阅读说明：本技术 认知功能评估装置、认知功能评估系统、认知功能评估方法及程序 (Cognitive function evaluation device, cognitive function evaluation system, cognitive function evaluation method, and program ) 是由 南云亮佑 角贞幸 细川满春 阿部贤吾 松村吉浩 西山高史 苅安诚 吉村贵子 外山稔 于 2019-03-15 设计创作，主要内容包括：认知功能评估装置(100)具备：取得部(110),其取得表示被评估者(U)响应赋予被评估者(U)的问题而发出的语音的语音数据；评估部(130),其通过进行第一评估及第二评估来评估被评估者(U)的认知功能,该第一评估基于在由取得部(110)取得的语音数据中的规定期间中被评估者(U)发出语音的时间所占的比例,该第二评估基于由取得部(110)取得的语音数据的基本频率；以及输出部(140),其输出评估部(130)评估出的评估结果。(A cognitive function assessment device (100) is provided with: an acquisition unit (110) that acquires speech data representing speech uttered by the person (U) to be evaluated in response to a question given to the person (U) to be evaluated; an evaluation unit (130) that evaluates the cognitive function of the person (U) being evaluated by performing a first evaluation based on the proportion of time that the person (U) being evaluated utters speech in a predetermined period in the speech data acquired by the acquisition unit (110), and a second evaluation based on the fundamental frequency of the speech data acquired by the acquisition unit (110); and an output unit (140) that outputs the evaluation result evaluated by the evaluation unit (130).)

1. A cognitive function assessment device is provided with:

an acquisition unit that acquires voice data representing a voice uttered by an evaluator in response to a question given to the evaluator;

an evaluation unit that evaluates the cognitive function of the person to be evaluated by performing a first evaluation based on a ratio of time during which the person to be evaluated utters a voice in the voice data acquired by the acquisition unit for a predetermined period, and a second evaluation based on a fundamental frequency of the voice data acquired by the acquisition unit; and

And an output unit that outputs the evaluation result evaluated by the evaluation unit.

2. The cognitive function assessment device according to claim 1,

the evaluation unit performs the first evaluation based on a ratio of a time during which the person to be evaluated utters a voice in the predetermined period belonging to a latter half of the voice data.

3. The cognitive function assessment device according to claim 1,

the evaluation unit performs the first evaluation based on a comparison of a ratio of a time during which the person to be evaluated utters the voice in a first period in the voice data and a ratio of a time during which the person to be evaluated utters the voice in a second period later than the first period in the voice data.

4. The cognitive function assessment device according to any one of claims 1 to 3,

the evaluation unit performs the second evaluation based on a variation per unit time of the fundamental frequency.

5. The cognitive function assessment device according to any one of claims 1 to 3,

the evaluation unit performs the second evaluation based on a fluctuation range per unit time of the fundamental frequency.

6. The cognitive function assessment device according to any one of claims 1 to 5,

the evaluation unit also evaluates the cognitive function of the person to be evaluated by performing a third evaluation based on the time until the person to be evaluated starts to utter voice after the question is given.

7. The cognitive function assessment device according to any one of claims 1 to 5,

the evaluation unit also evaluates the cognitive function of the person to be evaluated by performing a third evaluation based on the time until completion of the response to the question after the question is given.

8. The cognitive function assessment device according to any one of claims 1 to 7,

the voice data represents a voice uttered by the person under evaluation in response to the question replying to a sentence uttered by the instructor.

9. The cognitive function assessment device according to claim 8,

the sentence is a sentence having 5 phrases or more including a plurality of sets of subjects and predicates.

10. The cognitive function assessment device according to claim 8 or 9,

the voice data represents a voice uttered by the person under evaluation in response to the question that repeats the sentence uttered by the instructor after a prescribed time has elapsed.

11. The cognitive function assessment device according to any one of claims 1 to 7,

the voice data represents voice uttered by the person under evaluation in response to the question verbally explaining a situation depicted by a picture or photograph prompted by an instructor.

12. The cognitive function assessment device according to any one of claims 1 to 7,

the voice data represents a voice uttered by the evaluators in response to the question of reading out a number under a condition specified by an indicator.

13. The cognitive function assessment device according to any one of claims 1 to 7,

the speech data represents speech uttered by the person under evaluation in response to the question listing words satisfying a condition specified by an instructor.

14. A cognitive function assessment system is provided with:

the cognitive function assessment device according to any one of claims 1 to 13;

a sound receiving device that detects a voice of the evaluators; and

a display device that displays the evaluation result output by the output section.

