JP7300929B2 - Cognitive function promotion support system, learning system, estimation system, and cognitive function promotion support method - Google Patents

Description

The present invention relates to a cognitive function promotion support system, a learning system, an estimation system, and a cognitive function promotion support method.

In Japan, the number of people with dementia is increasing along with the progress of aging. As of 2012, it is said that about one in seven elderly people aged 65 and over have dementia. As people age, the likelihood of developing dementia increases, and it is expected that the number of people with dementia will continue to increase as the number of elderly people increases.
Since the number of patients with dementia tends to increase, communication between patients with dementia and their supporters becomes important. This is because if mutual communication cannot be done well, both the support recipient and the supporter may suffer a great mental burden.
Patent Document 1 discloses a support system that senses the idiosyncratic behavior of a dementia patient (supported person) and generates stimuli such as “calm music” and “calm images” that further suppress the idiosyncratic behavior. disclosed. In Patent Literature 1, from the personal data of the support recipient, a song that matches the patient's hobbies is selected, or a live video of a favorite band group is selected.

WO2018/212134

However, listening to music that matches one's hobbies does not necessarily suppress peculiar behavior. It may be that patients tend to respond better to ``calm music'' than to simple ''calm music,'' but the patient's favorite ``calm music'' suppresses idiosyncratic behavior. You won't know until you actually try it. Moreover, the number of songs of interest is not limited to one, but generally there are many. When there are many songs of a hobby, it takes a lot of time and effort to test whether or not the peculiar behavior can be suppressed for all songs, and it is not realistic.

The present invention has been made in view of such circumstances, and includes a cognitive function promotion support system, a learning system, an estimation system, and a cognitive function promotion support system that can estimate in advance a user's reaction to a stimulus without actually trying it. Offer a way to help.

In order to solve the above-described problems of the present invention, the present invention extracts a plurality of types of degrees of emotion, including at least exhilaration and stress, from electroencephalograms during stimulation, which indicate electroencephalograms when a predetermined stimulus is received. an emotion analysis unit; an enhancement type determination unit that determines, based on the degrees of the plurality of types of emotions extracted by the emotion analysis unit, an enhancement type that is classified from the viewpoint of promoting cognitive function with respect to the electroencephalogram during stimulation; For each unspecified user, learning a data set for learning in which a resting electroencephalogram indicating an electroencephalogram at rest with eyes closed and information indicating the facilitation type of the stimulating electroencephalogram is associated with the resting electroencephalogram and a trained model generation unit that generates a trained model that has learned a relationship with the facilitation type; an estimation target electroencephalogram acquisition unit that acquires an estimation target electroencephalogram that is the resting electroencephalogram to be estimated; the estimation target electroencephalogram; and an estimation unit that estimates the promotion type in the estimation target electroencephalogram using the trained model.

In addition, the present invention includes an emotion analysis unit that extracts a plurality of degrees of emotions including at least the degree of exhilaration and the degree of stress from electroencephalograms during stimulation, which indicate electroencephalograms when a predetermined stimulus is received, and the emotion analysis unit. a facilitation type determination unit that determines a facilitation type that is classified from the viewpoint of promoting cognitive function for the electroencephalogram during stimulation based on the degree of the plurality of types of extracted emotions; Learning that learns the relationship between the resting electroencephalogram and the facilitation type by learning a data set for learning in which the information indicating the facilitation type of the electroencephalogram at rest is associated with the information indicating the facilitation type of the electroencephalogram during stimulation and a trained model generator that generates a trained model.

In addition, the present invention is classified from the viewpoint of promoting cognitive function in each unspecified user's resting electroencephalogram showing electroencephalograms when eyes are closed at rest and stimulated electroencephalograms showing electroencephalograms when receiving a predetermined stimulus. a trained model storage unit that stores a trained model that has learned the relationship between the resting electroencephalogram and the facilitation type by learning a learning data set in which information indicating the facilitation type is associated with the facilitation type; An estimation target electroencephalogram acquisition unit that acquires an estimation target electroencephalogram that is the resting electroencephalogram to be estimated, and an estimation unit that estimates the facilitation type in the estimation target electroencephalogram using the estimation target electroencephalogram and the trained model. and an estimation system comprising:

Further, in the present invention, the emotion analysis unit extracts a plurality of types of emotion levels including at least the exhilaration and the stress level from the stimulus electroencephalogram indicating the electroencephalogram when receiving a predetermined stimulus, and the facilitation type determination unit extracts the degree of emotion. However, based on the degree of the plurality of types of emotions extracted by the emotion analysis unit, the stimulated electroencephalogram is determined to be a promotion type classified from the viewpoint of promoting cognitive function, and the learned model generation unit By learning a learning data set that associates a resting electroencephalogram indicating an electroencephalogram at rest with eyes closed and information indicating the facilitation type of the stimulating electroencephalogram for each specific user, the resting electroencephalogram and the above A trained model that has learned a relationship with a promotion type is generated, an estimation target electroencephalogram acquisition unit acquires an estimation target electroencephalogram that is the resting electroencephalogram to be estimated, and an estimation unit acquires the estimation target electroencephalogram and the A cognitive function promotion support method for estimating the promotion type in the estimation target electroencephalogram using a trained model.

