JP7664581B2 - A system for estimating task execution inhibition function based on tasks with a user interface (UI) that induces intuitive operation - Google Patents

Description

The present disclosure relates to a function estimation device, and in particular to a function estimation device that estimates the task execution function and task inhibition function of the prefrontal cortex of the brain.

It is known that dementia tests (such as the Hasegawa Scale) are necessary to determine whether or not a person has dementia, or to check the degree of progression of dementia. In addition, it is known that impairments in task execution and task inhibition functions of the prefrontal cortex of the brain tend to be present in Alzheimer's disease, which is one of the diseases that causes dementia.

Task executive function is the ability to deal with the current situation and derive appropriate thoughts or actions when performing a task, and to promote decision-making regarding those thoughts or actions. Task inhibition function is the ability to consciously suppress inappropriate thoughts or actions in the current situation when performing a task. In order to estimate these task executive and task inhibition functions, it was necessary to conduct psychological tests (e.g., go-nogo tasks, Stroop tests, etc.).

“Dementia self-diagnosis test”, [online], Dementia Prevention Association, [searched October 19, 2020], Internet <URL: http://www.ninchi-k.com/print_test.html>

Among tests that suggest a visit to a dementia specialist by having the target user answer questions that can test multiple abilities, questions that can test whether the above-mentioned task execution function and task inhibition function are normal have been disclosed (see Non-Patent Document 1). This test adds up the scores of multiple questions that the target user answers correctly, and suggests a visit to a specialist if the total score does not reach a predetermined standard score. Therefore, although this test includes one question about the task execution function and task inhibition function, the detailed state of the target user's task execution function and task inhibition function is not suggested.

In addition, conducting a psychological test to estimate a target user's task execution function and task inhibition function requires the presence of an expert, the execution of prescribed procedures, and sufficient time to take the test, making it difficult to conduct such a test. For this reason, there is a demand for a system that can estimate a target user's task execution function and task inhibition function in more detail by simply having the target user take a simple test.

Therefore, the purpose of this disclosure is to estimate the target user's task execution and inhibition functions in more detail by simply conducting a simple test.

A function estimation device according to one aspect of the present disclosure includes a presentation unit that presents to a user a number of tasks that require operations to be performed on a user interface that induces the user to give an incorrect answer, an acquisition unit that acquires operation data indicating results of the user's operations on the number of tasks presented by the presentation unit, and an estimation unit that estimates indicators representing the user's task execution function and task inhibition function based on the user's operation data acquired by the acquisition unit, wherein the user interface includes a question, a correct answer option that the user should originally select for the question, and an incorrect answer option that reminds the user of the correct answer to the question by at least one element of color, decoration, expression, terminology, and arrangement indicated by the content of the question or the content of the correct answer option.

In this function estimation device, the user interface displays incorrect answer options that evoke the correct answer to the question together with the correct answer option. Therefore, the user interface can induce the user to give an incorrect answer, so that the user's operation data and the task execution function and task inhibition function can be significantly and closely related. Therefore, the estimation unit can estimate the indicators representing the user's task execution function and task inhibition function in more detail based on the user's operation data. Therefore, the user's task execution function and task inhibition function can be estimated in more detail by simply conducting a simple test.

According to the present disclosure, it is possible to estimate a target user's task execution and inhibition functions in more detail by simply conducting a simple test.

1 is a functional block diagram of a function estimation device according to an embodiment. 1A is a diagram showing an example of a screen presenting a triggered user interface with distinctive terms and sizes in the options, and FIG. 1B is a diagram showing an example of a screen presenting a triggered user interface with distinctive terms and decorations in the options. FIG. 13 is a diagram showing an example of operation data of a triggered user interface. FIG. 1A is a diagram showing an example of the test results of a psychological test, and FIG. 1B is a diagram showing indices representing task executive function and task inhibition function derived from the test results of the psychological test. FIG. 11 is a flow diagram showing a process for constructing an estimation model. FIG. 11 is a flow diagram showing an acquisition process of operation data. FIG. 11 is a flow diagram showing a process of estimating a user's task execution function and task suppression function using an estimation model. FIG. 2 is a diagram illustrating an example of a hardware configuration of a function estimation device.

The embodiments of the present invention will be described with reference to the attached drawings. Where possible, identical parts will be given the same reference numerals and duplicate explanations will be omitted. The dimensional ratios of the drawings do not necessarily match those in the description.

The configuration of a function estimation device according to an embodiment will be described with reference to Fig. 1. The function estimation device 1 shown in Fig. 1 is a device that constructs an estimation model for estimating indexes representing a task execution function and a task inhibition function, and estimates the indexes representing a user's task execution function and task inhibition function.

The function estimation device 1 is a device that can be operated by a user. Examples of the function estimation device 1 include a smartphone and a tablet terminal. For example, an application (hereinafter referred to as an "app") that can be operated by a user is installed in the function estimation device 1. The type of the app is not particularly limited, and examples include an SNS (social network service) app, a communication app, a video playback app, a camera function app, etc.

The function estimation device 1 includes a reception display unit 5, a presentation unit 10, a calculation unit 15, an acquisition unit 20, a learning unit 30, an estimation unit 40, and a storage unit 90. The reception display unit 5 displays apps, later-described tasks, a user interface, and the like, owned by the function estimation device 1, and accepts input operations by a user (for example, user operations in a later-described user interface presented by the presentation unit 10).

The storage unit 90 is a functional unit that stores information. The storage unit 90 functions as a database that stores data related to a user interface and tasks presented by the presentation unit 10, which will be described later. The storage unit 90 stores data calculated by the calculation unit 15, which will be described later. The storage unit 90 may store a combination of the data from the presentation unit 10 and the data obtained by the calculation unit 15. The calculation unit 15, the acquisition unit 20, the learning unit 30, and the estimation unit 40 are configured to be able to acquire information from the storage unit 90. The storage unit 90 may be provided outside the function estimation device 1.

The presentation unit 10 presents to the user via the reception display unit 5 a number of tasks that can be operated on the user interface. A task is an assignment or process that requires the user who handles the function estimation device 1 to operate the function estimation device 1. The user interface presented by the presentation unit 10 is displayed, for example, as a pop-up on the reception display unit 5 of the function estimation device 1, and is visually recognized by the user and operated by the user via the reception display unit 5. For example, the user taps on the reception display unit 5 at an operation location on the user interface presented by the presentation unit 10 to operate the user interface.

The presentation unit 10 presents the user with a number of tasks that involve operations on a triggering user interface (hereinafter referred to as "triggering UI"), which is a user interface that induces the user to give an incorrect answer. By presenting the triggering UI by the presentation unit 10, it is possible to sense whether or not a naturally induced response can be suppressed through the reception display unit 5.

