Information processing device and information processing method

Abstract

An information processing device according to an embodiment comprises: a monitoring unit 12 that stores information relating to the operation of a system 11 by an operator, the information stored in a storage unit 13 in association with time information; an index value detection unit 14 that uses the operation information to calculate an arbitrary index value indicating the state of the operator; a reference value creation unit 15 that uses a plurality of the index values to create a reference value corresponding to a factor of a business task performed using the system; and a relative value evaluation unit 16 that calculates a second index value from the index values and the reference value and outputs an evaluation result obtained using the second index value.

Description

Information processing device and information processing method

[0001] The present invention relates to an information processing device and an information processing method.

[0002] Various researches are being conducted to obtain and estimate the operator's state from the accumulated operation logs of the operator. For example, researches are being conducted to obtain indicators such as the operator's stress level, concentration level, operation accuracy, and hesitation from the operation logs.

[0003] For example, research is being conducted into estimating the stress level of an operator by analyzing the relationship between the rate of keystrokes and an operation log of the amount of operation (such as the number of mouse clicks) and the amount of stress (amount of salivary amylase secretion).

[0004] For example, research is being conducted to estimate the level of concentration by analyzing the relationship between operation logs of screen changes and operation amounts (such as the number of mouse clicks) and the level of concentration based on subjective evaluation. Furthermore, research is being conducted to estimate the accuracy of operations by detecting three types of rework from operation logs and integrating their occurrence frequencies.

[0005] For example, a method has been proposed for evaluating an operator's hesitation during system operation using an operation log of mouse tracking. Another method has been proposed for evaluating an operator's hesitation using information on mouse movements between the two candidates, by estimating two candidates that may be conflicts from the operation targets during system operation.

[0006] By acquiring the status of these operators, it is possible to improve operations and management according to the operator's status and reduce human error.

[0007] Y. Usami, C. Ishizawa, Y. Kageyama, and M. Shirasu, “A Study on the Relationship between Concentration State and Biological Information During PC Work,” Proceedings of the Joint Conference on Automatic Control Systems, vol. 61, pp. 25-28, Nov. 2018. M. Toba, T. Sakurai, and Y. Mori, “Correlation Analysis between Features of PC Operation Logs and Stress Levels of Office Workers,” IEICE Transactions on Electronics, Information and Communication Engineers, vol. J95-D, no. 4, pp. 747-757, Jan. 2016. M. Toba, T. Sakurai, Y. Mori, and M. Egi, “Multiple Regression Analysis between Features of PC Operation Logs and Stress Levels of Office Workers,” IPSJ Digital Practice, vol. 7, no. 1, pp. 71-79, Jan. 2016. Y. Nagai, J. Xu, and S. Sakazawa, "Analysis of the Relationship between Subjective Concentration Level and PC Operation Logs in Desk Work," Proceedings of the ITE Annual Conference, vol. 2014, no. 14-5, pp. 1-2, Sept. 2014. Hidetake Koya, Akira Kataoka, and Haruo Oishi, "A Study on Visualizing the Accuracy of System Operation Using Operation Logs," ICM, vol. 122, no. 96, pp. 1-6, Jul. 2022. Hidetake Koya, Hajime Nakajima, and Haruo Oishi, "A Study on Evaluation Methods of Indecision During System Operation," Proceedings of the IEICE General Conference, B-14-19, Mar. 2024.

[0008] In situations where the environment is fixed, such as in psychological experiments, it is possible to detect index values ​​as relatively stable absolute values.However, when attempting to detect index values ​​that show the operator's state by applying the operator's system operation log to actual system operations, it was difficult to detect index values ​​as stable absolute values ​​due to factors such as the target system, work content, and operator.

[0009] The present invention has been made in view of the above circumstances, and has an object to provide an information processing device and an information processing method that obtain a stable index value that indicates the state of an operator.

[0010] An information processing device according to a first aspect of the present invention comprises a monitoring unit that associates system operation information by an operator with time information and stores the information in a memory unit; an index value detection unit that uses the operation information to calculate an arbitrary index value that indicates the state of the operator; a reference value creation unit that uses a plurality of the index values ​​to create a reference value according to factors of the work performed using the system; and a relative value evaluation unit that calculates a second index value using the index value and the reference value and outputs an evaluation result using the second index value.

