculation unit 153 may estimate the work situation using detailed information of the GUI elements and obtain the duration of the current work.

The operation accuracy calculation unit 154 integrates the plurality of index values calculated by the index calculation unit 153 and calculates the operation accuracy according to the current work of the business worker who is the system operator.

For example, the operation accuracy calculation unit 154 integrates the plurality of index values P ₁ to P ₄ regarding rework by calculating a weighted sum of each of the index values P ₁ to P ₄ . The operation accuracy calculation unit 154 uses weights that correspond to the current business situation and are set for each of the index values P ₁ to P ₄ .

The operation accuracy calculation unit 154 calculates the operation accuracy using equation (5).

In equation (5), Index Value _i is the value of each index value P _i (i=1 to 4). W _{current_operation, i} is the weight for each current operation and index value. When determining the current business using the same method as the "duration time of the current business", current_operation is information on the active window, and W _{current_operation, i} is the weight for each index value in each active window. Further, the weight may be defined by a person empirically, or may be derived by regression analysis or the like from data accumulated in advance along with an evaluation of operation accuracy.

Furthermore, the operation accuracy calculation unit 154 may calculate the operation accuracy using a hierarchical neural network (NN).

FIG. 7 is a diagram illustrating the hierarchical NN employed by the operation accuracy calculation unit 154. For example, the hierarchical NN employed by the operation accuracy calculation unit 154 is a hierarchical NN that has previously learned the relationship between the evaluation of operation accuracy and the plurality of index values P ₁ to P ₄ . In this hierarchical NN, learning has been performed based on the evaluation (classification) of operation accuracy and accumulated data in advance. As shown in FIG. 7, this hierarchical NN is a NN in which each index value P ₁ to P ₄ and the current business situation (work classification) are given as input layers, and the value of the output layer is used as the operational accuracy. It is.

The operation accuracy calculation unit 154 calculates the operation accuracy by integrating the plurality of index values P ₁ to P ₄ using the hierarchical NN illustrated in FIG. The operation accuracy calculation unit 154 inputs the index values P ₁ to P ₄ and the digitized current business classification to the hierarchical NN, and calculates the operation accuracy based on the operation accuracy classification results output from the hierarchical NN. , obtain the operation precision. Classifications of operation accuracy include, for example, Excellent, Good, Average, Fair, and Poor.

[Operation accuracy calculation process]
FIG. 8 is a flowchart showing the processing procedure of the operation accuracy calculation process according to the embodiment. As shown in FIG. 8, first, in the processing device 10, the operation log acquisition unit 152 performs an operation log acquisition process in which the operation log of the system operation by the worker is detected and acquired (step S1).

The index calculation unit 153 performs an index calculation process of calculating a plurality of index values related to rework as index values related to operation accuracy based on the operation log (step S2).

The operation accuracy calculation unit 154 performs operation accuracy calculation processing that integrates the plurality of index values calculated by the index calculation unit 153 and calculates the operation accuracy according to the current work of the worker who is the system operator. (Step S3).

The processing device 10 outputs the operation accuracy calculated by the operation accuracy calculation unit 154 (step S4). The processing device 10 performs processing such as displaying an alert to a worker who attempts to operate the system when the operation accuracy in an important task is lower than a predetermined value.

[Indicator calculation process]
Next, an example of the processing procedure of the index calculation process (step S2) will be described. FIG. 9 is a flowchart illustrating an example of the processing procedure of the index calculation process.

As shown in FIG. 9, the index calculation unit 153 acquires the operation log to be processed from the storage unit 14 (step S11), and refers to the operation log. The index calculation unit 153 determines whether the operation target operated by the worker is an executable GUI based on the operation log (step S12).

If the operation target operated by the worker is an executable GUI (step S12: Yes), the index calculation unit 153 determines whether the information on the GUI element is classified as a rework operation ( Step S13).

When the information on the GUI element is classified as a rework operation (step S13: Yes), the index calculation unit 153 adds the line number of the operation log classified as a rework operation and this operation to the rework detection table 1421. Line data including the log occurrence time is inserted (step S14). The index calculation unit 153 determines whether it is the index calculation timing (step S15).

If the operation target operated by the worker is not an executable GUI (step S12: No), if the information on the GUI element is not classified as a rework operation (step S13: No), or if it is not the index calculation timing ( Step S15: No), the index calculation unit 153 returns to step S11.

If it is the index calculation timing (step S15: Yes), the index calculation unit 153 calculates the index value P ₁ (frequency of occurrence of rework operation) using equation (1) (step S16).

Also, another example of the processing procedure of the index calculation process (step S2) will be described. FIG. 10 is a flowchart showing another example of the processing procedure of the index calculation process.

As shown in FIG. 10, the index calculation unit 153 acquires the operation log to be processed from the storage unit 14 (step S21), and refers to the operation log. The index calculation unit 153 determines whether the operation in the operation log is a keyboard input (step S22).