The presentation unit 10 presents to the user, via the reception display unit 5, multiple tasks for performing operations on an inducing UI after the user launches an app that estimates a brain state (hereinafter referred to as the estimation app). Launching the estimation app refers to, for example, the user touching the icon of the estimation app displayed on the reception display unit 5 in the function estimation device 1, causing the estimation app to start operating. The number of multiple tasks is a predetermined number.

As shown in FIG. 2, the trigger UI 80 presents the user with, for example, a question 81, a correct answer option 82 that is an answer to the question 81 and that the user should originally select, and an incorrect answer option 83 that is an answer to the question 81 and that the user should not originally select.

The question 81 in the trigger UI 80 is, for example, a question or fact-checking sentence about at least one of color, decoration, expression, terminology, and layout. The correct answer option 82 is, for example, a correct answer (correct answer) to the question 81, and is an option that represents at least one element of color, decoration, expression, terminology, and layout. The incorrect answer option 83 is, for example, an option that has an element different from at least one element of color, decoration, expression, terminology, and layout indicated by the correct answer option 82.

Color includes concepts such as shade, brightness, and saturation of a color. Decoration includes concepts such as pattern, emphasis, size, and shape. Emphasis includes effects such as shadow and three-dimensional effect given to a shape. Expression includes a sentence form or sound representing the question 81, correct answer option 82, or incorrect answer option 83. Expression includes a phrase that expresses a relationship between the correct answer option 82 and the incorrect answer option 83. Terms include words, numbers, or phrases that represent the question 81, correct answer option 82, or incorrect answer option 83, or their meanings.

The incorrect answer option 83 is designed, for example, to show a correct answer that the user can intuitively recall from the content of the question 81. That is, the triggering UI 80 is designed so that, when users intuitively select an option, most users are likely to select the incorrect answer option 83, which they should not have selected. Alternatively, when a user selects the correct answer option 82 in the triggering UI 80, the triggering UI 80 is designed to cause the user to hesitate between the correct answer option 82 and the incorrect answer option 83, so that it takes many users a long time to complete the operation.

The incorrect answer option 83 reminds the user of the correct answer to the question 81 by at least one element of color, decoration, expression, terminology, and arrangement indicated by the content of the question 81 or the content of the correct answer option 82. The content of the question 81 includes at least one characteristic of the meaning, manner, and index suggested by the sentence shown as the question 81, the term shown as the question 81, or the characters (numbers) contained in the sentence or the term. The content of the correct answer option 82 includes at least one characteristic of the meaning, manner, and index suggested by the sentence shown as the correct answer option 82, the term shown as the correct answer option 82, or the characters (numbers) contained in the sentence or the term.

For example, among contents that can be expressed using at least one characteristic of the meaning, manner, and index contained in the content asked about, the content being prompted to confirm, or the content expressed in question 81, the content that indicates the correct answer to question 81 is shown in correct answer option 82, and other contents that were not shown in correct answer option 82 are shown in incorrect answer option 83. Incorrect answer option 83 is designed, for example, so that some of the elements shown in the content of correct answer option 82 are different, or so that the same content shown in the content of correct answer option 82 is expressed with different elements.

The above-mentioned example is shown below. As shown in FIG. 2A, part or all of the decoration of the incorrect answer option 83a in the trigger UI 80a may be different from part or all of the decoration of the correct answer option 82a, but may be the same as the expression indicated by the content of the term in the question 81a. The question 81a is a sentence saying, "Please choose the one with the larger value." In addition to the value indicating the correct answer to the question 81a, the content that can be expressed using the size, which is an index included in the content asked in the question 81a, includes, for example, the size of the option as decoration. In this case, the value indicated by the correct answer option 82a ("8" in FIG. 2A) is set to be larger than the value indicated by the incorrect answer option 83a ("3" in FIG. 2A). On the other hand, the size of the characters indicating the value of the incorrect answer option 83a is set to be larger than the size of the characters indicating the value of the correct answer option 82a.

In the trigger UI 80a, the expression (relationship) indicated by the content of the correct answer option 82a relative to the content of the incorrect answer option 83a may be expressed by some or all of the decoration of the incorrect answer option 83a relative to some or all of the decoration of the correct answer option 82a. In this case, the value indicated by the correct answer option 82a, which is the correct answer to the question 81 ("8" in FIG. 2(a)), is set to be larger than the value indicated by the incorrect answer option 83a ("3" in FIG. 2(a)). In this case, the "larger" relationship indicated by the content "8" of the correct answer option 82 relative to the content "3" of the incorrect answer option 83a is expressed by size instead of value, and the size of the incorrect answer option 83a is expressed to be larger than the size of the correct answer option 82.

In the elicitation UI 80a, a user who fully (completely) recognizes the content of the question 81a and the content of each of the options 82a and 83a is likely to select the correct answer option 82a, which has a large value. On the other hand, a user who only partially recognizes the content of the sentence in the question 81a, or who fails to understand the content of each of the options 82a and 83a, is likely to overlook the word "value" in the question 81a and only recognize the term "large." Therefore, the user is likely to intuitively select the incorrect answer option 83a, which is visually represented in a large size.

As shown in FIG. 2B, some or all of the terms of the incorrect answer option 83b in the trigger UI 80b may be in accordance with the aspect indicated by the content of the terms in the question 81b, compared to some or all of the terms of the correct answer option 82b. In FIG. 2, the color of the decoration of the character part of the question 81b and the color of the decoration of the character part of the incorrect answer option 83b are represented by a diagonal line pattern, and the diagonal line pattern indicates the color "red". In FIG. 2, the color of the decoration of the character part of the correct answer option 82b is represented by a pointillism (dot) pattern, and the pointillism pattern indicates the color "blue". The question 81b is a sentence that reads "What is the color of this character?" The content that can be expressed for the color, which is the aspect being asked about in the question 81b, includes, for example, the color indicated by the decoration, in addition to the color indicated by the term that is the content indicating the correct answer to the question 81b. In this case, the color implied by the term in correct answer option 82b ("red" in FIG. 2(b)) is different from the color implied by the term in incorrect answer option 83b ("blue" in FIG. 2(b)), and is set to match the correct answer indicated by the content of question sentence 81. On the other hand, the color given to the term as decoration in incorrect answer option 83a is different from the color given to the term as decoration in correct answer option 82a, and is set to match the correct answer indicated by the content of question sentence 81.