According to the present invention, a user's reaction to a stimulus can be estimated in advance without actually trying it.

BRIEF DESCRIPTION OF THE DRAWINGS It is a block diagram which shows the example of a structure of the cognitive function promotion assistance system 1 which concerns on embodiment. 4 is a diagram showing an example of information stored in a storage unit 23 according to the embodiment; FIG. It is a figure which shows the example of stimulation type information 230 which concerns on embodiment. FIG. 4 is a diagram showing an example of electroencephalogram information upon stimulation 231 according to the embodiment; FIG. 4 is a diagram showing an example of weighting information 232 according to the embodiment; FIG. FIG. 4 is a diagram showing an example of stimulus species score information 233 according to the embodiment; FIG. 10 is a diagram illustrating an example of cognitive function enhancement score information 234 according to an embodiment; FIG. 10 is a diagram showing an example of evaluation type correspondence information 235 according to the embodiment; [0014] Figure 4 illustrates an example of promotion type information 236, according to an embodiment; It is a sequence diagram showing a flow of processing performed by the cognitive function promotion support system 1 according to the embodiment.

Hereinafter, embodiments of the invention will be described with reference to the drawings.

The cognitive function promotion support system 1 is a system that supports a patient with dementia to promote the patient's cognitive function by selecting a stimulus suitable for each individual patient.
FIG. 1 is a block diagram showing an example of the configuration of a cognitive function promotion support system 1 according to an embodiment. The cognitive function promotion support system 1 includes, for example, an electroencephalogram measurement device 10, an electroencephalogram analysis device 20, a learning device 30, and an estimation device 40.

The electroencephalogram measuring apparatus 10 is an apparatus for measuring electroencephalograms of a human (person to be measured). The electroencephalogram measurement apparatus 10, for example, wears a headband with electrodes on the head of the person to be measured, contacts the electrodes at a predetermined position on the head of the person to be measured, and performs measurement at a predetermined measurement cycle. acquire the brain waves of the person.

The electroencephalogram measurement device 10 measures electroencephalograms (encephalograms at rest) of the person to be measured with their eyes closed at rest for a predetermined period of time (for example, 30 seconds). Here, the term “at rest with eyes closed” refers to a state in which the subject is in a state of rest, such as sitting on a chair, and the subject remains awake with his/her eyes closed. The electroencephalogram measurement device 10 outputs information indicating time-series changes in the measured resting electroencephalogram to the learning device 30 in association with identification information (electroencephalogram ID) that uniquely identifies the electroencephalogram.

The electroencephalogram measurement device 10 measures electroencephalograms (electroencephalograms during stimulation) for a predetermined time (for example, 5 minutes) when the subject is stimulated. The stimulus here means stimulating at least one of the multiple senses that the subject can feel. The multiple senses are, for example, the so-called five senses composed of hearing, sight, touch, taste, and smell. For example, when stimulating hearing, the person to be measured is made to listen to sounds such as music and voice. Similar methods apply to visual, tactile, gustatory and olfactory stimulation.

In this embodiment, a plurality of stimuli are prepared, and the subject's electroencephalogram is measured when all or part of the plurality of stimuli are applied. This acquires the relationship between stimuli and electroencephalogram tendencies.
A plurality of stimuli are prepared from the viewpoint of promoting cognitive function, and are such as to make the user feel nostalgic and interesting. Such stimulation increases the likelihood that the brain will be uplifted and excited, stress will be reduced, the brain will be more active, and cognitive function will be enhanced.
The multiple stimuli are, for example, nursery rhymes, comedy, memories, and the like.
A nursery rhyme is a song for children and a song that makes one feel nostalgic.
Comedy is an art to make people laugh, such as rakugo, manzai, and comedy.
A memory is a past event that makes one feel nostalgic, such as a memorable song or a photograph of a memorable place.
Each of the plurality of stimuli as described above may be selected according to the individual subject, or may be a song or photo commonly selected according to the subject's sex and age. There may be.

