Information provision device, information provision method, and information provision program

Abstract

An information provision device (10) has a degree of concentration inference unit (131), a cognitive proficiency inference unit (132), and a work state evaluation unit (133). The degree of concentration inference unit (131) infers the degree to which a worker that is performing work is concentrating on the work on the basis of information about the behavior of the worker. The cognitive proficiency inference unit (132) infers the cognitive proficiency of the worker with respect to the work on the basis of the information about the behavior of the worker. The work state evaluation unit (133) infers a work state for the worker from a work efficiency that is a reference calculated from the cognitive proficiency, a work efficiency measured for the worker, and the degree of concentration.

Description

Information providing device, information providing method, and information providing program

[0001] The present invention relates to an information providing device, an information providing method, and an information providing program.

[0002] In recent years, advances in technologies such as virtual reality (VR), augmented reality (AR), and remote conferencing have made it possible for workers to collaborate with others who are not present or with AI to perform intellectual tasks (such as document creation, shogi, and programming).

[0003] In addition, a system has been proposed that quantitatively measures the level of proficiency of each worker in intellectual work when working together, automatically determines the presentation format appropriate for each worker, and presents information to support communication between workers (see, for example, Patent Document 1).

[0004] International Publication No. 2023 / 105698

[0005] Saki Tanaka, Airi Tsuji, Kaori Fujinami; "A Study on Identifying Concentrated and Non-concentrated States Using Eye-Gaze ​​Information During Silent Reading," 21st Forum on Information Science and Technology (FIT2022), J-025, Proceedings, Vol. 3, pp. 379-386

[0006] However, the conventional technology has a problem in that it is difficult to provide work support while taking into consideration the worker's concentration level.

[0007] For example, the system described in Patent Document 1 provides information in a format that corresponds to the worker's level of skill in the task. However, task performance is affected not only by the worker's level of skill in the task, but also by the worker's state of concentration.

[0008] For example, even if a worker is highly skilled and there is no problem with the quality of their work, there are cases where the worker is in a state of excessive concentration, and if this state continues for a long time, they accumulate fatigue to the point where they are unable to continue working. In such cases, the worker's performance will decline in the long term.

[0009] In order to solve the above-mentioned problems and achieve the objectives, the information providing device is characterized by having a concentration estimation unit that estimates the concentration level of the worker on the task based on information about the behavior of the worker performing the task, a cognitive proficiency estimation unit that estimates the cognitive proficiency of the worker for the task based on information about the behavior of the worker, and a work state evaluation unit that estimates the work state of the worker from a reference work efficiency calculated from the cognitive proficiency, the measured work efficiency of the worker, and the concentration level.

[0010] According to the present invention, it is possible to provide support for a work task while taking into consideration the worker's concentration level.

[0011] FIG. 1 is a diagram illustrating information presented by an information providing device. FIG. 2 is a diagram illustrating information presented by an information providing device. FIG. 3 is a diagram illustrating an example of a configuration of an information providing system according to a first embodiment. FIG. 4 is a diagram illustrating an example of a worker DB. FIG. 5 is a diagram illustrating an example of a work record DB. FIG. 6 is a diagram illustrating an example of an intervention information DB. FIG. 7 is a flowchart illustrating a processing flow of the information providing device according to the first embodiment. FIG. 8 is a diagram illustrating an example of a computer that executes an information providing program.

[0012] Hereinafter, embodiments of an information providing device, an information providing method, and an information providing program according to the present application will be described in detail with reference to the accompanying drawings. However, the present invention is not limited to the embodiments described below.

[0013] First Embodiment FIGS. 1 and 2 are diagrams illustrating information provided by an information providing device according to a first embodiment.

[0014] 1 is a user who performs a task. A collaborator is a user who performs a task together with the worker, and may be referred to as a team member, partner, or the like. A collaborator may be the worker's superior, colleague, subordinate, business partner, or the like. Alternatively, the worker may be a beginner at a task, and the collaborator may be an expert at the task.

[0015] For example, a worker performs an operation in a task, while a collaborating partner provides information to the worker via the information providing device 10. The collaborating partner provides instructions for the task or advice regarding the task to the worker.

[0016] For example, the task may be inputting data into an information device using a mouse, a keyboard, a touch panel, or a joystick. The task may also be operating a controller of an XR (AR, VR, etc.) device, inputting hand gestures, or playing a board game such as shogi.

[0017] 1 , a worker performs input work into a terminal device 20. The terminal device is an information device, such as a personal computer (PC), a smartphone, or a tablet terminal. A collaborating partner receives information via a terminal device 30.