[0011] An information processing method according to a second aspect of the present invention is a method of storing operation information of a system by an operator in a memory unit in association with time information, creating a reference value according to factors of the work performed using the system using a plurality of index values ​​indicating the state of the operator, calculating the index values ​​using the operation information, calculating a second index value obtained from the index values ​​and the reference value, and outputting an evaluation result using the second index value.

[0012] According to one aspect of the present invention, it is possible to provide an information processing device and an information processing method for acquiring a stable index value indicating the state of an operator.

[0013] FIG. 1 is a diagram schematically illustrating an example of a configuration of an information processing apparatus according to an embodiment. FIG. 2 is a flowchart schematically illustrating an example of an operation of the information processing apparatus according to an embodiment. FIG. 3 is a flowchart illustrating an example of the procedure for the reference value creation process illustrated in FIG. 2. FIG. 4 is a diagram illustrating an example of the process in which a reference value creation unit calculates a group of index values ​​from a group of operation logs. FIG. 5 is a diagram illustrating an example of the process in which a reference value creation unit creates a reference value from a group of index values. FIG. 6 is a flowchart illustrating an example of the procedure for the relative value evaluation process illustrated in FIG. 2. FIG. 7 is a diagram illustrating an example of the process in which a relative value evaluation unit creates a range on an ordinal scale. FIG. 8 is a diagram illustrating another example of the process in which a relative value evaluation unit creates a range on an ordinal scale.

[0014] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An information processing apparatus and an information processing method according to an embodiment of the present invention will be described in detail below with reference to the accompanying drawings. Fig. 1 is a diagram illustrating an example of the configuration of an information processing apparatus according to an embodiment.

[0015] The information processing device 10 of this embodiment is, for example, a personal computer (PC) terminal equipped with a business system 11. The PC terminal includes at least one processor and a memory storing a program executed by the processor, and can realize various functions described below by software or a combination of software and hardware. Note that some or all of the processing by the PC terminal may be realized using hardware such as an LSI (Large Scale Integration) or an ASIC (Application Specific Integrated Circuit).

[0016] The information processing device 10 of this embodiment may be configured, for example, as a single PC terminal, or may be a virtual PC terminal configured by one or more computers on a network, or may be a mobile terminal such as a tablet terminal or a smartphone.

[0017] The information processing device 10 includes a business system 11, a monitoring unit 12, a storage unit 13, an index value detection unit 14, a reference value creation unit 15, and a relative value evaluation unit 16. The information processing device 10 may also include a communication unit, an input unit, and an output unit (not shown). The communication unit transmits and receives information data to and from the outside using a communication protocol defined by the Internet, for example, under the control of the processor. The input unit may include an information input unit such as a mouse or keyboard operated by a user (operator) of the information processing device 10, or an audio input unit such as a microphone. The output unit may include a display unit that displays visual information, a speaker that outputs audio information, or the like, under the control of the processor.

[0018] The storage unit 13 includes a program storage unit and a data storage unit. The program storage unit is configured by combining, for example, a nonvolatile memory such as a hard disk drive (HDD) or a solid state drive (SSD) as a storage medium that can be written to and read from at any time, with a nonvolatile memory such as a read only memory (ROM), and stores application programs necessary for executing various processes according to an embodiment of the present invention, in addition to middleware such as an operating system (OS).

[0019] The data storage unit is, for example, a combination of a nonvolatile memory such as an HDD or SSD as a storage medium that can be written to and read from at any time, and a volatile memory such as a RAM (Random Access Memory).

[0020] The data storage unit accumulates, for example, an operation log of the business system 11 described below. The operation log includes the type of business for which the business system 11 is used (e.g., day shift, night shift, monitoring, activation, inquiry response, etc.), operator information (e.g., ID (identifier) ​​for identifying the operator, age / generation, business experience (e.g., five years or less in the business, 20 years or more in the business, etc.), qualifications / skills, etc.), information on the business system 11 (e.g., business system name, business system functions (fault notification function, etc.), business system complexity, etc.), and time-series information in which information identifying the type of operation is associated with time information at which the operation was performed. Note that for a business system 11 having a TAM (Technology Acceptance Model) of a certain value or higher, the business system information may include the TAM value, and for a business system 11 having an SUS (System Usability Scale) of a certain value or lower, the business system information may include the SUS value.