15. A cognitive function assessment method is a computer-implemented cognitive function assessment method, and comprises the following steps:

An acquisition step of acquiring voice data representing a voice uttered by an evaluator in response to a question given to the evaluator;

an evaluation step of evaluating the cognitive function of the person to be evaluated by performing a first evaluation based on a ratio of a time during which the person to be evaluated utters a voice in the voice data acquired in the acquisition step for a predetermined period and a second evaluation based on a fundamental frequency of the voice data acquired in the acquisition step; and

and an output step of outputting the evaluation result evaluated in the evaluation step.

16. A program for causing a computer to execute the cognitive function assessment method according to claim 15.

Technical Field

The present invention relates to a cognitive function assessment device, a cognitive function assessment system, a cognitive function assessment method, and a program that can assess cognitive function of a person to be assessed.

Background

Conventionally, as a test for evaluating cognitive function, there are a modified Changchun-type simple intellectual evaluation Scale (HDS-R), MMSE (Mini-mental State evaluation: brief intellectual State Examination), CDR (Clinical Dementia evaluation Scale), and the like as a method for describing answers on a test paper by a patient to be evaluated for cognitive function, i.e., a subject to be evaluated. These methods are methods for examining a subject to be evaluated in a medical institution by a trained physician, a clinical psychologist, or the like.

Here, in the evaluation method using the test paper, there is a problem that the subject to be evaluated is forced to bear the burden of a long test time. In addition, in the case where the test is repeatedly performed on the evaluated person, there is a question that the evaluated person remembers the answer because it is the same test. In order to solve this problem, a technique is disclosed in which a question and answer in a test conducted by an examinee are recorded by a doctor or the like, and the voice of the examinee is analyzed (for example, refer to patent document 1).

Disclosure of Invention

Problems to be solved by the invention

For the evaluation of cognitive function, it is required to evaluate the cognitive function of an evaluator more easily.

Therefore, an object of the present invention is to provide a cognitive function assessment apparatus and the like that can easily assess cognitive functions of a person to be assessed.

Means for solving the problems

A cognitive function assessment device according to an embodiment of the present invention includes: an acquisition unit that acquires voice data representing a voice uttered by an evaluator in response to a question given to the evaluator; an evaluation unit that evaluates the cognitive function of the person to be evaluated by performing a first evaluation based on a ratio of a time during which the person to be evaluated utters a voice in the voice data acquired by the acquisition unit for a predetermined period and a second evaluation based on a fundamental frequency of the voice data acquired by the acquisition unit; and an output unit that outputs the evaluation result evaluated by the evaluation unit.

A cognitive function assessment system according to an embodiment of the present invention includes: the cognitive function assessment device; a sound receiving device that detects a voice of the evaluators; and a display device that displays the evaluation result output by the output section.

A cognitive function assessment method according to an aspect of the present invention is a computer-implemented cognitive function assessment method including the steps of: an acquisition step of acquiring voice data representing a voice uttered by an evaluator in response to a question given to the evaluator; an evaluation step of evaluating the cognitive function of the person to be evaluated by performing a first evaluation based on a ratio of a time during which the person to be evaluated utters a voice in the voice data acquired in the acquisition step for a predetermined period and a second evaluation based on a fundamental frequency of the voice data acquired in the acquisition step; and an output step of outputting the evaluation result evaluated in the evaluation step.

A program according to an embodiment of the present invention is a program for causing a computer to execute the cognitive function assessment method.

ADVANTAGEOUS EFFECTS OF INVENTION

According to the cognitive function assessment device and the like of the present invention, the cognitive function of the person to be assessed can be assessed easily.

Drawings

Fig. 1 is a diagram showing a configuration of a cognitive function assessment system according to an embodiment.

Fig. 2 is a block diagram showing a characteristic functional configuration of the cognitive function assessment device according to the embodiment.

Fig. 3 is a flowchart showing a processing procedure of evaluating the cognitive function of the person to be evaluated by the cognitive function evaluation device according to the embodiment.

Fig. 4 is a diagram showing an example of an image corresponding to the evaluation result.

Fig. 5 is a diagram showing a first example of a method for acquiring voice data.

Fig. 6 is a diagram showing a second example of the method of acquiring voice data.

Fig. 7 is a diagram showing a third example of the method of acquiring voice data.

Fig. 8 is a diagram showing a fourth example of the method of acquiring voice data.

Fig. 9 is a diagram showing a fifth example of the method of acquiring voice data.

Fig. 10 is a diagram for explaining the scale of the sound emission time.

Fig. 11 is a graph showing a temporal change in fundamental frequency.