[0018] The information providing device 10 provides information to the terminal device 20 or the terminal device 30. The information providing device 10 is connected to the terminal device 20 and the terminal device 30 via a network NW. The information providing device 10 may also function as an interface for exchanging messages between the terminal device 20 and the terminal device 30. The terminal device 20 and the terminal device 30 may be directly connected by a data communication cable or the like without using the network NW. In this case, either or both of the terminal device 20 and the terminal device 30 have the same functions as the information providing device 10.

[0019] The information providing device 10 provides information to support the work based on information about the worker. For example, the information providing device 10 estimates the worker's level of proficiency and concentration, etc., using the worker's gaze data. Based on the estimation results, the information providing device 10 intervenes to raise the worker's awareness or that of a coworker. In this way, the information providing device 10 aims to alleviate the worker's mental burden and fatigue.

[0020] 1, when it is determined that a worker is concentrating but the work is delayed, the information providing device 10 transmits a message to the terminal device 30 used by the cooperating worker to urge the worker to cooperate. The terminal device 30 displays the received message in a pop-up display.

[0021] This promotes communication between team members and awareness of problems, etc., in a work environment where a worker and a collaborator are working in different locations due to, for example, remote work, etc. Even when the worker and the collaborator are working in the same space (for example, when the terminal device 20 and the terminal device 30 are in the same room), the same effect as when the worker and the collaborator are working in different locations can be obtained.

[0022] 2, when the information providing device 10 detects a decrease in the concentration level of the worker, it transmits a message urging the worker to take a break to the terminal device 20 used by the worker. The terminal device 20 displays the received message in a pop-up display.

[0023] The thick curved lines displayed on the terminal device 20 in Fig. 1 and the terminal devices 20 and 30 in Fig. 2 indicate the trajectory of the line of sight. However, these curved lines are shown for the purpose of explanation and are not actually displayed on the screen.

[0024] [Configuration of First Embodiment] Fig. 3 is a diagram showing an example of the configuration of an information providing system according to First Embodiment. As shown in Fig. 3, the information providing system 1 includes an information providing device 10, a terminal device 20, and a terminal device 30.

[0025] The terminal device 20 outputs the information received from the information providing device 10 to the worker. The terminal device 30 outputs the information received from the information providing device 10 to a collaborating partner. For example, the terminal device 20 and the terminal device 30 display a message by a pop-up. Furthermore, the terminal device 20 and the terminal device 30 transmit the input information to the information providing device 10.

[0026] The information providing device 10 estimates the work status based on the worker's concentration level and proficiency level, and provides information corresponding to the estimated work status. The concentration level is an index that quantifies the degree of concentration of the worker on the work. The proficiency level estimated by the information providing device 10 is called the perceived proficiency level.

[0027] Here, the description will be given assuming that the work is the operation of a PC. The worker operates the PC to create documents, emails, etc. The documents include documents, presentation slides, diagrams, etc. For example, the worker creates documents by operating a mouse, keyboard, touch panel, etc. while looking at a screen displayed on the terminal device 20 by document creation software.

[0028] As shown in FIG. 3 , the information providing device 10 includes a communication unit 11 , a storage unit 12 , and a control unit 13 .

[0029] The communication unit 11 performs data communication with other devices via a network, and is, for example, a network interface card (NIC).

[0030] The storage unit 12 is a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. Note that the storage unit 12 may also be a data-rewritable semiconductor memory such as a random access memory (RAM), a flash memory, or a non-volatile static random access memory (NVSRAM).

[0031] The storage unit 12 stores an operating system (OS) and various programs executed by the information providing device 10. The storage unit 12 stores a worker DB 121, a work record DB 122, and an intervention information DB 123.

[0032] The worker DB 121 stores information about workers. Fig. 4 is a diagram showing an example of the worker DB. As shown in Fig. 4, the worker DB 121 includes a worker ID, work experience, and a previous estimated cognitive proficiency level.

[0033] The worker ID is an identifier that indicates each row in the worker DB 121. Each row in the worker DB 121 corresponds to a worker.

[0034] The work experience indicates the amount of work experience of the worker corresponding to the worker ID. Here, the work experience is the number of hours (unit: years) that each worker has performed the work.

[0035] The previous estimated cognitive proficiency value is the average value of the cognitive proficiency estimated by the information providing device 10 when the worker performed the task one time before. A worker may perform the same task multiple times. Furthermore, the cognitive proficiency may be estimated multiple times for one task.

[0036] Note that α is a symbol that represents cognitive proficiency. The symbol with a bar directly above α represents the average value of cognitive proficiency. The initial value of α is 0, and it varies within the range from 0 to 1.0.

[0037] For example, FIG. 4 shows that a worker with a worker ID of "1" has one year of work experience and the previous estimated cognitive proficiency value is zero.

[0038] Also, for example, FIG. 4 shows that a worker with a worker ID of "2" has 10 years of work experience and the previous estimated cognitive proficiency value is 0.9.

