Information processing device and information processing method
The information processing device and method address the challenge of detecting deviations between operator and manual operations by dividing and analyzing logs to identify discrepancies, facilitating business rule-compliant operations and manual optimization.
Patent Information
- Application Number
- PCT/JP2024/007420
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-02-28
- Publication Date
- 2025-09-04
AI Technical Summary
Conventional technologies fail to analyze deviations between operator operations and established business procedures, leading to potential mistakes or incidents due to operations deviating from business rules, as they only consider normal operator actions and not manual guidelines.
An information processing device and method that divides operator and manual operation logs into elements, extracts common and deviating elements, and generates estimation results to identify discrepancies, enabling business analysis that considers business rules.
Enables detection of deviations between manual and actual operations, allowing for optimization of business manuals and prevention of mistakes by identifying unnecessary or inappropriate procedures.
Smart Images

Figure JP2024007420_04092025_PF_FP_ABST
Abstract
Description
Information processing device and information processing method
[0001] The embodiments relate to an information processing device and an information processing method.
[0002] There is a technology that collects operation logs from the terminals used by operators and visualizes and analyzes the multiple operation logs acquired from the daily work of multiple or a single operator (see, for example, Patent Literature 1). Using the results of this analysis, it is possible to understand the current state of work, such as "what kind of work is being performed, how long it takes, and what procedures (operations) are being used," which is a prerequisite for considering business improvement measures. Therefore, it is possible to apply RPA (Robotic Process Automation) and business process management (BPM) and other business improvement activities.
[0003] International Publication No. 2022 / 176134
[0004] Taisuke Wakasugi et al., "Operation Process Classification-Based Business Design Support Technology Contributing to DX Promotion," [online], NTT Technical Journal, [Retrieved February 19, 2024], Internet <URL: https: / / journal.ntt.co.jp / article / 18032>
[0005] To improve business operations, not only the current status of the operations but also information on established business procedures and business rules is important. If an operator's operations deviate from the business rules described in the manual, it may lead to mistakes or incidents. Furthermore, if the manual does not match the actual situation on-site, the manual must be revised. However, conventional technology only analyzes the operation logs of the operations that the operator normally performs, making it difficult to detect deviations between operator operations and manual operations. The present invention has been made in light of the above circumstances, and its purpose is to provide an information processing device and information processing method that can realize business analysis that takes business rules into account.
[0006] An information processing apparatus according to an embodiment includes an operator operation acquisition unit, a manual operation acquisition unit, a dividing unit, a first extraction unit, and a second extraction unit. The operator operation acquisition unit acquires an operator operation log related to operations of software and devices by an operator. The manual operation acquisition unit acquires a manual operation log related to operations of the software and the devices in accordance with a work procedure indicated in a manual. The dividing unit divides each of the operator operation log and the manual operation log into a plurality of elements. The first extraction unit extracts, from the elements included in the operator operation log, a first element that is a common element sharing the same work and that differs from the work order in the manual operation log. The second extraction unit extracts, from the elements included in the manual operation log, a second element that has not been executed in the operator operation log.
[0007] According to the embodiment, it is possible to provide an information processing device and an information processing method that can realize business analysis that takes business rules into account.
[0008] FIG. 1 is a block diagram showing an example of the overall configuration of a business system according to this embodiment. FIG. 2 is a block diagram showing an example of an information processing device according to this embodiment. FIG. 3 is a flowchart showing an example of the operation of the information processing device according to this embodiment. FIG. 4 is a diagram showing a specific example of comparison processing in an operation log comparison unit according to this embodiment. FIG. 5 is a diagram showing a specific example of comparison processing in an operation log comparison unit according to this embodiment. FIG. 6 is a diagram showing a manual operation log and an operator operation log before being divided into elements. FIG. 7 is a diagram showing an example of a first element determined from the manual operation log and the operator operation log. FIG. 8 is a diagram showing an example of a second element determined from the manual operation log and the operator operation log. FIG. 9 is a block diagram showing the hardware configuration of an information processing device according to this embodiment.
[0009] Each embodiment will be described below with reference to the drawings. Each embodiment illustrates an apparatus or method for embodying the technical idea of the invention. The drawings are schematic or conceptual. Hereinafter, the same reference numerals are used to designate components having substantially the same functions and configurations. The numbers following the letters that make up the reference numerals are used to distinguish between elements that are referred to by the reference numerals containing the same letters and that have similar configurations. When there is no need to distinguish between elements indicated by reference numerals containing the same letters or numbers, these elements will be referred to by reference numerals containing only letters or numbers.