The electroencephalogram measurement device 10 associates the information indicating the time-series change of the measured stimulus electroencephalogram with the electroencephalogram ID and the information uniquely identifying the type of stimulation (stimulus type ID), the electroencephalogram analysis device 20, and the learning Output to device 30 .

The electroencephalogram analyzer 20 is a device that analyzes electroencephalograms. Specifically, the electroencephalogram analyzer 20 classifies the electroencephalogram upon stimulation into a plurality of types (promotion types described later) based on the viewpoint of promoting cognitive function. The electroencephalogram analysis device 20 includes, for example, an emotion analysis unit 21, a facilitation type determination unit 22, and a storage unit 23.

The emotion analysis unit 21 extracts time-series changes in the degree of multiple types of emotions, including at least the degree of excitement (elevation) and the degree of stress, according to the time-series changes in the electroencephalogram. The degree of excitement (elevation) is a feeling like when feeling excited, and generally refers to the degree to which tension is expressed. That is, the degree of excitement (excitement) is the degree of exaltation of the person to be measured, which is derived from the electroencephalogram. The degree of stress is the degree of stress that the person to be measured received, which is derived from the electroencephalogram. The multiple types of emotions include excitement, stress, liking, concentration, calmness, and the like. The degree of liking is the degree to which the person to be measured has a favorable impression derived from the electroencephalogram. The degree of concentration is the degree of concentration of the subject derived from the electroencephalogram. The degree of calmness is the degree of calmness of the person to be measured derived from the electroencephalogram.

The emotion analysis unit 21 uses, for example, a computational model to extract the degree of these multiple types of emotions from the electroencephalogram. This computational model obtains, for example, electroencephalograms that evoke a plurality of types of emotions such as excitement, liking, stress, concentration, and calmness for a plurality of people, and for these electroencephalograms This is a model generated by performing statistical processing. By using such a computational model, it is possible to extract a plurality of degrees of emotion from brain waves.

The emotion analysis unit 21 associates the time-series changes in the degree of each of the plurality of types of emotions extracted from the subject's electroencephalogram with the electroencephalogram ID and the stimulus type ID, and outputs them to the facilitation type determination unit 22 .

The promotion type determination unit 22 determines the promotion type based on the time-series change in the degree of each of the plurality of types of emotions from the emotion analysis unit 21 . The promotion type is a plurality of types classified according to the extent to which cognitive function is promoted by which type of stimulus.

The facilitation type determination unit 22 extracts, for example, the degree at the start and the degree after the start in the time-series change in the degree of each of the plurality of types of emotions acquired from the emotion analysis unit 21 . The degree at the start is, for example, the average value of the degree for a predetermined time (for example, 30 seconds) after the measurement of the electroencephalogram during stimulation is started. The degree after the start is an arbitrary time interval (for example, 30 seconds) after a predetermined time (for example, 30 seconds) has elapsed after the acquisition of the electroencephalogram during stimulation is started until the measurement of the electroencephalogram during stimulation is completed. is the average value of the degree of

The promotion type determination unit 22 calculates the degree of change indicating the difference between the extracted degrees at the start and after the start. The facilitation type determination unit 22 associates the degree at the start, the degree after the start, and the degree of change with the electroencephalogram ID and the stimulation type ID, and stores the electroencephalogram information during stimulation 231 (see FIG. 3B) in the storage unit 23. .

The promotion type determination unit 22 weights each of the calculated degrees of change according to the emotion. The weighting is stored in the weighting information 232 (see FIG. 3C) of the storage unit 23, for example. For example, if the cognitive function is promoted most when the level of excitement increases and the level of stress decreases, the weight of the level of excitement is a positive (plus) value, which is greater than that of other emotions. set to a value (eg, 0.8). The weight of the stress degree is a negative (minus) value, and is set to a large absolute value (eg, -0.8) compared to other emotions. Likeness, concentration, and calmness are set to small absolute values (eg, 0.3, 0.1, -0.1) compared to the weighting of excitement. In other words, from the viewpoint of promoting cognitive function, emotions that are important to rise in response to stimuli are weighted with a large positive (plus) absolute value, and emotions that are important to fall are weighted negative ( (minus) is weighted with a large absolute value.

The promotion type determination unit 22 calculates a promotion score by summing up the weighted degrees of change. The facilitation type determination unit 22 associates the degree of change, the weighted degree of change, and facilitation score with the electroencephalogram ID and the stimulus type ID, and stores them in the storage unit 23 as facilitation score information 233 (see FIG. 3D). .