Fig. 12 is a diagram showing the configuration of a cognitive function assessment system according to modification 1 of the embodiment.

Fig. 13 is a diagram showing the configuration of a cognitive function assessment system according to modification 2 of the embodiment.

Detailed Description

Hereinafter, embodiments will be described with reference to the drawings. The embodiments described below are all general or specific examples. The numerical values, shapes, materials, structural elements, arrangement positions and connection modes of the structural elements, steps, order of the steps, and the like shown in the following embodiments are examples, and the gist thereof is not limited to the invention. Among the components of the following embodiments, components not described in the independent claims representing the uppermost concept will be described as arbitrary components.

The drawings are schematic and not strictly schematic. In the drawings, substantially the same components are denoted by the same reference numerals, and redundant description may be omitted or simplified.

In the following embodiments, the expression indicating the direction is used. For example, parallel means not only completely parallel but also substantially parallel, i.e., including deviations of, for example, about several%.

(embodiment mode)

[ Structure of cognitive function assessment device ]

The configuration of the cognitive function assessment system according to the embodiment will be described. Fig. 1 is a diagram showing a configuration of a cognitive function assessment system according to an embodiment.

The cognitive function assessment system 200 is a device for assessing the cognitive function of the person under assessment U based on the voice uttered by the person under assessment U. The cognitive function means the ability to recognize, memorize, or judge. As a specific example, the cognitive function assessment apparatus 100 assesses whether or not a person with dementia (a patient with dementia).

Dementia means the above-mentioned symptom of deterioration of cognitive function. One specific example of dementia includes Alzheimer's dementia. Since dementia has no subjective symptom, the patients with dementia are prompted to go to a hospital for a medical examination by their family or a third person, and the patients with dementia are subjected to the medical examination by a doctor. In addition, whether or not the subject U is dementia can be confirmed by subjecting the subject U to a batch test for diagnosing dementia, such as MoCA (Montreal cognitive assessment) test.

In addition, the MoCA test requires about 15 minutes. In order to diagnose the change of the user U over time, the MoCA test needs to be performed a plurality of times every other day to determine whether the user U is mentally disabled. That is, in the MoCA test, a long period is required to diagnose whether or not the subject U is dementia.

It is known that a person with dementia and a person without dementia (healthy person) have different voices even if the spoken word is the same word.

The cognitive function assessment system 200 is a device that assesses the cognitive function of the person under assessment U with high accuracy by analyzing the voice of the person under assessment U.

As shown in fig. 1, the cognitive function assessment system 200 includes a cognitive function assessment apparatus 100, a sound pickup apparatus 300, and a display device 400.

The cognitive function evaluation device 100 is a computer that: voice data representing a voice uttered by the person to be evaluated U is acquired by the sound pickup apparatus 300, and the cognitive function of the person to be evaluated U is evaluated based on the acquired voice data.

The sound pickup device 300 is a microphone that detects a voice uttered by the person to be evaluated U and outputs voice data representing the detected voice to the cognitive function evaluation device 100. In order to detect the voice uttered by the person U to be evaluated with high accuracy, the sound shielding wall 310 and/or the blowout preventer 320 may be disposed around the sound pickup device 300.

The display device 400 displays an image based on the image data output from the cognitive function evaluation apparatus 100. Specifically, the display device 400 is a monitor apparatus configured by a liquid crystal panel, an organic EL panel, or the like. As the display device 400, an information terminal such as a television, a smart phone, or a tablet terminal may be used.

The cognitive function evaluation device 100, the sound pickup device 300, and the display device 400 may be connected by wire or wirelessly as long as they can transmit and receive voice data or image data.

The cognitive function assessment apparatus 100 analyzes the voice of the person U to be assessed based on the voice data detected by the sound pickup apparatus 300, assesses the cognitive function of the person U to be assessed based on the result of the analysis, and outputs image data for displaying an image representing the assessment result to the display device 400. Thus, the cognitive function assessment apparatus 100 can notify the level of cognitive function to an mentally deficient patient who does not have subjective symptoms, and thus can prompt the mentally deficient patient to receive a doctor's examination, for example. In other words, the cognitive function assessment apparatus 100 can assist an mentally disabled patient to receive the doctor's examination by notifying the mentally disabled patient of the degree of cognitive function.

The cognitive function evaluation device 100 is, for example, a personal computer, but may be a server device.

Fig. 2 is a block diagram showing a functional configuration of the cognitive function assessment apparatus 100. The cognitive function evaluation device 100 includes an acquisition unit 110, a calculation unit 120, an evaluation unit 130, an output unit 140, and a storage unit 150.

