JP7403129B2 - Eating and swallowing function evaluation method, program, eating and swallowing function evaluation device, and eating and swallowing function evaluation system - Google Patents

Description

The present invention relates to an eating and swallowing function evaluation method, a program, an eating and swallowing function evaluation device, and an eating and swallowing function evaluation system that can evaluate the eating and swallowing function of a person to be evaluated.

Dysphagia has risks such as aspiration, malnutrition, loss of enjoyment of eating, dehydration, decreased physical strength and immunity, oral contamination, and aspiration pneumonia, so it is important to prevent dysphagia. is required. Traditionally, by evaluating the eating and swallowing function, measures have been taken to deal with eating and swallowing disorders, such as consuming meals with appropriate food formats and conducting rehabilitation to restore appropriate function. There are various evaluation methods. For example, a device for evaluating the eating and swallowing function is attached to the neck of the person to be evaluated, and pharyngeal movement features are obtained as the eating and swallowing function evaluation index (marker) to evaluate the eating and swallowing function of the person being evaluated. An evaluation method is disclosed (for example, see Patent Document 1).

JP2017-23676A

However, the method disclosed in Patent Document 1 requires the person to be evaluated to wear an instrument, which may cause discomfort to the person to be evaluated. Eating and swallowing function can also be evaluated by visual examination, interview, or palpation by specialists such as dentists, dental hygienists, speech therapists, or internal medicine physicians. A specialist should diagnose the dysphagia after it becomes severe, such as when paralysis occurs or when dysphagia is caused by surgery on organs related to swallowing (e.g., tongue, soft palate, or pharynx). In many cases, it is. However, even though elderly people are constantly choking and spilling food due to the effects of aging, the decline in eating and swallowing function is sometimes overlooked as a natural symptom of old age. . If a decrease in ingestion and swallowing is overlooked, it can lead to malnutrition due to a decrease in food intake, for example, and malnutrition can lead to a decrease in immunity. In addition, it is easy to aspire, leading to a vicious cycle where aspiration and weakened immune system may eventually lead to aspiration pneumonia.

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to provide an eating/swallowing function evaluation method that can easily evaluate the eating/swallowing function of a person to be evaluated.

The eating and swallowing function evaluation method according to one aspect of the present invention includes an acquisition step of acquiring audio data obtained by non-contact collecting the sound of a predetermined syllable or a predetermined sentence uttered by the person to be evaluated; The method includes a calculation step of calculating a feature amount from the acquired voice data, and an evaluation step of evaluating the eating and swallowing function of the person to be evaluated from the calculated feature amount.

Further, a program according to one aspect of the present invention is a program for causing a computer to execute the above-described eating and swallowing function evaluation method.

The eating and swallowing function evaluation device according to one aspect of the present invention also includes an acquisition unit that acquires audio data obtained by non-contact collecting the voice of a person being evaluated who utters a predetermined syllable or a predetermined sentence. a calculation unit that calculates a feature amount from the audio data acquired by the acquisition unit; an evaluation unit that evaluates the eating and swallowing function of the person to be evaluated from the feature amount calculated by the calculation unit; and an output section that outputs the evaluation results evaluated by the section.

Furthermore, an eating and swallowing function evaluation system according to one aspect of the present invention includes the above-mentioned eating and swallowing function evaluation device, and a voice in which the person to be evaluated utters the predetermined syllable or the predetermined sentence is collected in a non-contact manner. a sound collection device that makes a sound, and the acquisition unit of the eating and swallowing function evaluation device is configured such that the sound collection device collects the sound of the evaluated person uttering a predetermined syllable or a predetermined sentence in a non-contact manner. Obtain the audio data obtained by

According to the eating and swallowing function evaluation method of the present invention, it is possible to easily evaluate the eating and swallowing function of the person to be evaluated.