The promotion type determination unit 22 associates an evaluation corresponding to the calculated promotion score value. Evaluation, for example, is performed in three stages of A to C, and when the promotion score can take between 0 points and 100 points, 0 points or more and less than 40 points are "C" evaluation, 40 points or more Less than 80 points are evaluated as "B", and 80 to 100 points are evaluated as "A". The facilitation type determination unit 22 associates the facilitation score and the evaluation with the electroencephalogram ID and the stimulation type ID, and stores them in the storage unit 23 as evaluation information 234 (see FIG. 3E).

Note that the above is just an example, and the evaluation is not limited to the three grades from "A" to "C". The evaluation may be performed in two stages or less, or may be performed in four stages or more. Also, the evaluation does not have to be symbols such as “A” to “C”, and may be numerical values (that is, evaluation values).

The facilitation type determination unit 22 calculates facilitation scores for each of the plurality of stimuli, and associates the calculated evaluations. The promotion type determination unit 22 refers to the evaluation type correspondence information 235 (see FIG. 3F) of the storage unit 23 to determine the promotion type according to the combination of evaluations of the plurality of stimuli. In the evaluation type correspondence information 235, combinations of evaluations of a plurality of stimuli are stored in association with promotion types. The promotion type determination unit 22 associates the determined promotion type with the electroencephalogram ID and stores it in the storage unit 23 as promotion type information 236 (see FIG. 3G). Further, the facilitation type determination unit 22 transmits the determined facilitation type to the learning device 30 in association with the electroencephalogram ID.

FIG. 2 is a diagram showing an example of information stored in the storage unit 23 according to the embodiment. As shown in FIG. 2, the storage unit 23 stores, for example, stimulus type information 230, electroencephalogram information upon stimulation 231, weighting information 232, facilitation score information 233, evaluation information 234, evaluation type correspondence information 235, Promotion type information 236 is provided.

FIG. 3A is a diagram showing an example of stimulus type information 230 according to the embodiment. The stimulus type information 230 is information about each of a plurality of stimuli. In this example, the stimulus type information 230 includes items such as a stimulus type ID, content, and remarks. The stimulus type ID is information for uniquely identifying a stimulus type (stimulus type). The content indicates the specific content of the stimulus type, and in this example, nursery rhymes, comedy, and memories are indicated. The remarks indicate more specific contents of the stimulus (for example, in the case of nursery rhymes, the genre, title, etc.).

FIG. 3B is a diagram showing an example of electroencephalogram information upon stimulation 231 according to the embodiment. The electroencephalogram information upon stimulation 231 is information relating to an electroencephalogram upon stimulation. The stimulated electroencephalogram information 231 is generated for each stimulus type for the same electroencephalogram ID, that is, for the stimulated electroencephalogram of the same subject. In this example, the stimulated electroencephalogram information includes items such as an electroencephalogram ID, a stimulus type ID, and a degree of emotion. An electroencephalogram ID is information for uniquely identifying an electroencephalogram. The stimulus type ID is information that uniquely identifies the stimulus type. The emotional level is the level of emotion, and includes items for each of a plurality of types of emotions (excitement, liking, stress, concentration, calmness). Each of the multiple types of emotions has items for start, after start, and degree of change, and each item indicates the degree of emotion at the start, the degree of emotion after start, and the degree of change. . In this example, for the electroencephalogram during stimulation with the electroencephalogram ID (0001), the excitement level increases by 27 (=72-45) and the stress level increases by 21 (=|45-) due to the stimulus with the stimulus type ID (1002) (comedy). 66|) is shown to have descended.

FIG. 3C is a diagram illustrating an example of weighting information 232 according to an embodiment. The weighting information 232 is the weighting of each of the plurality of types of emotions determined from the viewpoint of promoting cognitive function. In this example, the weighting for excitement is 0.8, the weighting for liking is 0.3, the weighting for stress is -0.8, the weighting for concentration is 0.1, and the weighting for calmness. is −0.1. Weighting information may be generated according to categories such as gender and age.

FIG. 3D is a diagram illustrating an example of promotion score information 233 according to an embodiment. The facilitation score information 233 is information relating to facilitation scores calculated based on stimulated electroencephalograms. The facilitation score information 233 is generated for each stimulus type for the same electroencephalogram ID. In this example, the facilitation score information includes items such as an electroencephalogram ID, a stimulus type ID, and a degree of emotion. Since these items are equivalent to the electroencephalogram information upon stimulation 231, the description thereof will be omitted. Each of the plurality of types of emotions has items of degree of change and weighted degree of change. The degree of change is the same as the degree of change in the stimulated electroencephalogram information 231 . The degree of weighting change indicates a value obtained by multiplying the degree of change by a weight corresponding to the emotion indicated in the weighting information 232 . In addition, there is an item of facilitation score by integrating each of multiple types of emotions. The facilitation score indicates a value obtained by adding up the degree of weighting change as a point indicating the facilitation score. In this example, it is shown that the facilitation score due to the stimulus with the stimulus type ID (1002) (comedy) was 46 points for the stimulated electroencephalogram with the electroencephalogram ID (0001).