[0039] The work record DB 122 is a record of work performed by a worker. Fig. 5 is a diagram showing an example of the work record DB. As shown in Fig. 5, the work record DB 122 includes a work ID, a worker ID, a scene, a gaze path, an operation record, an operation time, and an evaluation value.

[0040] The task ID is an identifier that identifies each row in the task record DB 122. Each row in the task record DB 122 corresponds to a task. The worker ID is an identifier that identifies a worker.

[0041] 5 shows only one row as an example, records of multiple tasks are stored in the work record DB 122. Furthermore, the workers whose tasks are stored in the work record DB 122 are not limited to the workers whose cognitive proficiency levels are to be estimated.

[0042] The work record DB 122 may be used as training data for learning a model that calculates a cognitive proficiency level.

[0043] A scene is information indicating a situation in which a worker performs work. In this case, a scene is a screen on which work is performed. For example, the screen is a GUI (Graphical User Interface) of software for creating documents.

[0044] The scan path is a trace of the movement of the worker's gaze from an arbitrary time for t' seconds when looking at a scene. In the example of Fig. 5, the scan path is shown in the form of an image, but the scan path may also be shown in the form of time-series data indicating the gaze point coordinates and eye direction collected over t' seconds.

[0045] The operation record is the operation performed by the worker on the scene shown in the scene. The operation time is the time taken to perform the operation shown in the operation record.

[0046] The evaluation value is an evaluation value for the operation performed by the worker. For example, the evaluation value is calculated based on the line of sight. The evaluation value may be larger as the amount of operation by the worker (number of characters, number of figures, amount of cursor movement, etc.) increases. The evaluation value may be calculated by an external evaluation tool. The evaluation value may be manually set by the worker, a co-worker, or the like.

[0047] Note that z' is a symbol representing an evaluation value. z' takes a value ranging from 0 to 1.0. Also, s' is a symbol representing a scene. s' is, for example, an image.

[0048] 5 shows that the task with task ID "1" was performed by a worker with worker ID "3," the operation record was "character input," and the operation time was 128 seconds. Also, FIG. 5 shows that the evaluation value of the task with task ID "1" is "0.6."

[0049] The intervention information DB 123 stores information about intervention in work by the information providing device 10. Here, the information providing device 10 intervenes in the work of the worker by presenting information to the worker or a co-worker. Intervention in work by the information providing device 10 is expected to improve the worker's performance in the long term.

[0050] 6 is a diagram showing an example of the intervention information DB 123. As shown in FIG. 6, the intervention information DB 123 includes information ID, concentration level, change in concentration level, change in cognitive proficiency level, and intervention content.

[0051] The control unit 13 controls the entire information providing device 10. The control unit 13 is, for example, an electronic circuit such as a central processing unit (CPU), a micro processing unit (MPU), or a graphics processing unit (GPU), or an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0052] The control unit 13 also has an internal memory for storing programs defining various processing procedures and control data, and executes each process using the internal memory. The control unit 13 also functions as various processing units when various programs are run. For example, the control unit 13 has a concentration level estimation unit 131, a cognitive proficiency estimation unit 132, a task status evaluation unit 133, and a presentation information generation unit 134.

[0053] The concentration level estimation unit 131 estimates the concentration level of the worker on the task based on information about the behavior of the worker performing the task. Here, a method for estimating the concentration level by the concentration level estimation unit 131 will be described.

[0054] The concentration level estimation unit 131 can estimate the concentration level using a machine learning technique. For example, the concentration level estimation unit 131 performs supervised learning of a model that outputs the concentration level based on input gaze data. In this case, the supervised data is a pair of an explanatory variable based on the gaze data and a target variable representing the concentration level. For example, the model is a neural network (NN) or a support vector machine. The model may be constructed based on data of a specific worker to suit the worker, or may be constructed based on data of multiple workers to be generalizable.

[0055] The degree of concentration may be expressed as a binary value, indicating whether or not the gaze is focused. In this case, the model classifies the input gaze data into either a focused class or a non-focused class.

[0056] The concentration level may also be a continuous value based on work efficiency, etc. In this case, the model predicts the concentration level as a continuous value based on the input gaze data.

[0057] For example, the explanatory variables in the teacher data are gaze data, or the average number of gaze fixation points calculated from the gaze data. ０ The number of stops v(t) from time t to time τ is calculated as shown in equation (1). Note that u(t) is as shown in equation (2).

[0058]

[0059]

[0060] Here, x(t) and y(t) are the horizontal and vertical coordinate values ​​of the gaze point at time t, respectively. Also, r is a constant (where r>0) that defines the size of the range of coordinates that is determined as a stop. Also, the gaze point is represented by coordinates on the screen. In other words, the concentration level estimation unit 131 calculates the horizontal and vertical coordinate values ​​of the gaze point at time t. ０ If the range of movement from the coordinates of the gaze point at the time t is less than r, it is determined that the object is stationary.