The acquisition unit 110 acquires the voice data detected by the sound pickup device 300. The acquisition unit 110 is a communication interface for performing wired communication or wireless communication, for example.

The calculation unit 120 is a processing unit that analyzes the voice data of the person U under evaluation acquired by the acquisition unit 110. Specifically, the calculation unit 120 is realized by a processor, a microcomputer, or a dedicated circuit.

The evaluation unit 130 evaluates the cognitive function of the person U to be evaluated by comparing the analysis result of the speech data by the calculation unit 120 with the reference data 151 stored in the storage unit 150. Specifically, the evaluation unit 130 is realized by a processor, a microcomputer, or a dedicated circuit.

The output unit 140 outputs the evaluation result of the cognitive function of the person under evaluation U evaluated by the evaluation unit 130 to the display device 400. The output unit 140 is, for example, a communication interface for performing wired communication or wireless communication.

The storage unit 150 is a storage device that stores reference data 151 that becomes an evaluation criterion of the cognitive function of a person. The evaluation unit 130 refers to the reference data 151 when evaluating the degree of cognitive function of the subject U. The storage unit 150 is realized by, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), a semiconductor Memory, an HDD (Hard Disk Drive), or the like.

The storage unit 150 also stores programs executed by the calculation unit 120 and the evaluation unit 130, and image data indicating an evaluation result used when the evaluation result of the cognitive function of the person to be evaluated U is output.

[ order of treatment in the cognitive function assessment method ]

Next, a specific processing procedure of the cognitive function assessment method executed by the cognitive function assessment apparatus 100 will be described. Fig. 3 is a flowchart showing a processing procedure in which the cognitive function assessment apparatus 100 assesses the cognitive function of the person U to be assessed.

First, the acquisition unit 110 acquires the voice data of the user U to be evaluated via the sound pickup apparatus 300 (step S101).

Next, the calculation unit 120 calculates a feature amount based on the voice data acquired by the acquisition unit 110 (step S102). In step S102, for example, the calculation unit 120 calculates, as the feature amount, the proportion of the time during which the evaluators U utter the voice in a predetermined period in the voice data. The calculation unit 120 calculates the fundamental frequency of the speech data as the feature value.

Next, the evaluation unit 130 evaluates the cognitive function of the person U to be evaluated based on the feature amount calculated by the calculation unit 120 in step S102 (step S103). In step S103, the reference data 151 stored in the storage unit 150 is used as an evaluation criterion.

Next, the output unit 140 outputs the evaluation result of the cognitive function of the person to be evaluated U evaluated by the evaluation unit 130 (step S104). In step S104, the output section 140 acquires, for example, image data of an image corresponding to the evaluation result evaluated by the evaluation section 130 in step S103 from the storage section 150, and transmits the acquired image data to the display device 400.

The display device 400 acquires image data output by the output unit 140 and displays an image based on the image data. Fig. 4 is a diagram showing an example of an image corresponding to the evaluation result. The image shown in fig. 4 indicates a tendency of deterioration of the cognitive function of the evaluated subject U.

In this way, by displaying the evaluation result as an image, the person U to be evaluated can easily confirm the evaluation result of the cognitive function. In addition, when the cognitive function evaluation device 100 is used to evaluate the cognitive function, for example, when the person U to be evaluated is at home, the cognitive function evaluation device 100 can prompt the person U to be evaluated to see a doctor by displaying an image.

[ method of acquiring Voice data ]

Next, a method of acquiring voice data in step S101 will be described. In step S101, in order to make the level of dementia of the person U to be evaluated appear in the voice data significantly, the voice data is acquired in a state where a certain degree of load is applied to the brain of the person U to be evaluated. Specifically, a question is given to the person U to be evaluated, and the acquisition unit 110 acquires voice data indicating a voice uttered by the person U to be evaluated in response to the question given to the person U to be evaluated.

Here, various methods can be considered as a method of assigning a problem. An example of a method of acquiring voice data will be described below. Fig. 5 is a diagram showing a first example of a method for acquiring voice data.

In the example of fig. 5, the question that the indicator T utters is repeated is given to the user U to be evaluated. First, the indicator T indicates the evaluators U to repeat the sentence ((a) of fig. 5) to make them speak the sentence ((b) of fig. 5). Then, the evaluators U utter a voice in response to the question ((c) of fig. 5). The acquisition unit 110 acquires the speech data of such speech.