FIG. 3E is a diagram illustrating an example of rating information 234 according to an embodiment. The evaluation information 234 is information relating to the evaluation of the stimulated electroencephalogram. The evaluation information 234 is generated for each stimulus type for the same electroencephalogram ID. In this example, the evaluation information includes items such as electroencephalogram ID, stimulation type ID, facilitation score, and evaluation. Each item of electroencephalogram ID and stimulus type ID is equivalent to electroencephalogram information during stimulation 231 , and facilitation score is equivalent to facilitation score of facilitation score information 233 . The evaluation shows the evaluation according to the facilitation score. In this example, it is shown that the electroencephalogram during stimulation of the electroencephalogram ID (0001) was evaluated as "B" by the stimulation of the stimulation type ID (1002) (comedy).

FIG. 3F is a diagram illustrating an example of evaluation type correspondence information 235 according to the embodiment. The evaluation type correspondence information 235 is information indicating the relationship between a combination of multiple types of evaluations for each emotion and a promotion type. Thus, promotion types may be classified into a plurality of types such as type 1 to type N (N is any natural number equal to or greater than 2). In this example, it is shown that the electroencephalogram upon stimulation is classified into facilitation type 1, where nursery rhymes are graded A, comedy is graded C, and memories are graded C. It also shows that the electroencephalogram upon stimulation is classified into facilitation type 2, where nursery rhymes are graded A, comedy is graded B, and memories are graded C.

FIG. 3G is a diagram illustrating example promotion type information 236 in accordance with an embodiment. The facilitation type information 236 is information indicating which facilitation type the subject's stimulated electroencephalogram belongs to. Facilitation type information 236 is generated for each electroencephalogram ID. This example shows that the stimulated electroencephalogram of the subject with the electroencephalogram ID (0001) is classified as facilitation type 2. FIG. Promotion type 2 corresponds to the type of the evaluation type correspondence information 235, where nursery rhymes are rated A, comedy is rated B, and memories are rated C. In other words, from the electroencephalogram during stimulation of this subject, the stimulus that promotes the subject's cognitive function the most is "children's song", the stimulus that is slightly promoted is "comedy", and the stimulus that is hardly promoted is "memories". ” indicates that it was determined that

Returning to FIG. 1, the learning device 30 generates a trained model obtained by learning the relationship between resting electroencephalograms and facilitation types through machine learning. The learning device 30 includes, for example, a learning target electroencephalogram acquisition unit 31 , a facilitation type acquisition unit 32 , a learning data set generation unit 33 , and a trained model generation unit 34 .

The learning target electroencephalogram acquisition unit 31 acquires information indicating the subject's resting electroencephalogram measured by the electroencephalogram measurement device 10 and outputs the acquired information to the learning data set generation unit 33 .
The facilitation type acquisition unit 32 acquires information indicating the facilitation type of the electroencephalogram during stimulation of the subject determined by the electroencephalogram analyzer 20 and outputs the acquired information to the learning data set generation unit 33 .
The learning data set generation unit 33 uses the resting electroencephalogram acquired from the learning target electroencephalogram acquisition unit 31 and the facilitation type acquired from the facilitation type acquisition unit 32 to generate a learning data set. The learning data set generation unit 33 generates a learning data set by combining resting electroencephalograms and facilitation types that are associated with the same electroencephalogram ID.

Thereby, the features of the resting electroencephalogram are associated with the facilitation type. For example, resting brain waves with average values of excitement and stress greater than a certain value are associated with facilitation type 1, in which cognitive function is most promoted by the stimulus of "children's songs" but is hardly promoted by other stimuli. . In addition, for example, brain waves at rest with an average stress value of moderate (for example, about 40 to 60) are most cognitively promoted by the stimulation of "children's songs", but are slightly promoted by the stimulation of "comedy". It corresponds to facilitation type 2, which is hardly stimulated by the stimulus "remember".

The learning data set generation unit 33 acquires resting electroencephalograms (an example of “learning target electroencephalograms”) and facilitation types of an unspecified number of subjects, and generates a predetermined number of learning data sets. The larger the number of data sets for learning, the more various relationships between resting brain waves and facilitation types can be learned.
Further, the learning data set generation unit 33 may generate a plurality of learning data sets according to attributes of the subject (for example, sex, age, degree of cognitive function, etc.). In this case, the learning data set generator 33 refers to the attribute information based on the electroencephalogram ID. The attribute information is information in which the electroencephalogram ID and the attribute information of the subject are linked, and is information stored in a storage unit (not shown) of the learning device 30, for example.