[0010] An example of the overall configuration of a business system to which processing by an information processing device according to this embodiment is applied will be described with reference to Fig. 1. The business system 1 according to this embodiment includes an information processing device 10, an operation terminal 20 that collects operation logs, and a log collection unit 30 that acquires each operation log. It is assumed that the business system 1 is provided as a system that can be used in common by multiple operators.
[0011] The operation terminal 20 is, for example, a personal computer (PC) or a tablet terminal, and an operator inputs data into or operates the software.
[0012] The log collection unit 30 collects, as an operation log, historical information for each operation corresponding to the operator's input to the software and the operation of devices such as a mouse and keyboard. Furthermore, the log collection unit 30 may collect the operation log as an operation process organized into specific units for each task. The log collection unit 30 may collect the operation log at any timing. For example, the operation log may be collected collectively at predetermined time intervals, or the operation log may be collected continuously while the operator is logged in to the operation terminal 20 or while specific software is running. In this embodiment, it is assumed that the log collection unit 30 collects an operation log resulting from an operator performing work without paying attention to the manual (hereinafter referred to as an operator operation log) and an operation log resulting from an operator performing work in accordance with the manual while referring to the manual (hereinafter referred to as a manual operation log).
[0013] The information processing device 10 compares the operator operation log with the manual operation log, and generates an estimation result that estimates operation processes in which the operator's work procedures deviate from the work procedures specified in the manual.
[0014] Next, details of the information processing device 10 according to this embodiment will be described with reference to the block diagram of Fig. 2. The information processing device 10 includes an operator operation acquisition unit 101, a manual operation acquisition unit 102, a division unit 103, an operation log comparison unit 104, a first extraction unit 105, a second extraction unit 106, an output unit 107, and a storage unit 108.
[0015] The operator operation acquisition unit 101 acquires an operator operation log of operations performed by an operator (user) without paying attention to the manual. The operator operation log includes the work procedures in which the operator operated software, devices, etc.
[0016] The manual operation acquisition unit 102 acquires a manual operation log relating to the operation of software and devices performed in accordance with the work procedures indicated in the manual.
[0017] The dividing unit 103 divides each of the operator operation log and the manual operation log into a plurality of elements. The dividing method may be, for example, dividing into a plurality of elements according to the similarity of the tasks, or dividing by each break in the operation. A break in the operation is a processing unit that can separate an operation, such as when the cursor is moved with the mouse and the operation is stopped, when a click is made, or when an operation on a specific window or GUI component is completed.
[0018] The operation log comparison unit 104 compares the operator operation log with the manual operation log, and determines corresponding elements between the operator operation log and the manual operation log according to the similarity of the elements.
[0019] The first extraction unit 105 extracts a first element from among the elements included in the operator operation log, which is a common element having a common task, and which differs from the task sequence in the manual operation log. The second extraction unit 106 extracts a second element from among the elements included in the manual operation log, which is not executed in the operator operation log.
[0020] The output unit 107 outputs the estimation results relating to the first and second elements to the outside. The storage unit 108 stores the estimation results relating to the first and second elements.
[0021] Next, an example of the operation of the information processing device 10 will be described with reference to the flowchart in Fig. 3. In step SA1, the operator operation acquisition unit 101 acquires an operator operation log. It is assumed that the operator operation log is acquired from the log collection unit 30 shown in Fig. 1, but it may also be acquired directly from the operation terminal 20.
[0022] In step SA2, the manual operation acquisition unit 102 acquires a manual operation log. The manual operation log is assumed to be acquired from the log collection unit 30 shown in FIG.
[0023] In step SA3, the dividing unit 103 divides each of the operator operation log and the manual operation log into a plurality of elements. For example, as in Patent Document 1, the above-mentioned prior art document, the division unit 103 evaluates the similarity of the operation contents (task contents) for each element according to the similarity of the operation contents using a vector. If the similarity of the operation contents is equal to or greater than a threshold, the division unit 103 groups multiple operations into an "element" representing a single task unit, and divides each of the operator operation log and the manual operation log. Note that the division unit 103 may determine that operations on GUI components in windows with the same title are one element. Alternatively, the division unit 103 may divide the log by the interval between operations.
[0024] In step SA4, the operation log comparison unit 104 compares the operator operation log with the manual operation log and determines corresponding elements between the operator operation log and the manual operation log according to the similarity of the elements. The method of determining corresponding elements may be, for example, the method shown in step SA3.
[0025] In step SA5, the first extraction unit 105 determines, as common elements, elements that perform the same or similar tasks between the operator operation log and the manual operation log, i.e., elements whose task content is equal to or greater than a threshold. A common element is a task unit in which tasks are common between the operator operation log and the manual operation log. Specifically, as in step SA3, the first extraction unit 105 sequentially compares, for example, elements in the operation log and the manual operation log, and calculates vectors of words that appear on the screen. The first extraction unit 105 may determine a common element if the cosine distance similarity of the vectors is equal to or greater than a threshold. Alternatively, corresponding elements may be determined to be common elements if their titles indicate operations on the same window or operations on the same area of the same GUI component.