[0061] The concentration level in the training data may be subjectively determined by the worker at any time during the work, or may be determined based on the work efficiency value at any time during the work, the work speed at any time during the work, or the like.

[0062] The explanatory variables are not limited to those described here, and may be any information relating to the behavior of the worker. For example, the concentration level estimation unit 131 uses feature amounts extracted from gaze data as explanatory variables.

[0063] For example, the concentration level estimation unit 131 can extract, from the gaze data, one or a combination of the following features: the number of saccades (rapid eye movements that occur when looking at an object), the saccade distance, the gaze fixation time, the number of gaze fixations, the gaze point coordinates, the gaze movement amount, and the change in pupil diameter. Furthermore, the concentration level estimation unit 131 may use, as explanatory variables, values ​​obtained by statistically processing the extracted features. For example, the statistical processing may involve calculating an average or sum within a certain time period.

[0064] Furthermore, the concentration level estimation unit 131 may construct a model that estimates the concentration level as a continuous value using the amount of change in information related to the worker's behavior.

[0065] The explanatory variables of the model may also include the time elapsed since the start of the task, allowing the estimation results of the model to reflect trends such as the tendency for concentration levels to improve immediately after the start of the task and the tendency for concentration levels to improve after a specific amount of time has passed since the start of the task.

[0066] In addition, the concentration level estimation unit 131 may treat the results of an evaluation of the worker's concentration level using annotations by a third party, etc., as a known concentration level, and construct a model using the known concentration level and information on the worker's behavior.

[0067] An example of a method for estimating the concentration level will be described below.

[0068] Example 1 (Example without machine learning) Suppose the number of stopping points in m seconds after starting work, during which the concentration level is assumed to be high (or is known to be high), is b. In this case, the concentration level estimation unit 131 calculates the number of stopping points c in T seconds before and after an arbitrary time t, and calculates the ratio of b to c as the concentration level at time t. In this case, under the assumption that c increases as the concentration level decreases, the concentration level estimation unit 131 calculates b / c as the concentration level.

[0069] Example 2 (Example without machine learning): Assume that the average dwell time for m seconds after starting a task during which the concentration level is assumed to be high (or known to be high) is d [ms]. In this case, the concentration level estimation unit 131 calculates the average dwell time e [ms] for T minutes before and after an arbitrary time t, and calculates the ratio of d to e as the concentration level at time t. In this case, under the assumption that e decreases as the concentration level decreases, the concentration level estimation unit 131 calculates e / d as the concentration level.

[0070] Example 3 (Example without machine learning): The concentration level estimation unit 131 records patterns of information about the worker's behavior (patterns of gaze trajectory, gaze point coordinates, number of stop points, stop duration, etc.) for m seconds after the start of work when the worker's concentration level is assumed to be high (or known to be high). Then, the concentration level estimation unit 131 calculates the similarity between the recorded pattern and the pattern of information about the worker's behavior acquired during actual work, and sets this similarity as the concentration level.

[0071] The concentration degree estimation unit 131 may calculate the final concentration degree by combining the values ​​calculated by the methods of Examples 1 to 3. For example, the concentration degree estimation unit 131 calculates the weighted average or weighted sum of b / c concentrated by the method of Example 1 and the similarity calculated by the method of Example 3 as the concentration degree.

[0072] Example 4 (Example without Machine Learning) When v(t) in equation (1) is greater than a threshold, the concentration level estimation unit 131 determines that the gaze is at point (x(t ０ ), y(t ０ On the other hand, if v(t) is equal to or less than the threshold, it is determined that the line of sight is not fixed, and it is assumed that the worker is not concentrating.

[0073] Example 5 (Example Using Machine Learning) The concentration level estimation unit 131 has the worker perform a task other than the actual task, and records information about the worker's behavior for m seconds for which the level of concentration and a specific concentration level value are assumed (or known). The concentration level estimation unit 131 may then use machine learning to learn pairs of information about the recorded worker's concentration level at that time and the worker's behavior, and construct an estimation model. Tasks that the worker is asked to perform include tracing geometric shapes, copying, replying to emails, etc. Note that, in this embodiment, these tasks are performed using an information device, but they may also be tasks that do not require an information device (for example, writing with a pencil on paper).

[0074] Geometric figure tracing is a task in which a person traces and draws a specified shape (circle, square, etc.). Geometric figure tracing allows the accuracy and speed of the task to be evaluated using continuous values, and also allows the change in concentration level during short, repetitive tasks to be evaluated. Geometric figure tracing also has the advantage of being less susceptible to the influence of actual work experience, as it differs from office work such as typing, and the cognitive proficiency level of the worker at the start of the task is standardized to almost 0.