[0021] The business system 11 is a system used to perform various tasks such as monitoring, activation, and inquiry response, and by having the hardware processor of the information processing device 10 execute application programs stored in the program memory section of the memory section 13, various functions can be realized according to the information input by the operator operating the mouse or keyboard.

[0022] The reference value creation unit 15 creates a reference value according to a task factor (or a combination of task factors) by using multiple index values ​​corresponding to a single task factor or a combination of multiple task factors. The reference value creation unit 15 can create a reference value according to the purpose of evaluation by combining factors such as operators, task systems, and task types.

[0023] For example, when creating a reference value for a specific monitoring task, the reference value creation unit 15 acquires multiple sets of operation information (operation logs) corresponding to factors that indicate that the task type is monitoring task from the storage unit 13. Furthermore, when creating a reference value for an operation using a fault notification function where the task type is monitoring task and the operation is performed by an operator with five years or less of work experience, the reference value creation unit 15 acquires multiple sets of operation information (operation logs) corresponding to all of these factors from the storage unit 13.

[0024] The reference value creation unit 15 calculates multiple index values ​​using multiple operation logs (operation log group) corresponding to the cause information, and acquires an index value group. The index values ​​used by the reference value creation unit 15 are any index values ​​that indicate the state of the operator, such as the operator's stress level, concentration level, operation accuracy, hesitation, etc. The reference value creation unit 15 may calculate and acquire index values ​​using a known method. Alternatively, the reference value creation unit 15 may acquire index values ​​that have already been calculated and stored in the storage unit 13, or index values ​​supplied from outside the information processing device 10. Alternatively, the reference value creation unit 15 may calculate multiple types of index values ​​from each operation log.

[0025] The index value data may be in a format according to the method used to calculate the index value. For example, the reference value creation unit 15 may calculate a time-series index value (time-series information of the index value) using an operation log that records a time-series operation corresponding to a predetermined business factor, or may calculate a single index value from the operation log that records a time-series operation.

[0026] The reference value creation unit 15 performs, for example, statistical processing on the acquired group of index values ​​to create a reference value. The reference value creation unit 15 transmits the created reference value to the relative value evaluation unit 16. Note that the reference value creation unit 15 may record the created reference value in the storage unit 13 in association with corresponding factor information and creation time information.

[0027] The monitoring unit 12 monitors the business system 11 and accumulates a series of operation information (operation log) in which information on operations of the business system 11 performed by an operator is associated with time information in the storage unit 13. The operation log includes, for example, operation information of the operator on the information processing device 10, input information from the operator to the business system 11, processing information of the business system 11 in response to the operator's input, and output information from the business system 11 to the operator.

[0028] For example, in accordance with the cause information instructed by the index value detection unit 14 described below, the monitoring unit 12 can record the operation information of the business system 11 in the storage unit 13 in association with the cause information instructed by the index value detection unit 14. When the monitoring unit 12 has completed recording the series of operation information of the business system 11 in the storage unit 13, it notifies the index value detection unit 14 that the saving of the operation log has been completed.

[0029] The index value detection unit 14 refers to the operation logs stored in the storage unit 13, acquires the operation logs used to create the index value, and calculates an arbitrary index value using the acquired operation logs. The index value detection unit 14 can acquire, from the storage unit 13, operation information corresponding to factor information that is set in advance or input from outside.

[0030] The index value calculated by the index value detection unit 14 is a value (single value or time-series value) indicating the state of the operator, similar to the index value used when the reference value creation unit 15 created the reference value. The index value is any index value indicating the state of the operator, such as the operator's stress level, concentration level, operation accuracy, hesitation, etc. The index value detection unit 14 can use a known method to calculate the index value. The index value detection unit 14 transmits the calculated index value and corresponding factor information to the relative value evaluation unit 16.

[0031] The index value detection unit 14 may perform statistical processing on the time-series index values ​​to convert them into a single index value, and then transmit the index value to the relative value evaluation unit 16 .