[0026] In step SA6, the first extraction unit 105 extracts, from the common elements, elements in the operator operation log that are in a different order from the work order in the manual operation log as first elements. Because the extracted first elements are common elements, they have a high similarity in terms of content of the operation logs. However, because the work order differs from the manual, the similarity in the operation process is low. In other words, the similarity in the work order is assumed to be below a threshold. In other words, the first elements are elements that cause a discrepancy between the work content of the manual operation and the work content of the operator operation. In step SA7, the second extraction unit 106 extracts, from the elements included in the manual operation log, elements that have not been performed in the operator operation log as second elements. The extracted second elements are work (operations) described in the manual but that the operator has not performed for some reason, and are elements that cause a discrepancy between the work content of the manual operation and the work content of the operator operation.
[0027] In step SA8, the output unit 107 outputs the estimation results (the first element and the second element). The acquired operator operation log and manual operation log may also be output. The storage unit 108 may store the analysis results together with the operator operation log.
[0028] Next, a specific example of the comparison process in the operation log comparison unit 104 will be described with reference to Fig. 4 and Fig. 5. Fig. 4 shows a GUI component 40 on a registration screen for an element to be compared in the operator operation log, and a GUI component 45 for an element in the manual operation log that corresponds to the element to be compared. The operation log comparison unit 104 determines whether the work contents are the same based on whether the same item has been entered or not entered on the common GUI component.
[0029] 4, the items "Registration ID," "Name," "Prefecture," "Address," and "Service Type" are displayed, and the input contents are different between GUI component 40 and GUI component 45. However, although the input contents themselves are different, the items that have been input match, and therefore the operation log comparison unit 104 determines that the work contents match between the elements of the operator operation log and the manual operation log.
[0030] 5 is similar to FIG. 4 and shows an example of a GUI component 40 in an operator operation log and a GUI component 45 in a manual operation log. Compared to FIG. 4, the GUI component 45 has an unfilled item 51. Specifically, "Name" and "Address" have not been filled in. Therefore, the operation log comparator 104 determines that the work contents differ between the elements in the operator operation log and the manual operation log.
[0031] Next, a specific example of the extraction process for the first element and the second element will be described with reference to FIGS. 6 to 8 . FIG. 6( a) shows the manual operation log 60 and the operator operation log 65 before they are divided into elements in chronological order. FIG. 6( b) shows the manual operation log 60 and the operator operation log 65 after they have been divided into elements according to work procedures by the operation log comparison unit 104. In this example, the manual operation log 60 is divided into four elements indicating the work procedure of "a → b → c → a," and the operator operation log 65 is divided into six elements indicating the work procedure of "d → a → d → b → a → d." Here, elements indicated by the same alphabet indicate the same work or the same type of work. In other words, element "a" in the manual operation log 60 and element "a" in the operator operation log 65 are elements indicating the same work or the same type of work.
[0032] Next, FIG. 7 shows the first element determined from the manual operation log 60 and the operator operation log 65 shown in FIG. 6 . FIG. 7( a ) is similar to FIG. 6( b ), and shows elements associated by the operation log comparison unit 104. Here, element “d” is a task performed only in the operator operation log 65 and is considered to be an interrupt task different from the manual, and therefore is not an element that causes a discrepancy in the task content. Furthermore, the common elements are element “a” and element “b.” Here, element “b” is included in both the manual operation log 60 and the operator operation log 65, but the operation procedure (processing order) in the operator operation log 65 is “a → d → b,” which is a different operation procedure from the operation procedure “a → b” in the manual operation log 60. Therefore, the first extraction unit 105 extracts element “b” as the first element 71. Note that when an element includes operations that are multiple processing units, a common element in which the order (process) of each operation is different may be determined as the first element 71. For example, if the element "b" is an element consisting of multiple operations "b1, b2, b3," and the manual operation log 60 shows a process of "b1 → b2 → b3," while the operator operation log 65 shows a process of "b1 → b3 → b2," the processes of the operations in the common element "b" are different. Therefore, the determination unit 105 may determine the common element "b" as the first element 71.
[0033] Next, Fig. 8 shows second elements determined from the manual operation log 60 and the operator operation log 65 shown in Fig. 6. Fig. 8(a) is similar to Fig. 6(b), and shows elements associated with each other by the operation log comparison unit 104. The second extraction unit 106 extracts, as a second element 81, element "c", which is an element not executed in the operator operation log 65, from among the elements included in the manual operation log 60.
[0034] Next, an example of the hardware configuration of the information processing device 10 according to this embodiment will be described with reference to the block diagram shown in FIG.