In the trigger UI 80b, the difference in expression indicated by the content of the correct answer option 82b relative to the content of the incorrect answer option 83b may be expressed by a difference in part or all of the decoration of the incorrect answer option 83b relative to part or all of the decoration of the correct answer option 82b. In this case, the color implied by the term in the correct answer option 82b ("red" in FIG. 2(b)) is set to be different from the color implied by the term in the incorrect answer option 83a ("blue" in FIG. 2(b)). Here, the meaning implied by the term "blue" in the incorrect answer option 83a is the color blue, whereas the meaning implied by the term "red" in the correct answer option 82 is the color red. In this case, the color attached to the term as the decoration of the correct answer option 82 is set to blue, and the color attached to the term as the decoration of the incorrect answer option 83a is set to red. In FIG. 2(b), the color of the correct answer option 82b and the color of the incorrect answer option 83b are interchanged, but it is sufficient if at least the decorative color of the incorrect answer option 83b is a color that is indicated by the content (terminology) of the correct answer option 82b.

In the elicitation UI 80b, a user who fully (completely) recognizes the content of the question 81b and the content of each of the options 82b and 83b is likely to select the correct answer option 82b, which shows the color of the term's meaning. On the other hand, a user who only partially recognizes the content of the question 81b or fails to understand the content of each of the options 82b and 83b is likely to, for example, not place importance on the color "red" that the term means, but on the color "red" that is attached to the term as decoration. Therefore, the user is likely to intuitively select the incorrect answer option 83b, which visually shows the color attached to the term as decoration as red.

2(a) and (b), the incorrect answer option 83 reminds the user of the correct answer to the question 81 by at least one element of color, decoration, expression, terminology, and arrangement indicated by the content of the question 81 and the content of the correct answer option 82, thereby increasing the inducement effect of making the user select the incorrect answer option 83. In other words, the user needs to fully understand the content of the question 81, the correct answer option 82, and the incorrect answer option 83, and appropriately select the correct answer option 82 that represents the correct answer.

The color and decoration applied to the incorrect answer option 83b in the trigger UI 80b may be more extravagant than the color and decoration applied to the correct answer option 82a. Extravagant is an example of an aspect that is relatively likely to catch the user's eye.

The presentation unit 10 may present the inducement UI 80 by characterizing it with only one element of color, decoration, expression, terminology, and arrangement, or may present it by characterizing it with a combination of multiple elements. For example, by characterizing each of the options 82 and 83 with a combination of multiple elements, the user can be induced to more easily select the incorrect answer option 83 than the correct answer option 82.

After the estimation app is launched, multiple trigger UIs 80, which represent multiple tasks and are targets for the user to operate, are presented in sequence. When the user taps on either the correct answer option 82 or the incorrect answer option 83 via the reception display unit 5, the operation result is sent to the trigger UI 80 as input has been completed. The correct answer option 82 and the incorrect answer option 83 can be operated, for example, after the trigger UI 80 is displayed on the reception display unit 5. The operation result will be described later.

When the user selects the correct answer option 82 in the triggering UI 80 and the number of tasks in the estimation app has not been reached in a predetermined manner, the presentation unit 10 presents the triggering UI 80 representing the next task. When the user selects the correct answer option 82 in the triggering UI 80 and the number of tasks in the estimation app has been reached in a predetermined manner, the presentation unit 10 presents, for example, a screen indicating that all of the tasks in the estimation app have been completed. For example, the presentation unit 10 presents a task using the triggering UI 80, and when the user selects the incorrect answer option 83, presents the triggering UI 80 again. For example, the presentation unit 10 continues to present the triggering UI 80 until the user selects the correct answer option 82.

For each operation on the triggering UI 80 by the user (hereinafter referred to as an attempt), the reception display unit 5 outputs as operation results the type of triggering UI 80 (task) presented by the presentation unit 10, correct/incorrect information indicating whether the option selected by the user was correct or incorrect, the start timing at which the presentation or re-presentation of the triggering UI 80 began on the reception display unit 5, and the selection timing at which the user selected an option on the triggering UI 80. The start timing or selection timing is, for example, a date and time. The reception display unit 5 stores the operation result in the memory unit 90, for example.

In the above, the presentation unit 10 presents, as the triggering UI 80, the incorrect answer option 83 that reminds the user of the correct answer to the question 81. However, in some of the tasks among the multiple tasks, the incorrect answer option may present a UI (hereinafter, referred to as a normal UI) that indicates content that does not remind the user of the correct answer to the question. When there are a large number of tasks by the triggering UI 80, or when a task by the triggering UI 80 that asks the same type of content as a task by a certain triggering UI 80 is displayed periodically, the user's adaptability to the triggering UI 80 may improve (promote familiarity), and the function of the triggering UI 80 to induce the user to give an incorrect answer (the triggering effect) may not be exerted significantly. In order to exert the triggering effect of the task by the triggering UI 80 significantly, the presentation unit 10 may, for example, randomly present some of the tasks among the multiple tasks as tasks by the normal UI.

In the above, the presentation unit 10 has presented an example in which one incorrect answer option 83 is presented in one task (one triggering UI 80), but multiple incorrect answer options may be presented in one task. In this case, at least one of the multiple incorrect answer options has the same configuration as the incorrect answer option 83. In addition, the other incorrect answer options other than the one incorrect answer option may present content that does not remind the user of the correct answer to the question sentence 81.

Next, returning to FIG. 1, other functional units in the function estimation device 1 will be described. The calculation unit 15 calculates operation data related to the results of a user's operation on multiple tasks using the user interface presented by the presentation unit 10. For example, the calculation unit 15 calculates the operation data related to the triggering UI 80 after the presentation unit 10 presents multiple tasks using the triggering UI 80 a predetermined number of times or for a predetermined period of time.

The calculation of operation data related to the triggering UI 80 will be described below. The calculation unit 15 calculates the operation data based on data in the storage unit 90 for each predetermined number of times that a task is presented by the triggering UI 80, or for each predetermined period of time. The predetermined number of times is, for example, a predetermined number of times when each type of triggering UI 80 is displayed at least once. The predetermined period is a predetermined period of time, for example, several days or several weeks. When the calculation unit 15 calculates the operation data, the calculation unit 15 stores the operation data in the storage unit 90.

The operation data includes, for example, at least one of correct answer count data relating to the number of times the correct answer option 82 was selected in the triggering UI 80 and incorrect answer count data relating to the number of times the incorrect answer option 83 was selected in the triggering UI 80. The calculation unit 15 calculates at least one of the correct answer count data and the incorrect answer count data based on the correct/incorrect information and the number of correct/incorrect information acquired from the storage unit 90.

The calculation unit 15 calculates, as the correct answer count data, for example, a correct answer selection rate, which is the ratio of the number of times the task was performed using the trigger UI 80 to the number of times the correct answer option 82 was selected.