[0075] Transcription is a task in which the user inputs specified characters. The speed of transcription can be evaluated using a continuous value, and the accuracy of the task can be evaluated using the number of errors. Although the cognitive proficiency of each worker at the start of transcription varies from person to person, the task is close to the actual work environment, making it highly practical.

[0076] In addition, replying to emails is the task of creating a reply to an email. Although replying to emails has the disadvantage of being difficult to control the accuracy and speed, it has the advantage of being highly practical, as the work content is very similar to the actual work environment.

[0077] The cognitive proficiency estimation unit 132 estimates the cognitive proficiency of the worker for the task based on information about the worker's behavior. The cognitive proficiency estimation unit 132 can estimate the cognitive proficiency by the method described in Patent Document 1.

[0078] The cognitive proficiency estimation unit 132 estimates the worker's cognitive proficiency for the work based on first information, which is information for identifying the scene of the work, and second information, which is information about the worker performing the work.

[0079] Furthermore, for example, the first information is a scene in the work record DB 122 shown in Fig. 5. Furthermore, for example, the second information is a scan path in the work record DB 122 shown in Fig. 5.

[0080] For example, the cognitive proficiency estimation unit 132 estimates the worker's cognitive proficiency for the task by using the trajectory of the worker's gaze during the task as second information.

[0081] In addition, the cognitive proficiency estimation unit 132 can estimate the worker's cognitive proficiency for the work by using at least one of the worker's movements, the history of the worker's operations during the work, and the worker's biometric information as second information.

[0082] For example, the worker's movements are the line of sight trace in the work record DB 122. Furthermore, for example, the operation history is the work record and operation time in the work record DB 122. Furthermore, for example, the worker's biological information is the worker's body temperature, heart rate, pupils, and other vital signs.

[0083] The work state evaluation unit 133 estimates the work state of the worker from the reference work efficiency calculated from the cognitive proficiency level, the measured work efficiency, and the concentration level.

[0084] Here, when performing a task, it is thought that work efficiency changes depending on cognitive proficiency and concentration. Cognitive proficiency indicates how efficiently a worker can perform a task. Furthermore, cognitive proficiency changes depending on the situation and the details of each task as the task continues. Changes in cognitive proficiency change work efficiency. Furthermore, in situations where the situation and content of the task do not change, concentration affects work efficiency.

[0085] The work state evaluation unit 133 first measures the work efficiency, and if it is determined that the worker's work efficiency has declined, evaluates the influence of the cognitive proficiency and concentration level on the decline in work efficiency. The work state evaluation unit 133 estimates the worker's work state from the reference work efficiency calculated from the cognitive proficiency, the measured work efficiency, and the concentration level. The presentation information generation unit 134 generates information to be presented to the worker or a co-worker by referring to the intervention information DB 123 according to the result of the evaluation by the work state evaluation unit 133.

[0086] First, we will explain how the work efficiency is measured by the work state evaluation unit 133. The work state evaluation unit 133 calculates the work speed, work accuracy, and overall evaluation index as the work efficiency. Alternatively, the work state evaluation unit 133 may determine the work efficiency as a value calculated based on the work speed, work accuracy, and overall evaluation index (for example, the work time length, which is the reciprocal of the work speed, or the amount of error calculated from the accuracy).

[0087] The following describes the work speed, work accuracy, and overall evaluation index required for work efficiency.

[0088] The speed of a task is the amount of work performed within a certain period of time. For example, the speed of a task can be the length of a geometric figure that can be traced within a certain period of time, the number of characters that can be copied within a certain period of time, or the number of characters that can be typed in a reply to an email within a certain period of time.

[0089] Task accuracy is a numerical value that represents the accuracy of the task performed. For example, task accuracy can be the length of lines that overlap with the original shape when tracing a geometric shape, the number of characters that are correctly copied when copying, or the number of characters that are not corrected (not deleted with the backspace key or delete key) when replying to an email (a task with no correct answer). Task accuracy can also be evaluated by the number of mistakes. For example, the number of times the backspace key and the delete key are pressed can be used as the number of mistakes, and the smaller the number of mistakes, the larger the value of task accuracy (e.g., the reciprocal of the number of mistakes, or the inverse of the sign of the number of mistakes).

[0090] The overall evaluation index is a value calculated by combining the speed and accuracy of the work. For example, the overall evaluation index can be a weighted sum of the speed and accuracy of the work (the higher the value, the more efficient the work), or the accuracy of the work divided by the reciprocal of the speed of the work (the higher the value, the more accurate the work can be done in a short time).