The trained model generating unit 34 generates a trained model by performing machine learning on the learning model using the learning dataset generated by the learning dataset generating unit 33 . The trained model generation unit 34 trains a learning model by supervised learning. The learning model is, for example, a CNN (Convolutional Neural Network). A CNN is a model composed of three layers: an input layer, a hidden layer (hidden layer), and an output layer. Data to be estimated (input data) is input to the input layer. The output layer outputs data (estimation result) indicating the result of learning. The hidden layer performs the core processing of learning. For example, a hidden layer converts an input into a value expressed by a function called an activation function (transfer function) and outputs the value. For example, the activation function is a normalized linear function, a sigmoid function, a step function, etc., but is not limited to these, and any function may be used.
The input of the training data set in this embodiment is resting electroencephalograms, and the output is of the facilitation type.

The trained model generation unit 34 inputs the input data of the learning data set to the learning model. The learning model outputs estimation results from the output layer through hidden layer processing on input data. The learning model adjusts the processing parameters of the hidden layer so that the estimation result output from the output layer approaches the output of the data set for learning. The trained model generation unit 34 repeatedly adjusts the processing parameters of the hidden layer so that the estimation result output from the output layer approaches the output of the learning data set for all of the predetermined number of learning data sets. conduct. In this way, a learning model that has been trained so as to be able to output values close to the output of the learning data set as an estimation result with respect to the input of the learning data set is the trained model. The trained model generating unit 34 transmits information indicating the generated trained model to the estimation device 40 .

The estimating device 40 uses the resting electroencephalogram of the subject to be estimated (an example of an “estimation target electroencephalogram”) and the trained model to estimate the promotion type of the resting electroencephalogram to be estimated. The estimation device 40 includes, for example, an estimation target electroencephalogram acquisition unit 41 , a facilitation type estimation unit 42 , and a learned model storage unit 43 . The estimation target electroencephalogram acquisition unit 41 acquires a resting electroencephalogram for which the facilitation type is to be estimated, from the electroencephalogram measurement device 10 , and outputs the acquired resting electroencephalogram to the facilitation type estimation unit 42 . The learned model storage unit 43 stores the learned model generated by the learning device 30 . The facilitation type estimation unit 42 inputs the resting electroencephalogram from the estimation target electroencephalogram acquisition unit 41 to the trained model. The facilitation type estimation unit 42 uses the output from the trained model as an estimation result of estimating the facilitation type for the resting electroencephalogram. The promotion type estimation unit 42 displays the estimation result on, for example, a display unit (not shown) of the estimation device 40 . Alternatively, the promotion type estimation unit 42 may store the estimation result in a storage unit (not shown) of the estimation device 40 .

FIG. 4 is a sequence diagram showing the flow of processing performed by the cognitive function promotion support system 1 according to the embodiment. The processing performed by the cognitive function promotion support system 1 has a learning stage and an execution stage.

First, the flow of processing in the learning stage will be described.
The electroencephalogram measurement device 10 measures an electroencephalogram (encephalogram at rest) at rest with eyes closed (step S<b>10 ), and transmits information indicating the measured electroencephalogram at rest to the learning device 30 . The learning device 30 acquires information indicating a resting electroencephalogram from the electroencephalogram measurement device 10 (step S11).
The electroencephalogram measurement device 10 measures electroencephalograms during stimulation (electroencephalograms during stimulation) (step S<b>12 ), and transmits information indicating the measured electroencephalograms during stimulation to the electroencephalogram analyzer 20 . The electroencephalogram analyzer 20 acquires information indicating the stimulated electroencephalogram from the electroencephalogram measurement device 10 (step S13).
The electroencephalogram analyzer 20 determines the facilitation type of the stimulated electroencephalogram acquired from the electroencephalogram measurement device 10 (step S 14 ), and transmits the determined facilitation type to the learning device 30 . The learning device 30 acquires information indicating the promotion type from the electroencephalogram analysis device 20 (step S14).
The electroencephalogram analyzer 20 generates a learning data set by combining the resting electroencephalogram acquired in step S11 and the facilitation type acquired in step S14 (step S15).
The cognitive function promotion support system 1 generates a predetermined number of learning data sets by repeating step S100 (steps S10 to S15).
The learning device 30 generates a trained model using the training data set (step S20), and transmits the generated trained model to the estimation device 40. FIG. The estimation device 40 stores the learned model acquired from the learning device 30 (step S21).