[0032] The relative value evaluation unit 16 calculates a second index value (the difference between the index value and the reference value) using the index value calculated by the index value detection unit 14 and the reference value created by the reference value creation unit 15, and outputs an evaluation result (relative value) using the second index value. Note that when the relative value evaluation unit 16 acquires time-series index values ​​from the index value detection unit 14, it may perform statistical processing on the time-series index values ​​to calculate a single index value, and use the difference between the single index value and the reference value as the second index value.

[0033] An example of the operation of the information processing apparatus of this embodiment will be described below: Fig. 2 is a flowchart showing an outline of an example of the operation of the information processing apparatus of this embodiment.

[0034] In the information processing device 10 of this embodiment, the reference value creation unit 15 first performs a reference value creation process (step SA1). The reference value created by the reference value creation process is supplied to the relative value evaluation unit 16. When the creation of the reference value is completed and no business involving the operation of the business system 11 is performed (step SA2, No), the information processing device ends the process without performing index value detection and relative value evaluation.

[0035] Once the creation of the reference value is complete, the operator operates the business system 11, and a task using the business system 11 is performed (step SA2, YES), while the operator is performing the task, the index value detection unit 14 instructs the monitoring unit 12 on the cause information of the business system 11 to be monitored. The monitoring unit 12 associates a series of operation information (operation log) corresponding to the instructed cause information with the cause information and records the associated information in the storage unit 13, and the operation log is accumulated. Upon completing recording of the operation log corresponding to the specified cause information in the storage unit 13, the monitoring unit 12 notifies the index value detection unit 14 that recording of the operation log has been completed.

[0036] Next, the index value detection unit 14 accesses the storage unit 13 to acquire an operation log corresponding to the predetermined factor information, and calculates an arbitrary index value indicating the state of the operator using the acquired operation log (step SA3). The index value detection unit 14 supplies the calculated index value to the relative value evaluation unit 16.

[0037] Next, the relative value evaluation unit 16 performs a relative value evaluation process (step SA4) using the reference value created by the reference value creation unit 15 and the index value calculated by the index value detection unit 14. The relative value evaluation unit 16 calculates a second index value using the reference value and the index value, and outputs an evaluation result (relative value) using the second index value.

[0038] Next, the reference value creation process and relative value evaluation process of the operation of the information processing device will be described in detail. Fig. 3 is a flowchart showing an example of the procedure of the reference value creation process shown in Fig. 2.

[0039] In the reference value creation process SA1, the reference value creation unit 15 filters the past operation logs based on at least one of the conditions of the task type, the operator, and the business system (step SB1). Using the multiple operation logs (operation log group) obtained by filtering, the reference value creation unit 15 calculates an index value, which is a value indicating the state of the operator, from each operation log, and obtains a group of index values ​​(step SB2).

[0040] FIG. 4 is a diagram illustrating an example of a process in which the reference value creation unit calculates a group of index values ​​from a group of operation logs.

[0041] The reference value creation unit 15 calculates an index value, which is a value indicating the operator's state (stress level, concentration level, operation accuracy, hesitation in operation, etc.), for each of the multiple (N: a positive integer of 2 or more) operation logs (operation log 1, operation log 2, ... operation log N) obtained by filtering. The index value corresponding to each operation log is, for example, time-series numerical data including a value corresponding to a time element (t), which is the task time during which the operator performed the task. In the example shown in FIG. 4 , the reference value creation unit 15 acquires a group of index values ​​including N index values ​​(index value 1, index value 2, ... index value N).

[0042] Next, the reference value creation unit 15 creates a reference value by statistical processing using the acquired index value group (step SB3). Figure 5 is a diagram for explaining an example of processing in which the reference value creation unit creates a reference value from the index value group.

[0043] 5, the reference value creation unit 15 performs arbitrary statistical processing on index values ​​(first index values), which are time-series numerical data, to obtain a single numerical value (statistical index value). Here, the reference value creation unit 15 calculates the average value of multiple values ​​included in the time-series numerical data to calculate the single numerical value. Next, the reference value creation unit 15 calculates the average value of the calculated multiple first index values ​​as the reference value.