If the operation in the operation log is a keyboard input (step S22: Yes), the index calculation unit 153 includes the line number of the operation log, the time of occurrence of this operation log, and the input key in the typo detection table 1422. Insert row data (step S23). The index calculation unit 153 determines whether it is the index calculation timing (step S24).

If the operation of the operation log is not a keyboard input (step S22: No), or if it is not the index calculation timing (step S24: No), the index calculation unit 153 returns to step S21.

If it is the index calculation timing (step S24: Yes), the index calculation unit 153 calculates the index value P ₂ (frequency of occurrence of typographical errors) using equation (2) (step S25).

Also, another example of the processing procedure of the index calculation process (step S2) will be described. FIG. 11 is a flowchart showing another example of the processing procedure of the index calculation process.

As shown in FIG. 11, the index calculation unit 153 acquires the operation log to be processed from the storage unit 14 (step S31), and refers to the operation log. The index calculation unit 153 determines whether the active window is different from the previous active window based on the operation log (step S32).

If the active window is different from the previous active window (step S32: Yes), the index calculation unit 153 adds the line number of the operation log, the time of occurrence of this operation log, and the switched active window to the active window switching detection table 1423. The line data including window identification information is inserted (step S33). The index calculation unit 153 determines whether it is the index calculation timing (step S34).

If the active window is the same as the previous active window (step S32: No), or if it is not the index calculation timing (step S34: No), the index calculation unit 153 returns to step S31.

If it is the index calculation timing (step S34: Yes), the index calculation unit 153 calculates the index value P ₃ (frequency of active window switching without operation and/or reference) using equation (3) (step S35).

Further, as an index calculation process (step S2), the index calculation unit 153 refers to the operation log and the active window switching detection table 1423, and calculates the index value P ₄ (continuation of current work) using equation (4). time).

The index calculation unit 153 calculates at least two or more of the index values P ₁ to P ₄ by performing two or more of the four processing procedures of the index calculation process described above.

[Effects of embodiment]
FIG. 12 is a diagram explaining the conventional method. As shown in FIG. 12, in the conventional method, the state (stress amount) of a business worker (office worker) involved in system operations is calculated from a PC operation log. In conventional methods, there is no index value related to operational errors that are directly linked to operational accuracy, and furthermore, only the correlation between each individual index and the state (amount of stress) is determined. Accordingly, in the conventional method, it is not possible to take into account that the index value 1 is important in a certain work situation, and it may not be possible to appropriately calculate the state of the worker depending on the work situation.

FIG. 13 is a diagram illustrating a processing method according to the embodiment. As shown in FIG. 13, in the embodiment, the processing device 10 calculates an index value P ₁ (frequency of occurrence of rework operations), an index value P ₂ (frequency of occurrence of typographical errors), an index value P ₃ (frequency of active window switching without operation and/or reference) and index value P ₄ (duration time of current task) are calculated ((1) in FIG. 13).

Then, the processing device 10 receives input of the current business status (business classification) ((2) in FIG. 13), and receives each index value P ₁ to P ₄ and the current business status (business classification). The operation accuracy is calculated based on ((3) in FIG. 13).

If the current job involves a lot of text input and you want to calculate the status of the worker as a risk of human error, an index of the frequency of recent typos is important. Regarding this, the processing device 10 newly sets each index value P ₁ to P ₄ indicating the occurrence of an operation related to rework that is directly connected to the operation accuracy, and calculates each index value P ₁ to P ₄ .

For the purpose of preventing human errors, it is necessary to calculate the status of workers in their "current work" based on multiple index values. Regarding this, the processing device 10 integrates a plurality of index values P ₁ to P ₄ based on the operation log, and calculates the operation accuracy according to the worker's current work. Therefore, according to the processing device 10, the operational accuracy of the worker can be appropriately calculated.

At this time, the processing device 10 integrates the plurality of index values by calculating a weighted sum for each index value for the plurality of index values P ₁ to P ₄ . The processing device 10 uses, as weights, weights that correspond to the current business situation and are set for each of the index values P ₁ to P ₄ . Alternatively, the processing device 10 uses a hierarchical NN that has learned in advance the relationship between the evaluation of operation accuracy and the plurality of index values P ₁ to P ₄ to evaluate the operation accuracy by integrating the plurality of index values P ₁ to P ₄ . Calculate. This hierarchical NN provides each index value and the current business situation as an input layer, and uses the value of the output layer as the operation accuracy.

Thereby, the processing device 10 can appropriately calculate the operational accuracy, which varies depending on the work situation of the worker. In other words, the processing device 10 changes the important index depending on the business situation by using weights for each of the index values P ₁ to P ₄ corresponding to the business situation or by using a hierarchical NN. Even in the case of a worker's operation, it is possible to appropriately calculate the operating accuracy of the worker. Unlike conventional methods, the processing device 10 clarifies the measure of operation accuracy itself.

In this manner, the processing device 10 can appropriately acquire the operational accuracy of the business worker who is the system operator in the business that is currently being performed.