The calculation unit 15 calculates, as the data on the number of incorrect answers, a repeat error rate, which is the ratio of the number of tasks (hereinafter referred to as repeated tasks) in which the user repeatedly selected the incorrect answer option 83 re-presented in the triggering UI 80 to the number of times the task was performed by the triggering UI 80 of the estimation app. The repeat error rate is the ratio of the number of tasks in which the user selected the wrong answer option multiple times in the same triggering UI 80 to the total number of tasks.

The calculation unit 15 calculates the rate of incorrect answer repetition based on the type of task, the correct/incorrect information, and the number of correct/incorrect information stored in the storage unit 90. For example, when the user selects the incorrect answer option 83 in the first-presented trigger UI 80 and then selects the incorrect answer option 83 again in the re-presented trigger UI 80, the task by the trigger UI 80 becomes a repetitive task. When the number of incorrect answers is recorded twice or more in the correct/incorrect information for the same task, the calculation unit 15 determines the task as a repetitive task and calculates an index (hereinafter, referred to as the repetition index) as "1". When the number of incorrect answers is recorded once or less in the correct/incorrect information for the same task, the calculation unit 15 determines the task as a repetitive task and calculates the repetition index as "0". The calculation unit 15 calculates the repetition index for each task stored in the storage unit 90. The calculation unit 15 calculates the sum of the repetition indexes as the number of repetitive tasks. The calculation unit 15 calculates the number of repeated tasks divided by the total number of tasks as the rate of repeated incorrect answers.

The calculation unit 15 may calculate, as the data on the number of incorrect answers, the number of repeated incorrect answers, which is the number of times the incorrect answer option 83 re-presented in a certain task by the trigger UI 80 is repeatedly selected. In this case, the calculation unit 15 calculates the number of repeated incorrect answers based on the type of task and the correct/incorrect information stored in the storage unit 90. For example, if the user selects the incorrect answer option 83 in the trigger UI 80 presented for the first time and then selects the incorrect answer option 83 again in the trigger UI 80 presented again, the number of repeated incorrect answers becomes "1". After this selection, the number of repeated incorrect answers is incremented by one each time the user selects the incorrect answer option 83 in the trigger UI 80 re-presented in the same task. The calculation unit 15 may calculate, as the data on the number of incorrect answers, the maximum value of the number of repeated incorrect answers in the number of repeated incorrect answers in all tasks.

The operation data includes operation time data regarding the operation time required by the user to operate the user interface (for example, the operation time required to operate the triggering UI 80 presented by the presentation unit 10). As an example of operation time data, the calculation unit 15 calculates the operation time for each task based on the start timing and selection timing.

The calculation unit 15 calculates the correct answer operation time and the incorrect answer operation time, which are examples of operation time, based on the type of task, the correct/incorrect information, the start timing, and the selection timing. The correct answer operation time is the time from the first presentation timing of each task by the triggering UI 80 by the presentation unit 10 to the correct answer selection timing at which the user selects the correct answer option 82. The incorrect answer operation time is the time from the presentation timing at which each task by the triggering UI 80 is presented or re-presented by the presentation unit 10 to the incorrect answer selection timing at which the user selects the incorrect answer option 83. The calculation method is described below.

When the calculation unit 15 calculates the correct operation time, the calculation unit 15 calculates the earliest timing in the same task among the task types as the first appearance timing. The first appearance timing includes, among the start timings, an initial timing at which the first task is presented by the presentation unit 10 after the estimation app is launched, or a switch timing at which the presentation unit 10 switches from another task to a new task. When the calculation unit 15 calculates the correct operation time, the calculation unit 15 assigns, as the correct answer selection timing, a selection timing at which the correct answer is selected in the same task among the task types. The calculation unit 15 obtains the correct operation time by subtracting the first appearance timing from the correct answer selection timing.

When the calculation unit 15 calculates the incorrect operation time, the calculation unit 15 calculates the presentation timing. The presentation timing includes, among the start timings, an initial timing at which the first task is presented by the presentation unit 10 after the estimation app is launched, a switching timing at which another task is switched to a new task by the presentation unit 10, or a re-presentation timing at which the triggering UI 80 is re-presented by the presentation unit 10. When the calculation unit 15 calculates the incorrect operation time, the calculation unit 15 assigns, as the incorrect answer selection timing, a selection timing at which an incorrect answer is selected in a trial that includes the above-mentioned presentation timing. The calculation unit 15 obtains the incorrect operation time by subtracting the presentation timing from the incorrect answer selection timing. Note that the calculation unit 15 may use the sum of the above-mentioned incorrect operation times obtained in the same task among the task types as an example of the incorrect operation time.

The calculation unit 15 calculates a feature amount based on the operation time obtained from multiple tasks by the triggering UI 80 as an example of operation time data. The feature amount includes, for example, an average value of operation time for multiple tasks, a variance of operation time, etc. The feature amount includes, for example, an average value of correct operation time for multiple tasks, a variance of correct operation time, an average value of incorrect operation time, a variance of incorrect operation time, etc.

The calculation unit 15 may calculate operation data including a degree of deviation between the correct operation time and correct selection data of the learning user and the correct operation time and correct selection data of the target user. The learning user is, for example, a subject (user) from which operation data used for learning an estimation model described later in the learning unit 30 is extracted. The target user is a subject (user) from which an index representing a task execution function and a task inhibition function is estimated using an estimation model described later. The correct selection data includes, for example, a correct selection rate. In this embodiment, when simply referring to a "user", it may include the learning user and the target user.

The correct answer operation time and correct answer selection rate of the learning user are related, for example, by a regression equation that derives an approximate correct answer selection rate for the correct answer operation time. The above-mentioned degree of deviation refers, for example, to the error of the correct answer operation time and correct answer selection rate of the target user with respect to the regression equation obtained by the learning user. The error refers, for example, to the difference between the correct answer selection rate obtained from the regression equation for a certain correct answer operation time and the correct answer selection rate of the target user.

A large deviation means that the error is large. A large positive deviation means that the correct answer selection rate of the target user is higher than the correct answer selection rate obtained from the regression equation, and the error is large. A large negative deviation means that the correct answer selection rate of the target user is lower than the correct answer selection rate obtained from the regression equation, and the error is large.

In addition, each variable in the operation data may be counted and calculated for each element (color, decoration, expression, terminology, and arrangement) that characterizes the incorrect answer option 83 of the triggering UI 80. Each variable in the operation data may be counted and calculated for each task or user interface. The calculation unit 15 stores the calculated operation data in the storage unit 90.

Next, the acquisition unit 20 shown in FIG. 1 acquires operation data for multiple tasks by the triggering UI 80 from the storage unit 90, as shown in FIG. 3. The acquisition unit 20 may directly acquire the operation data calculated by the calculation unit 15.