Next, the flow of processing in the execution stage will be described.
The electroencephalogram measurement device 10 measures an electroencephalogram (encephalogram at rest) at rest with eyes closed (step S<b>30 ), and transmits information indicating the measured electroencephalogram at rest to the estimation device 40 . The estimating device 40 acquires information indicating a resting electroencephalogram from the electroencephalogram measuring device 10 (step S31). The estimating device 40 estimates the facilitation type of the resting electroencephalogram based on the output obtained by inputting the acquired resting electroencephalogram to the trained model stored in step S21 (step S32).

As described above, the cognitive function promotion support system 1 of the embodiment includes the emotion analysis unit 21, the promotion type determination unit 22, the trained model generation unit 34, the estimation target electroencephalogram acquisition unit 41, and the promotion type estimation unit. 42. The emotion analysis unit 21 extracts a plurality of types of emotion levels including at least the degree of excitement (elevation) and the degree of stress from the electroencephalogram during stimulation, which indicates the electroencephalogram when receiving a predetermined stimulation. The facilitation type determination unit 22 determines which one of a plurality of facilitation types classified from the viewpoint of promoting cognitive function is the electroencephalogram upon stimulation based on the degrees of the plurality of types of emotions extracted by the emotion analysis unit 21. . The trained model generation unit 34 learns a learning data set in which the resting electroencephalogram and the information indicating the facilitation type are associated with each unspecified person to be measured, so that the resting electroencephalogram and the facilitation type are learned. Generate a trained model that has learned the relationship between The estimation target electroencephalogram acquisition unit 41 acquires an estimation target resting electroencephalogram. The facilitation type estimation unit 42 estimates the facilitation type in the estimation target resting electroencephalogram using the estimation target resting electroencephalogram and the trained model.

Thus, in the cognitive function promotion support system 1 of the embodiment, the promotion type of the target user can be estimated from the resting electroencephalogram of the target user as the estimation target. The promotion type is a type classified from the viewpoint of what kind of stimulus promotes cognitive function. Therefore, a user's reaction to a stimulus can be estimated in advance without actually trying it.

Further, the facilitation type is determined using the degree of emotion that has changed in the stimulated electroencephalogram extracted by the emotion analysis unit 21 . By using a trained model that has learned the relationship between such promotion types and resting EEG, it is possible to estimate the promotion type based on deep psychology as well as the hobbies and preferences that the target user is consciously aware of. Is possible.
By estimating such a promotion type in advance, the cognitive function promotion support system 1 of the embodiment efficiently selects a stimulus according to the promotion type without actually trying reactions to all stimuli, and effectively It can promote cognitive function.
In addition, even if the target user asks about his or her hobbies or preferences and does not receive a correct answer, it is possible to estimate the promotion type of the target user.

Further, the facilitation type is determined using the degree of emotion that has changed in the stimulated electroencephalogram extracted by the emotion analysis unit 21 . Since the brain waves at rest and the brain waves during stimulation of the same person are closely related as the brain waves of the person, there is a correlation between the brain waves at rest and the facilitation type determined based on the brain waves during stimulation. Therefore, by performing estimation using a trained model that has learned the relationship between resting electroencephalograms and facilitation types, it is possible to accurately estimate facilitation types from the target user's resting electroencephalograms.

The cognitive function promotion support system 1 of the embodiment may function as a learning system. In this case, the learning system includes an emotion analysis unit 21 , a promotion type determination unit 22 and a trained model generation unit 34 . Thereby, the learning system can generate a trained model that has learned the relationship between the resting electroencephalogram and the facilitation type. By using such a trained model, the user's reaction to the stimulus can be presumed without actually trying it, and the same effect as described above can be obtained.

The cognitive function promotion support system 1 of the embodiment may function as an estimation system. In this case, the estimation system comprises a trained model storage unit 43 and a promotion type estimation unit 42 . The learned model storage unit 43 stores the learned model generated by the learning device 30 . As a result, the estimation system can pre-estimate the user's reaction to the stimulus without actually trying it, using a trained model that has learned the relationship between the resting EEG and the facilitation type. effect.

You may make it implement|achieve all or one part of the cognitive function promotion support system 1 in embodiment mentioned above by computer. In that case, a program for realizing this function may be recorded in a computer-readable recording medium, and the program recorded in this recording medium may be read into a computer system and executed. It should be noted that the "computer system" referred to here includes hardware such as an OS and peripheral devices. The term "computer-readable recording medium" refers to portable media such as flexible discs, magneto-optical discs, ROMs and CD-ROMs, and storage devices such as hard discs incorporated in computer systems. Furthermore, "computer-readable recording medium" refers to a program that dynamically retains programs for a short period of time, like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. It may also include something that holds the program for a certain period of time, such as a volatile memory inside a computer system that serves as a server or client in that case. Further, the program may be for realizing a part of the functions described above, or may be capable of realizing the functions described above in combination with a program already recorded in the computer system. It may be realized using a programmable logic device such as FPGA.