According to the processing device 10, by making it possible to obtain the operational accuracy according to the work situation, if the operational accuracy in an important work is lower than a predetermined value, the processing device 10 can notify the worker who tried to operate the system. Various solutions such as displaying alerts can be realized. This can greatly contribute to preventing human errors and improving business continuity.

[About the system configuration of the embodiment]
Each component of the processing device 10 is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distributing and integrating the functions of the processing device 10 is not limited to what is shown in the diagram, and all or part of it can be functionally or physically distributed in arbitrary units depending on various loads and usage conditions. It can be configured to be distributed or integrated.

Further, all or any part of each process performed in the processing device 10 may be realized by a CPU, a GPU (Graphics Processing Unit), or a program that is analyzed and executed by the CPU or GPU. Moreover, each process performed in the processing device 10 may be realized as hardware using wired logic.

Furthermore, among the processes described in the embodiments, all or part of the processes described as being performed automatically can also be performed manually. Alternatively, all or part of the processes described as being performed manually can also be performed automatically using known methods. In addition, the information including the processing procedures, control procedures, specific names, and various data and parameters described above and illustrated can be changed as appropriate, unless otherwise specified.

[program]
FIG. 14 is a diagram illustrating an example of a computer that implements the processing device 10 by executing a program. Computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These parts are connected by a bus 1080.

The memory 1010 includes a ROM 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as BIOS (Basic Input Output System). Hard disk drive interface 1030 is connected to hard disk drive 1090. Disk drive interface 1040 is connected to disk drive 1100. For example, a removable storage medium such as a magnetic disk or an optical disk is inserted into disk drive 1100. Serial port interface 1050 is connected to, for example, mouse 1110 and keyboard 1120. Video adapter 1060 is connected to display 1130, for example.

The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the processing device 10 is implemented as a program module 1093 in which code executable by the computer 1000 is written. Program module 1093 is stored in hard disk drive 1090, for example. For example, a program module 1093 for executing processing similar to the functional configuration of the processing device 10 is stored in the hard disk drive 1090. Note that the hard disk drive 1090 may be replaced by an SSD (Solid State Drive).

Further, the setting data used in the processing of the embodiment described above is stored as program data 1094 in, for example, the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads out the program module 1093 and program data 1094 stored in the memory 1010 and the hard disk drive 1090 to the RAM 1012 as necessary and executes them.

Note that the program module 1093 and the program data 1094 are not limited to being stored in the hard disk drive 1090, but may be stored in a removable storage medium, for example, and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and the program data 1094 may be stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.). The program module 1093 and program data 1094 may then be read by the CPU 1020 from another computer via the network interface 1070.

Although the embodiments applying the invention made by the present inventor have been described above, the present invention is not limited by the description and drawings that form part of the disclosure of the present invention according to the present embodiments. That is, all other embodiments, examples, operational techniques, etc. made by those skilled in the art based on this embodiment are included in the scope of the present invention.

10 processing device 11 input section 12 output section 13 communication section 14 storage section 15 control section 141 operation log 142 detection table 151 business system 152 operation log acquisition section 153 index calculation section 154 operation accuracy calculation section 1421 rework detection table 1422 typo detection Table 1423 Active window switching detection table

Claims

an acquisition unit that acquires an operation log of system operations by an operator;
a first calculation unit that calculates a plurality of index values regarding rework as index values regarding operation accuracy based on the operation log;
a second calculation unit that integrates the plurality of index values to calculate operation accuracy according to the operator's current work;
A processing device comprising:
The first calculation unit calculates at least two or more of the following: the frequency of occurrence of rework operations, the frequency of switching active windows without operation and/or reference, the frequency of occurrence of typographical errors, and the duration of the current task. The processing device according to claim 1, wherein the processing device calculates the index value as the index value.
The second calculation unit integrates the plurality of index values by calculating a weighted sum of each index value for the plurality of index values,
2. The processing device according to claim 1, wherein the second calculation unit uses a weight corresponding to the current business situation, which is set for each of the index values.
The second calculation unit is a hierarchical neural network that has learned in advance the relationship between the evaluation of operation accuracy and the plurality of index values, and receives each index value and the current business situation as an input layer, 2. The processing device according to claim 1, wherein the processing accuracy is calculated by integrating the plurality of index values using a hierarchical neural network in which the operation accuracy is a value of an output layer.
A processing method executed by a processing device, comprising:
a step of detecting an operation log of system operations by an operator;
a step of calculating a plurality of index values regarding rework as index values regarding operation accuracy based on the operation log;
integrating the plurality of index values to calculate operation accuracy according to the operator's current work;
A processing method characterized by comprising.
detecting an operation log of system operations by an operator;
calculating a plurality of index values regarding rework as index values regarding operation accuracy based on the operation log;
integrating the plurality of index values to calculate operation accuracy according to the operator's current work;
A processing program that causes a computer to execute.