[0091] The work status evaluation unit 133 may determine the work efficiency as a value calculated by combining the amount of related operations with the work speed, the work accuracy, and the overall evaluation index. For example, the work status evaluation unit 133 may determine the amount of mouse operation (the less the amount, the better the efficiency) during character input as the work efficiency.

[0092] If the difference between the reference work efficiency and the work efficiency calculated by the work state evaluation unit 133 exceeds a threshold, the presentation information generation unit 134 refers to the intervention information DB 123 and determines the content of the intervention.

[0093] For example, the presentation information generation unit 134 generates a message for intervention. The generated message is output via the output unit 22 or the input / output unit 31. That is, the presentation information generation unit 134 presents a message related to the work in accordance with the work status.

[0094] Furthermore, the presentation information generation unit 134 presents the concentration level estimated by the concentration level estimation unit 131 and the cognitive proficiency level estimated by the cognitive proficiency estimation unit 132. For example, the presentation information generation unit 134 presents the concentration level and the cognitive proficiency level as numerical values, thereby enabling the worker and the coworker to quantitatively grasp the concentration level and the cognitive proficiency level.

[0095] For example, as shown in information ID "1" in Fig. 6, when the concentration level is within a predetermined range and the fluctuation of the concentration level is smaller than the threshold value for a certain period of time (e.g., 90 minutes), the presentation information generator 134 generates a message urging the user to take a break. In this case, the intervention may be to forcibly interrupt the work.

[0096] Furthermore, for example, as shown by information ID "2" in Figure 6, if the fluctuation in concentration level over a certain period of time is greater than a threshold and the cognitive proficiency level is on the rise, the presentation information generation unit 134 will not intervene (will not generate a message). In this case, it is considered that the worker is repeating trial and error in the task, with the concentration level decreasing at the time of error and the cognitive proficiency level gradually increasing. Therefore, it is considered that the worker is in the learning phase of the task, and no intervention will be performed.

[0097] Furthermore, for example, as shown by information ID "3" in FIG. 6 , if fluctuations in concentration level greater than a threshold occur within a short period of time (e.g., 20 minutes), the presentation information generator 134 generates a message encouraging the co-worker to cooperate. If large fluctuations in concentration level occur frequently, it is determined that the environment is not conducive to concentrating and continuing the work. Therefore, it is considered possible to restore the worker's performance by intervening to improve the work environment or the work content. The intervention in this case may involve changing the work environment.

[0098] The presentation information generation unit 134 can divide the work time into certain intervals and calculate the fluctuation in the concentration level using the average and variance of the concentration level for each interval. For example, the presentation information generation unit 134 determines that the fluctuation is large when the difference in the average value for each interval is large, and determines that the fluctuation in the concentration level over a short period of time within the interval is large when the average value remains unchanged and the variance is large. The presentation information generation unit 134 may use a median and a standard deviation instead of the average value and variance. The presentation information generation unit 134 may also calculate the fluctuation in the concentration level as the differential value (difference) of the measured concentration level or the average value of the concentration level for a certain interval in the time direction.

[0099] The width of the section may be predetermined and stored as a setting, or may be set by the user (including the worker and collaborator) in advance or during use.

[0100] The presentation information generation unit 134 may also automatically adjust the width of the section. For example, the presentation information generation unit 134 may set a certain period of time (hereinafter, “duration period”) for determining whether the state in which the fluctuation in the concentration level is smaller than the threshold continues, for information ID “1” in FIG. 6 , to be shorter as the cognitive proficiency level is lower and longer as the cognitive proficiency level is higher.

[0101] The presentation information generation unit 134 may also set the duration depending on the work content. The presentation information generation unit 134 may set the duration to be short if the work is monotonous (for example, data entry in a fixed format) and long if the work is complex, such as creating a document.

[0102] The presentation information generation unit 134 may also set the duration by combining multiple pieces of biological information and taking into account the stress level and physical condition of the worker. For example, the presentation information generation unit 134 sets the duration to be shorter as the level of stress of the worker increases.

[0103] Furthermore, the presentation information generation unit 134 may assume that the higher the cognitive proficiency level, the smaller the fluctuation in the concentration level, and set the threshold for the fluctuation in the concentration level in information ID "1" in FIG. 6 to be smaller the higher the cognitive proficiency level. The smaller the threshold, the smaller the fluctuation that the presentation information generation unit 134 determines that intervention is necessary, and generates a message. In other words, the smaller the threshold, the more sensitive the determination of the presentation information generation unit 134 is to fluctuations in the concentration level.

[0104] Furthermore, even if the conditions shown in FIG. 6 are satisfied, the information providing device 10 may not intervene if any of the following conditions is satisfied.

[0105] For example, if a worker whose cognitive proficiency level is higher than the threshold has a moderate level of concentration (within a predetermined range) and is not fluctuating (less than the threshold), the information providing device 10 will not intervene, as it is considered that the worker is continuing to work stably without strain.