The term to be used is not particularly limited, but as described above, a slightly complicated term is preferable for the purpose of applying a certain degree of load to the brain of the subject U. In fig. 5 (b), for example, a sentence including a plurality of sets of subjects and predicates is used. In order to obtain voice data having a certain length, for example, 5 phrases or more are used. Instead of repeating the sentence, the question may be a plurality of numbers.

Fig. 6 is a diagram showing a second example of the method of acquiring voice data. In the example of fig. 6, the question that the instructor T utters is repeated is given to the evaluator U, as in the example of fig. 5. First, the indicator T indicates the evaluators U to repeat the sentence ((a) of fig. 6), and says the sentence ((b) of fig. 6). At this time, the voice is simultaneously instructed to start speaking after a predetermined time (for example, after 3 seconds) has elapsed. That is, in the example of fig. 6, the question that the word uttered by the indicator T is repeated after a predetermined time has elapsed is given to the user U. Then, the evaluators U respond to the question and emit voices after waiting for a prescribed time ((c) of fig. 6). The acquisition unit 110 acquires the speech data of such speech. Such a waiting time before speech is spoken is used for the purpose of applying a certain degree of load to the brain of the person U to be evaluated.

Fig. 7 is a diagram showing a third example of the method of acquiring voice data. In the example of fig. 7, the question depicted by the picture or photograph presented by the speech instruction instructor T is given to the person to be evaluated U. First, the indicator T indicates the content of the drawing or photograph which is described by the person U to be evaluated ((a) of fig. 7), and prompts the drawing or photograph ((b) of fig. 7). The evaluated person U lists the situation depicted by the presented drawing or photograph as much as possible ((c) of fig. 7). The acquisition unit 110 acquires the speech data of such speech.

Fig. 8 is a diagram showing a fourth example of the method of acquiring voice data. In the example of fig. 8, the subject U is given a question of reading out the number under the condition specified by the indicator T. First, the indicator T specifies a condition ((a) of fig. 8), and the person U to be evaluated reads out a number under the given condition ((b) of fig. 8). The acquisition unit 110 acquires the speech data of such speech.

Fig. 9 is a diagram showing a fifth example of the method of acquiring voice data. In the example of fig. 9, a question of listing words satisfying the condition specified by the indicator T is given to the person U to be evaluated. First, the indicator T specifies a condition ((a) of fig. 9), and the evaluated person U lists a word matching the assigned condition ((b) of fig. 9). The acquisition unit 110 acquires the speech data of such speech. The specified condition is, for example, a range (fish name, etc.), but may be a noun beginning with "i", or the like.

[ characteristic amount: proportion of sounding time)

Next, the feature amount calculated in step S102 will be described. The calculation unit 120 calculates, for example, a ratio of the utterance time of the user U to be evaluated as the feature amount. Fig. 10 is a diagram for explaining the scale of the sound emission time.

Fig. 10 shows a temporal change in the volume (power) of voice data representing a voice uttered by the evaluators U. The speech data includes a period during which the subject U utters and a period during which the subject U is silent. The calculation unit 120 determines, for example, a period in which the sound volume is equal to or greater than a predetermined threshold (for example, -50dB) as a period in which the user U is speaking. Further, the calculation unit 120 determines a period in which the sound volume does not reach the predetermined threshold as a period in which the user U is silent.

The utterance period is the total of the periods during which the evaluators U utter. The calculation unit 120 calculates the ratio of the utterance period to the predetermined period in the speech data acquired by the acquisition unit 110. Here, the predetermined period is, for example, a period from a time T1 when the indicator T ends giving the question to a time T2 when the evaluator U completes responding to the question (that is, the entire period T0 until the test ends). Note that the time T1 and the time T2 may be specified by voice recognition or the like, or may be specified by an evaluator such as the indicator T through a user interface (not shown) provided in the cognitive function evaluation device 100. The time t2 may be set in advance, for example, 30 seconds may elapse from the time t 1.

It can be considered that the cognitive function of the evaluated U whose utterance is interrupted is degraded. In addition, when the example-type questions as shown in fig. 7 and 9 are given, it is considered that the number of the examples of the evaluated person U whose cognitive function is degraded is reduced and the utterance time is shortened. Therefore, the evaluation unit 130 evaluates that the smaller the proportion of utterance time, the lower the cognitive function.

The predetermined period is not limited to the entire period T0 until the test is completed. For example, the predetermined period may be a period belonging to the second half of the voice data (in other words, the second half of the entire period T0). For example, when the evaluation target U is given the example-type question shown in fig. 9, the thought word gradually decreases and the utterance time gradually decreases regardless of the degree of the cognitive function of the evaluation target U. However, it can be considered that the number of words that the evaluators U think is smaller as the cognitive function deteriorates, and therefore the utterance time becomes shorter at an early stage. Therefore, the ratio of the utterance time in the predetermined period belonging to the second half of the speech data may be greatly different depending on the degree of cognitive function, and may be suitable for the evaluation of cognitive function.