[0044] The statistical processing used by the reference value creation unit 15 when obtaining a statistical index value from the first index value or when calculating a reference value from a statistical index value is not limited to calculating an average value, but may include processing for calculating a median, maximum value, minimum value, etc., processing for extracting characteristic values ​​from time-series numerical data, processing for calculating regularity or irregularity of time-series numerical data, etc.

[0045] Fig. 6 is a flowchart showing an example of the procedure of the relative value evaluation process shown in Fig. 2. In the relative value evaluation process SA4, the relative value evaluation unit 16 creates a range of an ordinal scale (step SC1). The relative value evaluation unit 16 can adjust the range of values ​​corresponding to each evaluation result for a scale represented by multiple evaluation results whose order has meaning (e.g., multiple evaluation results such as lowest, low, average, high, and highest).

[0046] The relative value evaluation unit 16 may adjust the range of values ​​corresponding to each ordinal scale using statistical data obtained in the process of the reference value creation process (step SA1) described above. For example, in the examples shown in Figures 4 and 5 described above, the width of the range of the evaluation results may be adjusted based on a normal distribution to which the standard deviation of the distribution of the average values ​​of the first index values ​​(statistical index values) is applied.

[0047] FIG. 7 is a diagram illustrating an example of the process by which the relative value evaluation unit creates a range of an ordinal scale. The upper graph in FIG. 7 shows an example of an index (standard deviation) of the distribution of statistical index values. The lower graph in FIG. 7 shows an example of an ordinal scale in which the width of the range of the evaluation results is adjusted based on the distribution shown in the upper graph. The horizontal axis x of the upper graph represents the standard deviation value, and for example, zero corresponds to a value equal to the reference value (average value). For example, if the distribution of statistical index values ​​is constant as shown in FIG. 7, the relative value evaluation unit 16 adjusts the width of the numerical ranges of values ​​corresponding to the five evaluation results so that they are equal.

[0048] For example, when evaluation results expressed by five ordinal scales of lowest, low, standard, high, and highest are used, the relative value evaluation unit 16 corresponds a range of −5 to −3 standard deviations to a “lowest” evaluation result, a range of −3 to −1 standard deviations to a “low” evaluation result, a range of −1 to 1 standard deviations to a “standard” evaluation result, a range of 1 to 3 standard deviations to a “high” evaluation result, and a range of 3 to 5 standard deviations to a “highest” evaluation result. The relative value evaluation unit 16 may adjust the width of the numerical range (numerical width from minimum to maximum) of the index value (second index value) corresponding to each ordinal scale according to the number and proportion of values ​​included in the range corresponding to the ordinal scale of each evaluation result, so that the numerical width from minimum to maximum corresponding to each evaluation result is equal.

[0049] 8 is a diagram illustrating another example of the process in which the relative value evaluation unit creates a range of an ordinal scale. The upper graph in Fig. 8 shows another example of an index (standard deviation) of the distribution of statistical index values. The lower graph in Fig. 8 shows an example of an ordinal scale in which the width of the range of the evaluation result is adjusted based on the distribution shown in the upper graph.

[0050] The horizontal axis x in the upper graph represents the standard deviation value, and for example, zero corresponds to a value equal to the reference value (average value). For example, if the distribution of statistical index values ​​is mountain-shaped with the reference value (average value) as a peak, as shown in Figure 8, the relative value evaluation unit 16 adjusts the width of the numerical range (numerical range from the minimum value to the maximum value) of the index value (second index value) corresponding to each ordinal scale so that it becomes a width corresponding to the number and proportion of values ​​included in the corresponding range of the standard deviation.

[0051] For example, when a scale represented by five evaluation results, minimum, low, standard, high, and maximum, is adopted, the relative value evaluation unit 16 corresponds a range of -5 to -3 standard deviations to a "minimum" evaluation result, a range of -3 to -1 standard deviations to a "low" evaluation result, a range of -1 to 1 standard deviations to a "standard" evaluation result, a range of 1 to 3 standard deviations to a "high" evaluation result, and a range of 3 to 5 standard deviations to a "highest" evaluation result. The relative value evaluation unit 16 adjusts the width of the numerical range of the index value (second index value) corresponding to each ordinal scale according to the number and proportion of values ​​included in the range corresponding to each evaluation result, and may set the numerical range from the minimum value to the maximum value corresponding to each ordinal scale so that the width of the numerical range of the index value (second index value) corresponding to the "standard" ordinal scale is the widest and the width of the numerical range of the index value (second index value) corresponding to the ordinal scale between "minimum" and "highest" is the smallest.