Although the embodiment of the present invention has been described in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and design and the like are included within the scope of the gist of the present invention.

DESCRIPTION OF SYMBOLS 1... Cognitive function promotion support system 10... Electroencephalogram measuring device 20... Electroencephalogram analyzer 21... Emotion analysis part (emotion analysis part)
22... Promotion type determination unit (promotion type determination unit)
23 -- Storage unit 30 -- Learning device 31 -- Learning target electroencephalogram acquisition unit 32 -- Promotion type acquisition unit 33 -- Learning data set generation unit 34 -- Learned model generation unit (learned model generation unit)
40 Estimation device 41 Estimation target electroencephalogram acquisition unit (estimation target electroencephalogram acquisition unit)
42 ... Promotion type estimation unit (estimation unit)
43 ... Learned model storage unit

Claims (4)

an emotion analysis unit that extracts a plurality of types of emotion levels including at least exhilaration and stress from stimulus electroencephalograms indicating electroencephalograms when a predetermined stimulus is received;
a facilitation type determination unit that determines a facilitation type that is classified from the viewpoint of promoting cognitive function with respect to the electroencephalogram during stimulation based on the degrees of the plurality of types of emotions extracted by the emotion analysis unit;
For each unspecified user, a learning data set in which a resting electroencephalogram indicating an electroencephalogram at rest with eyes closed and information indicating the facilitation type of the stimulating electroencephalogram are associated with each other is learned by a learning model. a trained model generation unit that generates a trained model that has learned the relationship between the time brain wave and the facilitation type;
an estimation target electroencephalogram acquisition unit that acquires an estimation target electroencephalogram that is the resting electroencephalogram to be estimated;
an estimation unit that estimates the facilitation type in the estimation target electroencephalogram using the estimation target electroencephalogram and the trained model;
Cognitive function promotion support system. an emotion analysis unit that extracts a plurality of types of emotion levels including at least exhilaration and stress from stimulus electroencephalograms indicating electroencephalograms when a predetermined stimulus is received;
a facilitation type determination unit that determines a facilitation type that is classified from the viewpoint of promoting cognitive function with respect to the electroencephalogram during stimulation based on the degrees of the plurality of types of emotions extracted by the emotion analysis unit;
For each unspecified user, learning a data set for learning in which a resting electroencephalogram indicating an electroencephalogram at rest with eyes closed and information indicating the facilitation type of the stimulating electroencephalogram is associated with the resting electroencephalogram and a trained model generation unit that generates a trained model that has learned a relationship with the promotion type;
A learning system with Information indicating the type of facilitation classified from the viewpoint of promoting cognitive function in each unspecified user's EEG at rest, which indicates an EEG at rest with eyes closed, and EEG at stimulation, which indicates an EEG when receiving a predetermined stimulus. and a learned model storage unit that stores a learned model that has learned the relationship between the resting electroencephalogram and the facilitation type by learning a data set for learning that associates and,
an estimation target electroencephalogram acquisition unit that acquires an estimation target electroencephalogram that is the resting electroencephalogram to be estimated;
an estimation unit that estimates the facilitation type in the estimation target electroencephalogram using the estimation target electroencephalogram and the trained model;
An estimation system with The emotion analysis unit extracts a plurality of degrees of emotion including at least the degree of exhilaration and the degree of stress from the electroencephalogram during stimulation, which indicates the electroencephalogram when receiving a predetermined stimulus,
a facilitation type determination unit that determines a facilitation type that is classified from the viewpoint of promoting cognitive function for the electroencephalogram during stimulation based on the degrees of the plurality of types of emotions extracted by the emotion analysis unit;
The trained model generation unit learns a learning data set in which resting electroencephalograms indicating electroencephalograms at rest with eyes closed and information indicating the facilitation type of the stimulated electroencephalograms for each unspecified user are associated. generates a trained model that has learned the relationship between the resting electroencephalogram and the facilitation type,
an estimation target electroencephalogram acquisition unit acquiring an estimation target electroencephalogram that is the resting electroencephalogram to be estimated;
The estimation unit estimates the facilitation type in the estimation target electroencephalogram using the estimation target electroencephalogram and the trained model.
Cognitive function promotion support method.

Images