The calculation unit 120 may calculate a change in the ratio of the sound emission time. For example, as shown in fig. 10, when the entire period from the end of the test is divided into 2 periods, i.e., the first period T1 and the second period T2, the calculation unit 120 may calculate the difference (i.e., the amount of change) between the ratio of the sound emission time in the first period T1 and the ratio of the sound emission time in the second period T2. The calculation unit 120 may calculate a ratio (that is, a change rate) of the proportion of the sounding time in the first period T1 to the proportion of the sounding time in the second period T2. In either case, the evaluation section 130 evaluates the cognitive function based on a comparison of the proportion of the utterance time in the first period T1 and the proportion of the utterance time in the second period T2.

As described above, it can be considered that the more deteriorated the cognitive function, the shorter the sound emission time of the evaluated person U becomes in the latter half of the entire period T0. Therefore, it can be considered that the change in the proportion of the utterance time (with the proportion of the utterance time in the first period T1 as a reference) is larger as the cognitive function of the person U under evaluation deteriorates. Therefore, the evaluation unit 130 evaluates that the greater the change in the proportion of utterance time, the lower the cognitive function. The entire period T0 may be divided into 3 or more periods.

[ characteristic amount: the time from the start of sounding during the entire period ]

The calculation unit 120 may calculate the entire period T0 shown in fig. 10 as the feature amount. That is, the calculation unit 120 may calculate, as the feature amount, a time from when the question is given to when the response to the question is completed.

For example, when the subject U is given a question of the rephrase type as shown in fig. 5 and 6, it is considered that the subject U whose cognitive function is degraded is difficult to rephrase due to the degradation of memory, and therefore it takes time until the rephrase is completed. Therefore, the evaluation unit 130 evaluates that the longer the entire period T0, the lower the cognitive function.

For example, when the example-type questions shown in fig. 7 and 9 are given, it is considered that the number of the examples of the person U to be evaluated whose cognitive function is degraded is small, and thus the utterance is completed quickly. Therefore, in this case, the evaluation unit 130 evaluates that the shorter the entire period T0, the lower the cognitive function.

The calculation unit 120 may calculate a time T3 (shown in fig. 10) from when the question is given to when the user U starts to utter the voice as the feature amount. It is considered that since the reaction speed of the evaluated person U with deteriorated cognitive function is decreased, it takes time until the utterance is started after the problem is given. Therefore, the evaluation unit 130 evaluates that the longer the time T3, the lower the cognitive function.

[ characteristic amount: fundamental frequency ]

The calculation unit 120 may calculate a variation per unit time of the fundamental frequency of the speech data as the feature value. Fig. 11 is a graph showing a temporal change in fundamental frequency.

The fundamental frequency means the number of vibrations of the sound source. That is, it means a musical interval of the voice uttered by the evaluator U. The variation per unit time of the fundamental frequency means a differential value of the fundamental frequency. With respect to the fundamental frequency, it is calculated, for example, from the initial peak of the autocorrelation function, but it may be calculated by other methods.

The fluctuation of the emotion of the evaluated person U whose cognitive function is degraded is small, and the fluctuation of the voice becomes small. Thus, it is considered that the variation of the fundamental frequency is reduced. In addition, it is considered that the person U to be evaluated with deteriorated cognitive function tends to have insufficient breathing (lung use method) during vocalization due to deterioration of physical function, and thus the variation of the basic frequency is small. Therefore, the evaluation unit 130 evaluates that the cognitive function is lower as the variation per unit time of the fundamental frequency of the voice data is smaller, for example.

The calculation unit 120 may calculate a fluctuation range per unit time of the fundamental frequency of the speech data as the feature amount. The fluctuation range per unit time of the fundamental frequency means a difference between the maximum value and the minimum value of the fundamental frequency in the unit time. In this case, the evaluation unit 130 evaluates that the smaller the fluctuation width per unit time of the fundamental frequency of the speech data, the lower the cognitive function, for the same reason as the above-described fluctuation of the fundamental frequency.

When calculating the fluctuation or fluctuation width of the fundamental frequency, the calculation unit 120 preferably processes only the period in which the user U is speaking in the speech data. As shown in fig. 11, the calculation unit 120 can determine a period during which the volume is equal to or greater than the threshold as a period during which the evaluator U utters. If the period in which the user U is uttering is selectively set as the processing target, the evaluation accuracy of the evaluation unit 130 is improved.