FIG. 1 is a diagram showing the configuration of an eating and swallowing function evaluation system according to an embodiment. FIG. 2 is a block diagram showing a characteristic functional configuration of the eating and swallowing function evaluation system according to the embodiment. FIG. 3 is a flowchart showing a processing procedure for evaluating the eating and swallowing function of the person to be evaluated using the eating and swallowing function evaluation method according to the embodiment. FIG. 4 is a diagram illustrating an overview of a method for acquiring the voice of the person to be evaluated using the eating and swallowing function evaluation method according to the embodiment. FIG. 5 is a diagram illustrating an example of audio data representing audio uttered by the person being evaluated. FIG. 6 is a frequency spectrum diagram for explaining formant frequencies. FIG. 7 is a diagram showing an example of a time change in formant frequency. FIG. 8 is a diagram showing specific examples of eating and swallowing functions in the preparatory period, oral cavity period, and pharyngeal period, and symptoms when each function deteriorates. FIG. 9 is a diagram showing an example of the evaluation results. FIG. 10 is a diagram showing an example of the evaluation results. FIG. 11 is a diagram showing an example of the evaluation results. FIG. 12 is a diagram showing an example of the evaluation results. FIG. 13 is a diagram illustrating an outline of a method for acquiring the voice of the person to be evaluated using the eating and swallowing function evaluation method according to Modification 1. FIG. 14 is a diagram illustrating an example of audio data representing the voice uttered by the person to be evaluated in Modification 1. FIG. 15 is a flowchart showing the processing procedure of the eating and swallowing function evaluation method according to the second modification. FIG. 16 is a diagram showing an example of audio data of the evaluator's vocal practice. FIG. 17 is a diagram illustrating an example of voice data to be evaluated by the evaluator. FIG. 18 is a diagram showing an example of an image for presenting evaluation results. FIG. 19 is a diagram illustrating an example of an image for presenting dietary advice. FIG. 20 is a diagram showing a first example of an image for presenting advice regarding exercise. FIG. 21 is a diagram showing a second example of an image for presenting advice regarding exercise. FIG. 22 is a diagram showing a third example of an image for presenting advice regarding exercise.

Embodiments will be described below with reference to the drawings. Note that the embodiments described below are all inclusive or specific examples. The numerical values, shapes, materials, components, arrangement positions and connection forms of the components, steps, order of steps, etc. shown in the following embodiments are merely examples, and do not limit the present invention. Further, among the constituent elements in the following embodiments, constituent elements that are not described in the independent claims indicating the most significant concept will be described as arbitrary constituent elements.

Note that each figure is a schematic diagram and is not necessarily strictly illustrated. Furthermore, in each figure, substantially the same configurations are denoted by the same reference numerals, and overlapping explanations may be omitted or simplified.

(Embodiment)
[Eating and swallowing function]
The present invention relates to a method for evaluating eating and swallowing functions, and the eating and swallowing functions will first be explained.

The swallowing function is a function of the human body necessary to recognize food, take it into the mouth, and complete the series of processes leading to the stomach. The feeding and swallowing function consists of five stages: a preliminary stage, a preparatory stage, an oral cavity stage, a pharyngeal stage, and an esophageal stage.

In the preliminary phase (also called the cognitive phase) of swallowing, the shape, hardness, temperature, etc. of the food are judged. The eating and swallowing function in the preceding stage is, for example, the visual recognition function of the eyes. During the preliminary phase, the nature and condition of the food are recognized and the necessary preparations for feeding, such as eating style, salivation, and posture, are made.

During the preparatory stage (also called mastication stage) of swallowing, the food taken into the mouth is chewed and ground (that is, masticated) by the teeth, and the masticated food is mixed with saliva by the tongue. The food is then collected into a bolus. Eating and swallowing functions during the preparatory stage include, for example, the motor function of facial muscles (lip muscles and cheek muscles) to take food into the oral cavity without spilling it, and the ability to recognize the taste and hardness of food. The recognition function of the tongue to press food against the teeth and the motor function of the tongue to mix small pieces of food with saliva, the occlusal state of the teeth to chew and grind food, The motor function of the cheeks prevents food from getting between the cheeks, the motor function of the masticatory muscles (massete and temporalis muscles, etc.), which is a general term for the muscles used for mastication, and the function of organizing small pieces of food. This includes the saliva secretion function. Masticatory function is influenced by the occlusal state of teeth, the motor function of masticatory muscles, the function of the tongue, etc. These feeding and swallowing functions during the preparatory period give the bolus physical properties (size, mass, viscosity) that make it easy to swallow, making it easier for the bolus to move smoothly from the oral cavity through the pharynx to the stomach.

During the oral phase of swallowing, the tongue (tip of the tongue) is lifted and the bolus is moved from the oral cavity to the pharynx. Eating and swallowing functions during the oral stage include, for example, the motor function of the tongue to move the food bolus to the pharynx, the lifting function of the soft palate to close the gap between the pharynx and the nasal cavity, and the like.

During the pharyngeal phase of swallowing, when the bolus reaches the pharynx, a swallowing reflex occurs and the bolus is sent to the esophagus within a short period of time (approximately 1 second). Specifically, the soft palate rises, closing the space between the nasal cavity and the pharynx, and the base of the tongue (specifically, the hyoid bone that supports the base of the tongue) and larynx rise, allowing the bolus to pass into the pharynx. During this process, the epiglottis inverts downward, blocking the entrance to the trachea and sending the bolus to the esophagus to prevent aspiration. Eating and swallowing functions during the pharyngeal stage include, for example, the motor function of the pharynx to close the space between the nasal cavity and the pharynx (specifically, the motor function of elevating the soft palate), and the function of the tongue (to transport the bolus to the pharynx). Specifically, the motor function of the tongue (at the base of the tongue) transports the bolus from the pharynx to the esophagus, and when the bolus flows into the pharynx, the glottis closes and blocks the trachea, and from above the epiglottis enters the entrance to the trachea. This includes the motor function of the larynx, which acts as a lid by hanging down.