[0035] As shown in FIG. 9, the information processing device 10 includes, for example, a central processing unit (CPU) 11, a read-only memory (ROM) 12, a random access memory (RAM) 13, a communication interface 14, and a storage 15.
[0036] The CPU 11 is an integrated circuit capable of executing various programs and controls the overall operation of the information processing device 10. The ROM 12 is, for example, a non-volatile semiconductor memory and stores programs and control data for controlling the information processing device 10. The RAM 13 is, for example, a volatile semiconductor memory and is used as a work area for the CPU 11. The communication interface 14 is, for example, an input / output component for exchanging information with the outside, such as a USB, an HDMI (registered trademark), or a network interface. The storage 15 is a non-volatile storage device. The storage 15 stores system software and the like for the information processing device 10. The CPU 11 may also be called a "processor."
[0037] In the above-described embodiments, the CPU 11 of the information processing device 10 may be another circuit (or processor). For example, the information processing device 10 may include an MPU (Micro Processing Unit) or the like instead of a CPU. Each of the processes described in each embodiment may be realized by dedicated hardware. The processes of the information processing device 10 may be a mixture of processes executed by software and processes executed by hardware, or may be only one of them.
[0038] According to the present embodiment described above, the operator operation log and the manual operation log are each divided into elements, and a first element that differs from the operation sequence in the manual operation log is extracted from among the elements included in the operator operation log, which share common tasks. Furthermore, a second element that has not been executed in the operator operation log is extracted from among the elements included in the manual operation log. Estimation results for the first element and the second element are generated. This makes it possible to detect discrepancies between the procedures described in the manual and the procedures performed by the operator. Furthermore, by referring to the estimation results, unnecessary procedures and procedures that do not conform to the actual situation on-site can be discovered in the current business manual, enabling the manual to be optimized. Furthermore, if a first element or an element not described in the manual is executed in the operator operation log, inappropriate procedures in the operator's operations can be identified, thereby preventing mistakes. As a result, business analysis that takes business rules into account can be realized.
[0039] The present invention is not limited to the above-described embodiments, and various modifications can be made in the implementation stage without departing from the spirit of the invention. Furthermore, the embodiments may be implemented in appropriate combinations, in which case the combined effects can be obtained. Furthermore, the above-described embodiments include various inventions, and various inventions can be extracted by combining selected elements from the disclosed elements. For example, if the problem can be solved and the desired effect can be obtained even if some elements are deleted from all elements shown in the embodiments, the configuration from which these elements are deleted can be extracted as an invention.
[0040] DESCRIPTION OF SYMBOLS 1...Business system 10...Information processing device 11...CPU 12...ROM 13...RAM 14...Communication interface 15...Storage 20...Operation terminal 30...Log collection unit 40, 45...GUI component 51...Item 60...Manual operation log 65...Operator operation log 71...First element 81...Second element 101...Operator operation acquisition unit 102...Manual operation acquisition unit 103...Splitting unit 104...Operation log comparison unit 105...First extraction unit 106...Second extraction unit 107...Output unit 108...Storage unit
Claims
1. An information processing device comprising: an operator operation acquisition unit that acquires an operator operation log related to operations of software and devices by an operator; a manual operation acquisition unit that acquires a manual operation log related to operations of the software and the devices in accordance with work procedures indicated in a manual; a division unit that divides each of the operator operation log and the manual operation log into a plurality of elements; a first extraction unit that extracts, from the elements included in the operator operation log, a first element that is a common element in which the work is common, and that differs from the work order in the manual operation log; and a second extraction unit that extracts, from the elements included in the manual operation log, a second element that is not executed in the operator operation log.
2. The information processing device according to claim 1, wherein the first extraction unit extracts elements between the operator operation log and the manual operation log whose similarity in work content is equal to or greater than a first threshold as the common elements, and extracts elements among the common elements whose similarity in work order is equal to or less than a second threshold as the first elements.
3. An information processing method in which an operator operation acquisition unit acquires an operator operation log related to the operation of software and devices by an operator, a manual operation acquisition unit acquires a manual operation log related to the operation of said software and said devices in accordance with the work procedures indicated in a manual, a division unit divides each of said operator operation log and said manual operation log into a plurality of elements, a first extraction unit extracts, from the elements included in said operator operation log, a first element that is common to the work and differs from the work order in said manual operation log, and a second extraction unit extracts, from the elements included in said manual operation log, a second element that is not executed in said operator operation log.
Citation Information
Patent Citations
Business support apparatus
JP2009116673A
Information processing terminal, information processing method, and information processing program
JP2020095574A
Classification device, classification method, and classification program
WO2022176134A1
Classification device, classification method, and classification program
WO2023238412A1