The acquisition unit 20 acquires, for example, the average operation time, the variance of the operation time, the correct answer selection rate, the average correct answer operation time, the variance of the correct answer operation time, the average incorrect answer operation time, the variance of the incorrect answer operation time, and the number of repeated incorrect answers as operation data for multiple tasks using the triggering UI 80.

The smaller at least one of the average operation time, the variance of operation time, the correct answer rate, the average incorrect operation time, and the variance of incorrect operation time suggests a decline in task execution function and task inhibition function. Furthermore, the larger at least one of the average correct operation time, the variance of correct operation time, and the incorrect answer repetition rate suggests a decline in task execution function and task inhibition function. A large average incorrect operation time and a large variance of incorrect operation time strongly suggest a decline in task inhibition function.

The smaller the average value of the operation time, the faster the user's reaction speed to the task using the triggering UI 80 is suggested. The greater the variance value of the operation time is than a predetermined first threshold, the lower the user's adaptability (unfamiliarization) to the task using the triggering UI 80 is suggested. In addition, if the variance value of the operation time is less than a predetermined second threshold, the user's adaptability (too familiarization) to the task using the triggering UI 80 is suggested. For example, the acquisition unit 20 may acquire the variance of the operation time from the operation data in advance, and if the variance value of the operation time is greater than or equal to the second threshold and less than or equal to the first threshold, the acquisition unit 20 may acquire another value of the operation data.

Although not shown in FIG. 3, the acquisition unit 20 may acquire the degree of deviation of the correct answer operation time and correct answer selection data of the target user from the correct answer operation time and correct answer selection data of the learning user. If the degree of deviation is large in the positive direction and the operation time (correct answer operation time) is small, it is suggested that the task execution function and task inhibition function are functioning normally.

In addition, if the user's task inhibition function is normal, it is estimated that the longer the user's operation time, the longer the user's thinking time will be, and therefore it is estimated that the correct answer option 82 is more likely to be selected. Therefore, if the degree of deviation is large in the positive direction and the operation time (normal operation time) is long, it is suggested that the task execution function is weakened.

On the other hand, if the degree of deviation is large in the negative direction and the operation time (normal operation time) is long, it is estimated that the task execution function and task inhibition function are weakened. If the degree of deviation is large in the negative direction and the operation time (normal operation time) is short, it is estimated that the task inhibition function is weakened.

Returning to FIG. 1 again, the learning unit 30 learns an estimation model 35 for estimating indices representing the task execution function and task inhibition function of a target user. The estimation model 35 is a model learned by conventional machine learning. The estimation model 35 is configured to include, for example, a conventional neural network. Alternatively, the estimation model 35 may be other models. The estimation model 35 inputs operation data used by the estimation unit 40 for estimation and outputs a function index. The function index is an index representing the task execution function and task inhibition function of a learning user or a target user.

The learning unit 30 generates an estimation model by performing machine learning using the acquired operation information of the learning user as an input (input value) to the estimation model and the acquired functional index of the learning user as an output (output value) from the estimation model. In this way, the learning unit 30 learns a function f shown in y=f(x), which is a relational expression of the estimation model, where x is the operation information of the learning user and y is the functional index of the learning user. The learning unit 30 stores the learned estimation model in the storage unit 90. Note that the learning user is a user who provides operation data and functional indexes used in learning the estimation model 35. The learning user and the target user may be the same or different.

The above-mentioned functional indicators are obtained by a psychological test. The psychological test is carried out in a predetermined procedure in the presence of an expert, with sufficient time for the subject to take the test. One example of a psychological test is the "go-nogo task" shown in FIG. 4. The go-nogo task is carried out, for example, by a learning user using a test terminal equipped with a reception display unit such as a smartphone.

As shown in FIG. 4(a), in the go-nogo task, tasks with reaction types of symbols to which the learning user should respond (GO symbols) and symbols to which the learning user should not respond (NOGO symbols) are presented on the screen of the test terminal a predetermined number of times. The learning user takes appropriate action for each reaction type. For example, in an experiment in which a GO symbol is presented, the learning user reacts quickly by tapping the test terminal, and in an experiment in which a NOGO symbol is presented, the learning user passes the test terminal without performing any operation.

If the learning user taps on the GO symbol, or if the learning user leaves the NOGO symbol without performing any operation, the execution result is "success." If the learning user leaves the GO symbol without performing any operation for a predetermined time or longer, or if the learning user mistakenly taps the NOGO symbol, the execution result is "failure." The test terminal acquires the above information on "success" and "failure" as the execution result. The test terminal also acquires the reaction time, which is the time from when the GO symbol is displayed until the learning user performs a tap operation, as the execution result. The test terminal acquires multiple execution results for multiple learning users.

As shown in FIG. 4B, the test terminal calculates a function index based on each data obtained as an execution result. The function index is, for example, at least one of the following data: an overall success rate, which is the average success rate for all learning users, which is the ratio of the number of tasks whose execution results are successful to the number of times the task is performed; a GO success rate, which is the success rate for all learning users in a task where a GO symbol is presented; a NOGO success rate, which is the success rate for all learning users in a task where a NOGO symbol is presented; and an average reaction time, which is the average reaction time for all learning users. The test terminal stores the function index in the memory unit 90.

For example, if the overall success rate is lower than a predetermined threshold, it suggests that at least one of the task execution function and the task inhibition function is weaker than normal. If the GO success rate is lower than a predetermined threshold, it suggests that the task execution function is weaker than normal. If the NOGO success rate is lower than a predetermined threshold, it suggests that the task inhibition function is weaker than normal. If the average reaction time is greater than a predetermined threshold, it suggests that the task execution function is weaker than normal. Each of the above thresholds is set by an expert for the go-nogo task being performed.

The learning user executes the tasks presented by the presentation unit 10 and executes the psychological test on the test terminal, thereby obtaining operation data and function indices as learning data for the estimation model 35. When the calculation unit 15 calculates operation data based on data in the storage unit 90 for a predetermined period, the learning unit 30 uses the function indices measured during the predetermined period or immediately before or after the predetermined period and the operation data for learning the estimation model 35. For example, the operation data calculated based on data from a plurality of tasks executed by the learning user during a certain period and stored in the storage unit 90, and the function indices obtained by the learning user executing one or a plurality of psychological tests using the test terminal during the certain period are used for learning the estimation model 35.

The acquisition unit 20 acquires functional indices of a predetermined number or more of multiple learning users. The learning unit 30 trains the estimation model 35 with the operation data and functional indices of the predetermined number or more of multiple learning users acquired by the acquisition unit 20. The predetermined number is, for example, tens or hundreds of people. The operation data derived in the task by the inducing UI 80 and the functional indices derived in the psychology test are data suggesting the state (e.g., decline) of the task execution function and the task inhibition function, respectively. This allows the estimation model 35 to acquire the function of estimating the functional indices from each index included in the operation data.