[0106] Also, for example, if the concentration level of a worker whose cognitive proficiency level is lower than the threshold value is gradually improving (the increase over time is greater than or equal to the threshold value), the information providing device 10 will not intervene because it is considered that the concentration level is increasing as the worker becomes more skilled at the work.

[0107] Also, for example, if both the cognitive proficiency and concentration level are medium and stable (remain within a predetermined range), it is considered that the work is being continued stably without strain, and the information providing device 10 will not intervene.

[0108] 1 and 2, the information providing device 10 can display the generated message as a pop-up on the terminal device 20 or the terminal device 30. The information providing device 10 may also send the message to the worker or the collaborator via email, a chat system, a social networking service (SNS), a short message service (SMS), or the like.

[0109] Furthermore, if the worker or collaborator is wearing a smart watch, AR glasses, VR-HMD, etc., the information providing device 10 may intervene by notifying the worker using vibration, sound, video, etc. via the worn device.

[0110] 3, the configuration of the terminal device 20 will be described. As shown in FIG. 3, the terminal device 20 includes an input unit 21 and an output unit 22.

[0111] The input unit 21 receives input of data and includes an operation unit 211, a gaze measurement unit 212, and a biological information measurement unit 213.

[0112] The operation unit 211 is a device for an operator to operate, and is, for example, a mouse, a keyboard, a touch panel, a joystick, a controller for an XR device, a sensor for recognizing hand gestures, or the like.

[0113] The gaze measurement unit 212 is a device for measuring the gaze of a worker. For example, the gaze measurement unit 212 is an eye tracker. The gaze measurement unit 212 may also be a camera device such as a web camera. The gaze measurement unit 212 may also be integrated with a terminal device such as AR glasses, or may be a separate device.

[0114] The biological information measuring unit 213 is a device for measuring biological information of the worker. For example, the biological information measuring unit 213 is a wearable device worn by the worker.

[0115] The output unit 22 is a device for outputting information provided by the information providing device 10. For example, the output unit 22 is a display that displays a screen.

[0116] The terminal device 30 also has an input / output unit 31. The input / output unit 31 inputs data to the terminal device 30 and outputs data from the terminal device 30. For example, the input / output unit 31 is a display that displays a screen.

[0117] [Processing of First Embodiment] The flow of processing by the information providing device 10 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the flow of processing by the information providing device according to the first embodiment.

[0118] First, the information providing device 10 acquires information about the worker's movements, operation history, and behavior (e.g., gaze data) (step S101). The information providing device 10 can acquire each piece of information from the terminal device 20 or the storage unit 12.

[0119] Next, the information providing device 10 estimates the worker's cognitive proficiency level for the task from the acquired information (step S102).

[0120] Next, the information providing device 10 calculates a standard work efficiency from the worker's cognitive proficiency (step S103). The standard work efficiency is determined based on the worker's cognitive proficiency and does not change as the work progresses. Note that step S103 may be performed before step S102.

[0121] The information providing device 10 also calculates (measures) the current work efficiency of the worker (step S104), and calculates the current concentration level of the worker from information related to the worker's behavior (step S105).

[0122] The information providing device 10 estimates a change in the work state from the reference work efficiency, the current work efficiency, and the concentration level (step S106).The information providing device 10 then presents information according to the change in the work state (step S107).

[0123] [Effects of the First Embodiment] As described above, the information providing device 10 estimates the concentration level of a worker on a task based on information about the behavior of the worker performing the task. The information providing device 10 also estimates the cognitive proficiency level of the worker for the task based on the information about the behavior of the worker. The information providing device 10 also estimates the task state of the worker based on the reference task efficiency calculated from the cognitive proficiency level, the measured task efficiency of the worker, and the concentration level.

[0124] In this way, the information providing device 10 can intervene in a task while taking into consideration both the concentration level and the cognitive proficiency level. As a result, according to this embodiment, it is possible to provide task support while taking into consideration the concentration level of the worker.

[0125] Here, the necessity for intervention and the content of the necessary intervention vary depending on the worker's cognitive proficiency and concentration level. For example, when an expert (a worker with a high level of cognitive proficiency) has a high level of concentration, the work is progressing efficiently, but excessive concentration may be a burden, so a break or interruption of work is necessary. Also, for example, when an expert has a low level of concentration, they are not performing to their full potential and therefore need to recover their concentration by taking a break or other means. Also, for example, when a beginner (a worker with a low level of cognitive proficiency) has a high level of concentration, it is expected that their cognitive proficiency is improving, so no intervention is necessary. Also, for example, when a beginner has a low level of concentration, cooperation from a coworker or the like is required to improve their cognitive proficiency. According to this embodiment, work can be supported in a manner suited to such various cases.