[0052] The relative value evaluation unit 16 adjusts the range of the ordinal scale according to factors that differ for each task, and creates an ordinal scale for each factor.

[0053] Next, the relative value evaluation unit 16 calculates the difference (second index value) by subtracting the index value from the reference value, and applies the calculated second index value to the ordinal scale to obtain an evaluation result (step SC2). At this time, if the index value acquired from the index value detection unit 14 is a time-series value, the relative value evaluation unit 16 may perform statistical processing (averaging) on ​​the time-series value to calculate a single index value, and calculate the difference by subtracting the single index value from the reference value as the second index value. Furthermore, the relative value evaluation unit 16 calculates the difference (second index value) by subtracting the corresponding index value from the reference value calculated for each factor, and obtains an evaluation result for each factor. The relative value evaluation unit 16 outputs a numerical value (relative value) indicating the evaluation result of the acquired ordinal scale.

[0054] As described above, by creating a reference value from factors that differ for each task, calculating a second index value from the reference value that corresponds to an index value indicating the operator's state using the operation log, and obtaining an evaluation result (relative value) based on an ordinal scale in which the range of the evaluation result is adjusted according to the factors, it is possible to remove differences due to task factors from the third index value and obtain a stable index value.

[0055] That is, in the information processing device of this embodiment, by relativizing the index value indicating the operator's state using the operation log, differences due to work factors are removed from the index value. Furthermore, according to the information processing device and information processing method of this embodiment, the range of the ordinal scale of the ultimately obtained evaluation result is adjusted according to the reference value used to calculate the second index value, thereby reducing fluctuations due to work factors in situations where a similar index value is expected to be obtained, thereby obtaining a stable index value (evaluation result). This makes it easy to apply evaluation using the operation log to actual work. As described above, according to this embodiment, it is possible to provide an information processing device and information processing method that obtain a stable index value indicating the operator's state.

[0056] The program according to this embodiment may be transferred in a state where it is stored in an electronic device, or may be transferred in a state where it is not stored in an electronic device. In the latter case, the program may be transferred via a network, or may be transferred in a state where it is stored in a storage medium. The storage medium is a non-transitory tangible medium. The storage medium is a computer-readable medium. The storage medium may be in any form, such as a CD-ROM or a memory card, as long as it is capable of storing the program and is computer-readable.

[0057] 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.

[0058] REFERENCE SIGNS LIST 10: Information processing device 11: Business system 12: Monitoring unit 13: Storage unit 14: Index value detection unit 15: Reference value creation unit 16: Relative value evaluation unit

Claims

1. An information processing device comprising: a monitoring unit that associates system operation information by an operator with time information and stores the information in a memory unit; an index value detection unit that uses the operation information to calculate an arbitrary index value that indicates the state of the operator; a reference value creation unit that uses a plurality of the index values ​​to create a reference value according to factors of the work performed using the system; and a relative value evaluation unit that calculates a second index value using the index value and the reference value and outputs an evaluation result using the second index value.

2. The information processing device according to claim 1, wherein said reference value creation unit creates said reference value using said operation information corresponding to a combination of said factors of at least an operator, said system, and said type of work.

3. An information processing device as described in claim 1 or claim 2, wherein the relative value evaluation unit outputs the evaluation result according to the ordinal scale corresponding to the second index value using an ordinal scale in which the numerical range of the second index value corresponding to each evaluation result is adjusted according to the factors that differ for each task.

4. An information processing method that associates system operation information by an operator with time information and stores it in a memory unit, creates a reference value according to factors of the work performed using the system using multiple index values ​​that indicate the operator's state, calculates the index value using the operation information, calculates a second index value obtained from the index value and the reference value, and outputs an evaluation result using the second index value.

Images