The estimation unit 40 estimates a functional index of the target user by applying the operation data of the target user acquired by the acquisition unit 20 to the estimation model 35 obtained by learning by the learning unit 30. The target user operates the function estimation device 1 and causes the acquisition unit 20 to acquire operation results for a plurality of tasks presented by the presentation unit 10. The estimation unit 40 estimates a functional index for each predetermined period by applying the operation data of the target user acquired by the acquisition unit 20 for each predetermined period to the estimation model 35. The estimation unit 40 may estimate a functional index for each presentation count by applying the operation data of the target user acquired by the acquisition unit 20 for each presentation count of a predetermined task to the estimation model 35.

The estimation unit 40 may diagnose the task execution function and the task inhibition function of the target user using the estimated functional index. Diagnosis of the task execution function and the task inhibition function refers to diagnosing the state of the brain of the target user based on the functional index, including whether or not there is an abnormality in the target user's function, whether or not there is a sign of decline (weakness), whether or not the function has declined (weakened) compared to the past or other users of the same age, and the like.

In this case, for example, the acquisition unit 20 acquires a threshold value for the functional index determined by an expert. The estimation unit 40 may diagnose the task execution function and task inhibition function of the target user based on, for example, the estimated functional index of the target user and the threshold value determined by the expert. For example, when the estimated functional index of the target user is lower than the threshold value, the estimation unit 40 can diagnose that the task execution function and task inhibition function of the target user may be decreased.

Also, for example, the acquisition unit 20 may acquire the functional index of the learning user and the diagnosis results of the task execution function and the task suppression function of the learning user. The estimation unit 40 may diagnose the task execution function and the task suppression function of the target user based on the estimated functional index of the target user, the functional index of the learning user, and the diagnosis results of the task execution function and the task suppression function of the learning user. In this case, if a diagnosis result is obtained that the task execution function and the task suppression function of the learning user are weakened, the estimation unit 40 may set the functional index of the learning user as a threshold. If there are multiple learning users, the estimation unit 40 may set a feature amount such as an average value of the functional index as a threshold. For example, if the estimated functional index of the target user is lower than the threshold determined by the estimation unit 40, the estimation unit 40 may diagnose that the task execution function and the task suppression function of the target user may be weakened.

The estimation unit 40 may have a function of outputting the estimated functional index of the target user or the diagnosed task execution function and task suppression function to the reception display unit 5 so that the target user can confirm it. In this case, the reception display unit 5 displays the estimated functional index of the target user or the diagnosed task execution function and task suppression function.

Note that the presentation unit in the claims corresponds to the reception/display unit 5 and the presentation unit 10. The acquisition unit in the claims corresponds to the reception/display unit 5, the calculation unit 15, and the acquisition unit 20. The learning unit in the claims corresponds to the learning unit 30. The estimation unit in the claims corresponds to the estimation unit 40.

Next, the process executed by the function estimation device 1 according to this embodiment (the estimation method performed by the function estimation device 1) will be described with reference to the flowcharts of Figures 5 to 7. First, the process of constructing the estimation model 35 in the function estimation device 1 shown in Figure 5 will be described.

The function estimation device 1 executes a process for acquiring operation data of the learning user (step S1 in FIG. 5). As shown in FIG. 6, step S1 is composed of the following steps. First, the presentation unit 10 presents a task by the trigger UI 80 on the reception display unit 5 at a predetermined timing (step S11). Next, the reception display unit 5 accepts the learning user's operation on the trigger UI 80, and the operation result is stored in the memory unit 90 (step S12).

Then, the calculation unit 15 determines whether or not the learning user has operated the triggering UI 80 a predetermined number of times (step S13). Since the number of operation results by the learning user stored in the memory unit 90 corresponds to the number of tasks by the triggering UI 80 presented by the presentation unit 10, the calculation unit 15 determines whether or not the number of operation results is equal to or greater than a predetermined number. If the calculation unit 15 determines that the number is equal to or greater than the predetermined number (step S13: YES), the function estimation device 1 proceeds to the next step. If the calculation unit 15 determines that the number of operation results is less than the predetermined number of times (step S13: NO), the function estimation device 1 returns to step S11.

In step S13, if it is determined that the number of operation results stored in the memory unit 90 is equal to or greater than a predetermined number (step S13: YES), the calculation unit 15 calculates the operation data of the learning user based on the operation results of the task by the triggering UI 80 (step S14).

Then, the acquisition unit 20 acquires operation data of the learning user based on the operation result of the task by the triggering UI 80 (step S15). This completes the operation data acquisition process shown in FIG. 6 (step S1 in FIG. 5).

Returning to Fig. 5, the acquisition unit 20 then acquires the functional index of the training user from which the operation data has been acquired (step S2). The learning unit 30 then learns an estimation model 35 in which the operation data is used as an explanatory variable and the functional index is used as a target variable (step S3). Through the above processing, the construction processing of the estimation model shown in Fig. 5 is completed.

Next, a process of estimating a functional index of a target user using the estimation model 35 in the function estimation device 1 will be described with reference to FIG. 7. First, the acquisition unit 20 acquires operation data of the target user (step S4). The process in step S4 is carried out, for example, in the same manner as each process in step S1 shown in FIG. 6. Step S4 is realized by a process procedure in which the "learning user" in the process procedure of steps S11 to S15 described above is replaced with the "target user". Next, the estimation unit 40 applies the operation data of the target user to the estimation model 35, thereby estimating the functional index of the target user (step S5). This completes the process of estimating the functional index of the target user shown in FIG. 7.

After step S5, the estimation unit 40 may diagnose the task execution function and the task suppression function of the target user based on the estimated functional index of the target user and a predetermined threshold value. Furthermore, as an output process, the estimation unit 40 may display the estimated functional index of the target user or the diagnosed task execution function and the task suppression function of the target user via the reception/display unit 5. As an output process, the estimation unit 40 may store the estimated functional index of the target user or the diagnosed task execution function and the task suppression function of the target user in the storage unit 90.

As described above, the function estimation device 1 of the present embodiment can estimate the task execution function and task inhibition function of the target user in more detail by simply performing a simple test, namely, a task using the inducing UI 80. The inducing UI 80 of the function estimation device 1 displays both the correct answer option 82 and the incorrect answer option 83 that evokes the correct answer to the question sentence 81. Thus, since the inducing UI 80 can induce the target user to select the incorrect answer option 83, the operation data of the target user and the task execution function and task inhibition function can be significantly and closely related. Therefore, the estimation unit 40 can estimate the index (function index) representing the task execution function and task inhibition function of the target user in more detail based on the operation data of the target user. The function estimation device 1 can easily diagnose the task execution function and task inhibition function of the target user based on, for example, the estimated function index of the target user and a threshold value determined by an expert or a function index of a learning user.