The calculation unit 120 may calculate, as the feature amount, a difference or a ratio between a fluctuation (or a fluctuation range) of the fundamental frequency in a first predetermined period (for example, 5 seconds) of a period in which the user U utters and a fluctuation (or a fluctuation range) of the fundamental frequency in a last predetermined period (for example, 5 seconds) of a period in which the user U utters. For example, the calculation unit 120 may use, as the feature quantity, a physical quantity obtained by normalizing the fluctuation (or fluctuation range) of the fundamental frequency in the first predetermined period (for example, 5 seconds) to the fluctuation of the fundamental frequency in the last predetermined period.

[ evaluation method ]

The evaluation unit 130 evaluates the cognitive function of the person to be evaluated U using at least 1 of the above feature amounts. However, if the evaluation is performed comprehensively using a plurality of feature amounts, the accuracy of the evaluation can be improved. For example, the evaluation unit 130 evaluates the cognitive function of the person to be evaluated U by performing a first evaluation based on the proportion of time during which the person to be evaluated U utters voice in the voice data for a predetermined period and performing a second evaluation based on the fundamental frequency of the voice data. The evaluation unit 130 can perform an evaluation using a plurality of feature amounts by, for example, summing up the score of the first evaluation determined from the reference data 151 and the score of the second evaluation determined from the reference data 151. Further, when adding the scores, the scores may be weighted according to the feature amount.

The reference data 151 is data indicating a correspondence relationship between the score and the feature value of the MoCA test, for example. The reference data 151 may be data indicating a relationship between a score of MMSE (Mini-Mental State evaluation) or the like and a feature amount, as long as the degree of cognitive function can be evaluated by comparing the feature amount with the reference data.

In addition, in the case where the presence or absence of the tendency of dementia is evaluated based on each feature amount, the evaluation unit 130 evaluates that the person U to be evaluated has the tendency of dementia, for example, in the case where all of the plurality of feature amounts used for the evaluation indicate the tendency of the presence of the tendency of dementia. In other words, the evaluation unit 130 evaluates that the person to be evaluated U has no tendency to develop dementia when at least 1 of the plurality of feature values used for the evaluation indicates a tendency to develop no dementia. However, the evaluation unit 130 may evaluate that the person U to be evaluated is prone to dementia when at least 1 of the plurality of feature values used for the evaluation indicates a tendency to be prone to dementia. In other words, the evaluation unit 130 may evaluate that the person U to be evaluated has no tendency to develop dementia when all of the plurality of feature amounts used for the evaluation indicate a tendency to develop no dementia.

[ Effect and the like ]

As described above, the cognitive function assessment apparatus 100 includes: an acquisition unit 110 that acquires speech data representing speech uttered by the user U in response to a question given to the user U; an evaluation unit 130 that evaluates the cognitive function of the user U by performing a first evaluation based on the proportion of the time during which the user U utters the voice in the voice data acquired by the acquisition unit 110 for a predetermined period, and performing a second evaluation based on the fundamental frequency of the voice data acquired by the acquisition unit 110; and an output unit 140 that outputs the evaluation result evaluated by the evaluation unit 130.

Such a cognitive function assessment apparatus 100 can easily assess the cognitive function of the person U to be assessed by acquiring the voice data. In addition, since 2 feature quantities, i.e., the sounding time and the fundamental frequency, are used, the evaluation accuracy is improved.

For example, the evaluation unit 130 performs the first evaluation based on the proportion of the time during which the person to be evaluated U utters voice in the predetermined period belonging to the second half of the voice data.

It is considered that, in the latter half of the speech data, a difference in utterance time is likely to occur depending on the cognitive function. Therefore, the cognitive function assessment apparatus 100 can improve the accuracy of assessment of the cognitive function of the person U to be assessed.

For example, the evaluation unit 130 performs the first evaluation based on a comparison between a ratio of a time during which the evaluators U utter the voice in the first period in the voice data and a ratio of a time during which the evaluators U utter the voice in the second period later than the first period in the voice data.

Such a cognitive function assessment device 100 can assess the cognitive function of the person to be assessed U based on the temporal change in the proportion of the utterance time.

Further, for example, the evaluation unit 130 performs the second evaluation based on the variation per unit time of the fundamental frequency.

Such a cognitive function assessment device 100 can assess the cognitive function of the person U to be assessed based on the change per unit time of the fundamental frequency of the voice data.

For example, the evaluation unit 130 performs the second evaluation based on the fluctuation range of the fundamental frequency per unit time.