[0126] Furthermore, the information about the worker's behavior is not limited to gaze data. For example, the information about the worker's behavior may be mouse movement, controller movement of XR equipment, hand movement for hand gesture input, joystick movement, cursor movement in keyboard operation, head movement trajectory, etc.

[0127] [System Configuration, etc.] The components of each device shown in the figure are conceptual functional units and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of the devices can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic. The program may be executed not only by the CPU but also by other processors such as a GPU.

[0128] Furthermore, among the processes described in the embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method.In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0129] [Program] In one embodiment, the information providing device 10 can be implemented by installing an information providing program that executes the above-described information providing process as package software or online software on a desired computer. For example, by executing the above-described information providing program on an information processing device, the information processing device can function as the information providing device 10. The information processing device referred to here includes desktop and notebook personal computers. Other information processing devices also include mobile communication terminals such as smartphones, mobile phones, and PHS (Personal Handyphone Systems), XR devices such as all-in-one AR glasses and VR goggles, and even slate terminals such as PDAs (Personal Digital Assistants) and tablet terminals.

[0130] The information providing device 10 may also be implemented as an information providing server device that provides services related to the information provision process to a client terminal device used by a worker. For example, the information providing server device may be implemented as a server device that provides an information provision service that receives information about the work and the worker as input and outputs a message for intervention. In this case, the information providing server device may be implemented as a web server or as a cloud that provides services related to the information provision process by outsourcing.

[0131] 8 is a diagram showing an example of a computer that executes an information provision program. The 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 components are connected by a bus 1080.

[0132] The memory 1010 includes a read-only memory (ROM) 1011 and a random access memory (RAM) 1012. The ROM 1011 stores a boot program such as a basic input / output system (BIOS). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to a mouse 1110 and a keyboard 1120, for example. The video adapter 1060 is connected to a display 1130, for example.

[0133] The hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, the program that defines each process of the information providing device 10 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, the program module 1093 for executing processes similar to those of the functional configuration of the information providing device 10 is stored in the hard disk drive 1090. Note that the hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0134] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0135] The program module 1093 and program data 1094 may not necessarily be stored in the hard disk drive 1090, but may also be stored in a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored in another computer connected via a network (such as a local area network (LAN) or a wide area network (WAN)). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070.

[0136] REFERENCE SIGNS LIST 1 Information provision system 10 Information provision device 11 Communication unit 12 Memory unit 13 Control unit 20, 30 Terminal device 21 Input unit 31 Input / output unit 22 Output unit 121 Worker DB 122 Work record DB 123 Intervention information DB 131 Concentration level estimation unit 132 Cognitive proficiency estimation unit 133 Work state evaluation unit 134 Presentation information generation unit 211 Operation unit 212 Gaze measurement unit 213 Biological information measurement unit

Claims

1. An information provision device comprising: a concentration level estimation unit that estimates a worker's concentration level on a task based on information about the worker's behavior while performing the task; a cognitive proficiency estimation unit that estimates the worker's cognitive proficiency for the task based on information about the worker's behavior; and a work state evaluation unit that estimates the worker's work state from a standard work efficiency calculated from the cognitive proficiency, the worker's measured work efficiency, and the concentration level.

2. The information provision device described in claim 1, characterized in that the concentration estimation unit estimates the worker's concentration level based on one or a combination of the following: number of saccades, saccade distance, gaze fixation time, number of gaze fixations, gaze point coordinates, amount of gaze movement, and amount of change in pupil diameter.

3. The information providing device according to claim 1, further comprising a presentation unit that presents a message regarding the work in accordance with the work status.

4. The information providing device according to claim 3, wherein the presentation unit presents a message urging the worker to take a break or a message urging the worker to cooperate.

5. An information providing device as described in claim 1, further comprising a presentation unit that presents the concentration level estimated by the concentration level estimation unit and the cognitive proficiency level estimated by the cognitive proficiency estimation unit.

6. An information provision method executed by an information provision device, comprising: a concentration estimation step of estimating the concentration level of a worker on a task based on information about the behavior of the worker performing the task; a cognitive proficiency estimation step of estimating the cognitive proficiency of the worker for the task based on information about the behavior of the worker; and a work state evaluation step of estimating the work state of the worker from a standard work efficiency calculated from the cognitive proficiency, the measured work efficiency of the worker, and the concentration level.

7. An information provision program that causes a computer to execute the following steps: a concentration estimation step of estimating the concentration level of a worker on a task based on information about the behavior of the worker performing the task; a cognitive proficiency estimation step of estimating the cognitive proficiency of the worker for the task based on information about the behavior of the worker; and a work status evaluation step of estimating the work status of the worker from a standard work efficiency calculated from the cognitive proficiency, the measured work efficiency of the worker, and the concentration level.

Images