Furthermore, in the learning unit 30, an estimation model 35 for estimating a functional index can be constructed by using the operation data of the learning user as an explanatory variable and the functional index of the learning user as a target variable. The functional index of the target user can be estimated by inputting the operation data of the target user as an explanatory variable into the estimation model 35. The target user can obtain the functional index by simply performing a plurality of tasks in which the target user operates the triggering UI 80.

In addition, the acquisition unit 20 acquires operation data including operation time data regarding the operation time required by the user to operate the triggering UI 80. In this case, since the operation time data of the user can be included in the operation data, the estimation accuracy of the estimation model 35 can be improved.

The acquisition unit 20 also acquires operation data including correct answer selection data regarding the number of times the user selected the normal correct answer option 72 and the correct answer option 82. In this case, the higher the correct answer selection rate that may be included in the correct answer selection data, the more likely it is that the task execution function and task inhibition function are normal.

The acquisition unit 20 also acquires operation data including the degree of deviation between the operation time data and correct answer selection data when the learning user selects the correct answer option and the operation time data and correct answer selection data when the target user selects the correct answer option. In this case, if the degree of deviation is large, it can be estimated that there is no correlation between the operation time data of the target user and the operation time data of the learning user. If the degree of deviation is small, it can be estimated with high accuracy the indicators representing the task execution function and task suppression function of the target user. In addition, if the task execution function and task suppression function are normal, it is estimated that the longer the operation time, the more likely it is that the normal correct answer option 72 or the correct answer option 82 will be selected. Therefore, if the degree of deviation is large and the operation time (normal operation time) is large, the function estimation device 1 can estimate that the task execution function and task suppression function are weakened.

The acquisition unit 20 also acquires operation data including incorrect answer selection data regarding the number of times the user selected the same incorrect answer option 83 in multiple tasks. In this case, it can be estimated that the greater the incorrect answer repetition rate included in the incorrect answer selection data, the weaker the task inhibition function of the target user is.

Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above embodiments. For example, the calculation unit 15 may calculate operation data related to the user's operation results obtained after the presentation unit 10 presents the task by the triggering UI 80 a predetermined first number of times or for a predetermined first period or more. It may be assumed that immediately after the introduction of the triggering UI 80 by the presentation unit 10, the user is not necessarily adapted (is not used) to the operation of the triggering UI 80. The operation data of each user immediately after the introduction of the triggering UI 80 (less than the first number of times or less than the first period) includes a mixture of the influence of the incorrect answer induced by the triggering UI 80 and the influence of each user's adaptability to the triggering UI 80.

On the other hand, the calculation unit 15 may calculate operation data related to the user's operation results obtained before the presentation unit 10 presents the task by the triggering UI 80 a predetermined second number of times or for a predetermined second period or more. When the user continues to use the triggering UI 80 after the presentation unit 10 introduces it, it may be assumed that the user remembers the appearance of the triggering UI 80. When the use of the estimation app presenting the triggering UI 80 continues (for a second number of times or more or for a second period or more), the operation data of each user also includes a mixture of the influence of the incorrect answer being induced by the triggering UI 80 and the influence of each user's adaptability to the triggering UI 80.

Therefore, although it is possible for the learning unit 30 to train the estimation model 35 using operation data of a training user of the triggering UI 80 less than the first number of times, less than the first period, more than the second number of times, or more than the second period, the estimation accuracy of the functional indexes of the estimation model 35 may decrease due to the influence of the fitness of the training user reflected in the operation data.

In addition, although it is possible for the estimation unit 40 to input into the estimation model 35 operation data of the target user at the beginning of the introduction of the inducing UI 80 less than the first number of times, less than the first period, second number of times or more, or second period or more, the estimation accuracy of the functional indexes of the estimation model 35 may decrease due to the influence of the fitness of the target user reflected in the operation data.

As described above, the calculation unit 15 calculates operation data related to operation results of the learning user and the target user obtained by performing the task by the triggering UI 80 for a first number of times or more and less than the second number of times, or for a first period or more and less than the second period, thereby improving the estimation accuracy in the estimation model 35. Note that the first number of times, the first period, the second number of times, or the second period may be determined based on, for example, a first threshold value or a second threshold value that is a threshold value related to the variance of the operation time obtained by the learning user.

Furthermore, the function estimation device 1 may not include the calculation unit 15. In this case, the acquisition unit 20 may not acquire the value calculated by the calculation unit 15 stored in the storage unit 90. The acquisition unit 20 may directly acquire operation data indicating the result of the user's operation for each task using the triggering UI 80 presented by the presentation unit 10. The acquisition unit 20, the learning unit 30, or the estimation unit 40 may have the function of the calculation unit 15.

Moreover, the function estimation device 1 may not include the learning unit 30. In this case, the estimation unit 40 may acquire an estimation model generated outside the function estimation device 1, and estimate the functional index of the target user using the estimation model. Moreover, the function estimation device 1 may not use an estimation model generated by machine learning. In this case, the functional index of the target user may be estimated based on predetermined criteria for the operation time, the correct answer selection rate, the number of repeated incorrect answers, etc. Furthermore, the estimation unit 40 may estimate the functional index of the target user based on the operation data obtained by the acquisition unit 20. For example, the estimation unit 40 may weight the inverse of the correct answer selection rate, the operation time, the number of repeated incorrect answers, the degree of deviation in the negative direction, etc., and use the sum of these as the functional index of the user. For example, when comparing the latest newly acquired operation data with the past operation data stored in the memory unit 90, if the correct answer selection rate decreases, the operation time increases, the number of repeated incorrect answers increases, or the degree of deviation becomes large in the negative direction, the estimation unit 40 may estimate that the functional index of the target user is smaller than the functional index obtained in the past, and may infer that the task execution function and task inhibition function are weakened.

In addition, the acquisition unit 20 may not acquire operation data including operation time data via the calculation unit 15. In this case, the acquisition unit 20 may acquire operation data other than the operation time data, the learning unit 30 may train the estimation model 35 using operation data other than the operation time data of the learning user, and the estimation unit 40 may estimate the function index of the target user using operation data other than the operation time data of the target user. Similarly, the acquisition unit 20 may not acquire the correct answer selection data, the incorrect answer selection data, and the above-mentioned deviation degree. In this case, the learning unit 30 may train the estimation model 35 using operation data of the learning user other than the data not acquired by the acquisition unit 20, and the estimation unit 40 may estimate the function index of the target user using operation data of the target user other than the data not acquired by the acquisition unit 20.