Such a cognitive function assessment device 100 can assess the cognitive function of the person to be assessed U based on the fluctuation width per unit time of the fundamental frequency of the voice data.

For example, the evaluation unit 130 also evaluates the cognitive function of the user U by performing a third evaluation based on the time from when the user U starts to utter the voice after being given the question.

Such a cognitive function assessment device 100 can assess the cognitive function of the person to be assessed U based on the time from when the person to be assessed U starts to utter a voice after the question is given.

In addition, for example, the evaluation unit 130 evaluates the cognitive function of the person to be evaluated U by performing a third evaluation based on the time from when the question is given to the completion of the response to the question.

Such a cognitive function assessment device 100 can assess the cognitive function of the person U to be assessed based on the time from when the question is given to when the response to the question is completed.

The voice data represents, for example, a voice uttered by the user U in response to a question that repeats a sentence uttered by the indicator T.

Such a cognitive function assessment apparatus 100 can set the following speech data as processing targets: the voice data represents a voice uttered by the evaluators U in response to a question that repeats a sentence uttered by the instructor T.

For example, the above-described sentence is a sentence including 5 phrases or more including a plurality of sets of subjects and predicates.

This enables the degree of dementia of the person U to be evaluated to be significantly present in the voice data. In addition, the acquisition unit 110 can acquire voice data for a long time.

The voice data represents, for example, a voice uttered by the user U in response to a question that the instructor T utters repeatedly after a predetermined time has elapsed.

Such a cognitive function assessment apparatus 100 can set the following speech data as processing targets: the voice data represents a voice uttered by the human subject U in response to a question that the instructor T utters repeatedly after a predetermined time has elapsed.

In addition, the voice data represents, for example, voice uttered by the person U to be evaluated in response to a question depicted in a picture or photograph of the verbal explanation instructor T.

Such a cognitive function assessment apparatus 100 can set the following speech data as processing targets: the voice data represents voice uttered by the person U to be evaluated in response to a question such as a situation depicted by a picture or photograph that verbally explains the prompt of the instructor T.

In addition, the voice data represents, for example, a voice uttered by the evaluators U in response to a question of reading out a number under a condition specified by the designators T.

Such a cognitive function assessment apparatus 100 can set the following speech data as processing targets: the voice data represents a voice uttered by the evaluators U in response to a question of reading out a number under a condition specified by the designator T.

In addition, the voice data represents, for example, a voice uttered by the person U to be evaluated in response to a question listing words satisfying the condition specified by the indicator T.

Such a cognitive function assessment apparatus 100 can set the following speech data as processing targets: the voice data represents a voice uttered by the evaluators U in response to a question listing words satisfying the condition specified by the designator T.

In addition, the cognitive function assessment system 200 includes: a cognitive function evaluation device 100; a sound pickup device 300 that detects the voice of the person U to be evaluated; and a display device 400 that displays the evaluation result output by the output section 140.

Such a cognitive function assessment system 200 can easily assess the cognitive function of the person to be assessed U by acquiring the voice data. In addition, since 2 feature quantities, i.e., the sounding time and the fundamental frequency, are used, the evaluation accuracy is improved.

In addition, the cognitive function assessment method according to the embodiment is a computer-implemented cognitive function assessment method. The cognitive function assessment method comprises the following steps: an acquisition step of acquiring voice data representing a voice uttered by the user U in response to a question given to the user U; an evaluation step of evaluating the cognitive function of the user U by performing a first evaluation based on a ratio of the time during which the user U utters the voice in the voice data acquired in the acquisition step for a predetermined period and a second evaluation based on the fundamental frequency of the voice data acquired in the acquisition step; and an output step of outputting the evaluation result evaluated in the evaluation step.

Such a cognitive function assessment method can easily assess the cognitive function of the person U to be assessed by acquiring the voice data. In addition, since 2 feature quantities, i.e., the sounding time and the fundamental frequency, are used, the evaluation accuracy is improved.

The present invention can also be realized as a program for causing a computer to execute the cognitive function assessment method described above.

Such a program enables easy assessment of the cognitive function of the person U to be evaluated. In addition, since 2 feature quantities, i.e., the sounding time and the fundamental frequency, are used, the evaluation accuracy is improved.

(modification example)

Next, the cognitive function assessment system according to modification 1 and modification 2 of the embodiment will be described. Note that, the same components as those in the embodiments are denoted by the same reference numerals, and redundant description may be omitted or simplified.

Fig. 12 is a diagram showing the configuration of a cognitive function assessment system according to modification 1 of the embodiment.