The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. There are no particular limitations on the method of realizing each functional block. That is, each functional block may be realized using one device that is physically or logically coupled, or may be realized using two or more devices that are physically or logically separated and directly or indirectly connected (e.g., using wires, wirelessly, etc.). The functional blocks may be realized by combining the one device or the multiple devices with software.

Functions include, but are not limited to, judgement, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, regard, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs the transmission function is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on the method of realization for either of these functions.

For example, the function estimation device 1 in one embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure. As shown in FIG. 8, the above-mentioned function estimation device 1 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, and a bus 1007.

In the following description, the term "apparatus" can be interpreted as a circuit, device, unit, etc. The hardware configuration of the function estimation device 1 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

Each function in the function estimation device 1 is realized by loading a specific software (program) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured with a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, and a register. For example, each function of the function estimation device 1 described above may be realized by the processor 1001.

The processor 1001 reads out programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. The programs used are those that cause a computer to execute at least some of the operations described in the above-mentioned embodiments. For example, each function of the function estimation device 1 may be realized by a control program stored in the memory 1002 and running on the processor 1001. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

The memory 1002 is a computer-readable recording medium, and may be composed of at least one of, for example, a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), and a random access memory (RAM). The memory 1002 may also be called a register, a cache, or a main memory (primary storage device). The memory 1002 can store executable programs (program codes), software modules, and the like for implementing an information providing method according to one embodiment of the present disclosure.

Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, and a magnetic strip. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

The communication device 1004 is hardware (transmitting/receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., to realize at least one of, for example, Frequency Division Duplex (FDD) and Time Division Duplex (TDD). For example, the above-mentioned acquisition unit 20, etc. may be realized by the communication device 1004.

The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

Each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

The function estimation device 1 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

Notification of information is not limited to the aspects/embodiments described in this disclosure and may be performed using other methods.

The processing steps, sequences, flow charts, etc. of each aspect/embodiment described in this disclosure may be reordered unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order and are not limited to the particular order presented.

Information, etc. may be output from a higher layer to a lower layer, or from a lower layer to a higher layer. Information, etc. may be input/output via multiple network nodes.

The input and output information may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

The determination may be based on a value represented by one bit (0 or 1), a Boolean (true or false) value, or a numerical comparison (e.g., with a predetermined value).

Each aspect/embodiment described in this disclosure may be used alone, in combination, or switched according to execution. Notification of specific information (e.g., notification that "X is the case") is not limited to explicit notification, but may be performed implicitly (e.g., by not notifying the specific information).

Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended as an illustrative example and does not have any limiting meaning on the present disclosure.

Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

Software, instructions, information, and the like may be transmitted and received via a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and/or wireless technologies (such as infrared, microwave), these wired and/or wireless technologies are included within the definition of a transmission medium.

The information, signals, and the like described in this disclosure may be represented using any of a variety of different technologies. For example, the data, instructions, commands, information, signals, bits, symbols, chips, and the like that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

Note that terms explained in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.

As used in this disclosure, the terms "system" and "network" are used interchangeably.

The information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values from a predetermined value, or may be expressed using other corresponding information.

The names used for the parameters described above are not limiting in any way. Furthermore, the formulas etc. using these parameters may differ from the formulas etc. explicitly disclosed in this disclosure.

The terms "determining" and "determining" as used in this disclosure may encompass a wide variety of actions. "Determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" may include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in a memory), and the like. "Determining" may include resolving, selecting, choosing, establishing, comparing, and the like. In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." "Judgment (decision)" can also be interpreted as "assuming," "expecting," or "considering," etc.

The terms "connected" and "coupled", or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access". As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

Any reference to elements using designations such as "first" and "second" used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Thus, a reference to a first and a second element does not imply either that only two elements may be employed or that the first element must precede the second element in some way.

The "part" in the configuration of each of the above devices may be replaced with a "circuit" or a "device", etc.

When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Additionally, the term "or," as used in this disclosure, is not intended to be an exclusive or.

In this disclosure, where articles have been added by translation, such as "a," "an," and "the" in English, this disclosure may include that the nouns following these articles are plural.

In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

1...function estimation device, 5...reception display unit, 10...presentation unit, 15...calculation unit, 20...acquisition unit, 30...learning unit, 35... estimation model, 40... estimation unit, 80...elicitation UI, 81...question sentence, 82...correct answer option, 83...incorrect answer option, 90...storage unit, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims (5)

a presentation unit that presents to the user a plurality of tasks for performing operations on a user interface that induces the user to give an incorrect answer;
an acquisition unit that acquires operation data indicating results of operations performed by the user on the plurality of tasks presented by the presentation unit when the number of times the presentation unit has presented the tasks to the user is equal to or greater than a first number of times and less than a second number of times, or when a period during which the presentation unit has presented the tasks to the user is equal to or greater than a first period and less than a second period;
an estimation unit that estimates indicators representing a task execution function and a task suppression function of the user based on the operation data of the user acquired by the acquisition unit;
Equipped with
The user interface includes:
Questions and
A correct answer option that the user should originally select for the question;
and an incorrect answer option that reminds the user of the correct answer to the question by at least one element of color, decoration, expression, terminology, and arrangement indicated by the content of the question or the content of the correct answer option;
The acquisition unit is
operation time data relating to operation times required for each of the training user and the target user to operate the user interface;
Correct answer selection data regarding the number of times the learning user and the target user selected the correct answer option;
a degree of deviation between the correct answer selection data of the learning user and the correct answer selection data of the target user with respect to the operation time data when each of the learning user and the target user selects the correct answer option; and
acquiring the operational data including
the estimation unit estimates indexes representing a task execution function and a task inhibition function of the target user based on the operation time data and the degree of deviation when the target user selects the correct answer option;
Functional estimation device. the function estimation device further includes a learning unit configured to learn an estimation model for estimating indexes representing task execution functions and task inhibition functions, the indexes representing task execution functions and task inhibition functions acquired for the learning user being used as explanatory variables and indexes representing task execution functions and task inhibition functions being acquired for the learning user being used as objective variables;
The function estimation device according to claim 1 , wherein the estimation unit estimates indicators representing the task execution function and task inhibition function of the target user by applying the operation data of the target user acquired by the acquisition unit to the estimation model obtained by learning by the learning unit. The function estimation device according to claim 1 or 2, wherein the acquisition unit acquires the operation data including operation time data that is data regarding the operation time required by the user to operate the user interface. The function estimation device according to any one of claims 1 to 3, wherein the acquisition unit acquires the operation data including correct answer selection data regarding the number of times the user selected the correct answer option. The function estimation device according to any one of claims 1 to 4, wherein the acquisition unit acquires the operation data including incorrect answer selection data, which is data regarding the number of times the user selected the same incorrect answer option in multiple tasks.

Images