During the esophageal phase of swallowing, peristalsis of the esophageal wall is induced, and the bolus is passed from the esophagus to the stomach. The feeding and swallowing function during the esophageal stage includes, for example, the peristaltic function of the esophagus to move the bolus to the stomach.

For example, as people age, they go from a healthy state to a state requiring care through a pre-frailty stage and a frailty stage. Decreased eating and swallowing function (also called oral frailty) is said to begin to appear during the pre-frailty stage. Decreased eating and swallowing function can be a factor that accelerates the progression from the frailty stage to a state that requires long-term care. Therefore, by noticing how eating and swallowing function declines during the pre-frailty stage and taking preventive measures in advance, it is possible to avoid falling into a state of need for care that continues from the frailty stage and to live a healthy and independent life. You will be able to keep it for a long time.

According to the present invention, it is possible to evaluate the eating and swallowing function of the person to be evaluated from the voice uttered by the person to be evaluated. Specific features are found in the sounds uttered by people with impaired eating and swallowing function, and by calculating these as feature quantities, it is possible to evaluate the person's eating and swallowing function. It is. In the following, evaluation of swallowing function during the preparatory period, oral cavity period, and pharyngeal period will be explained. The present invention provides an eating and swallowing function evaluation method, a program for causing a computer to execute the method, an eating and swallowing function evaluation device which is an example of the computer, and an eating and swallowing function evaluation system including the eating and swallowing function evaluation device. Realized. Below, the eating and swallowing function evaluation method and the like will be explained while showing the eating and swallowing function evaluation system.

[Configuration of eating and swallowing function evaluation system]
The configuration of the eating and swallowing function evaluation system according to the embodiment will be explained.

FIG. 1 is a diagram showing the configuration of an eating and swallowing function evaluation system 200 according to an embodiment.

The eating and swallowing function evaluation system 200 is a system for evaluating the eating and swallowing function of the person U to be evaluated by analyzing the voice of the person U, and as shown in FIG. It includes an evaluation device 100 and a mobile terminal 300.

The eating and swallowing function evaluation device 100 is a device that uses a mobile terminal 300 to acquire audio data indicating the voice uttered by the person to be evaluated U, and evaluates the eating and swallowing function of the person to be evaluated U from the acquired voice data. .

The mobile terminal 300 is a sound collecting device that non-contact collects the voice of the person being evaluated U uttering a predetermined syllable or a predetermined sentence, and the feeding and swallowing function evaluation device 100 receives audio data representing the collected voice. Output to. For example, the mobile terminal 300 is a smartphone, a tablet, or the like that has a microphone. Note that the mobile terminal 300 is not limited to a smartphone or a tablet, but may be a notebook PC, etc., as long as it has a sound collection function. Furthermore, the eating and swallowing function evaluation system 200 may include a sound collection device (microphone) instead of the mobile terminal 300. Furthermore, the eating and swallowing function evaluation system 200 may include an input interface for acquiring personal information of the person U to be evaluated, as will be described later. The input interface is not particularly limited as long as it has an input function, such as a keyboard or a touch panel.

Further, the mobile terminal 300 may be a display device that has a display and displays images based on image data output from the eating and swallowing function evaluation device 100. Note that the display device does not need to be the mobile terminal 300, and may be a monitor device configured with a liquid crystal panel, an organic EL panel, or the like. That is, in this embodiment, the mobile terminal 300 is both a sound collection device and a display device, but the sound collection device (microphone), input interface, and display device may be provided separately.

The eating and swallowing function evaluation device 100 and the mobile terminal 300 only need to be capable of transmitting and receiving audio data or image data for displaying images showing the evaluation results described later, and may be connected by wire. It may also be connected wirelessly.

The eating and swallowing function evaluation device 100 analyzes the voice of the person U to be evaluated based on the voice data collected by the mobile terminal 300, evaluates the eating and swallowing function of the person U from the analysis results, and performs the evaluation. Output the results. For example, the eating and swallowing function evaluation device 100 displays image data for displaying an image showing the evaluation result, or data for making a proposal regarding eating and swallowing to the person being evaluated based on the evaluation result. Output to the mobile terminal 300. In this way, the eating and swallowing function evaluation device 100 can notify the evaluated person U of the level of the eating and swallowing function and a proposal for preventing a decline in the eating and swallowing function. can prevent or improve the decline in eating and swallowing function.

Note that the eating and swallowing function evaluation device 100 is, for example, a personal computer, but may also be a server device. Further, the eating and swallowing function evaluation device 100 may be a mobile terminal 300. That is, the mobile terminal 300 may have the functions that the eating and swallowing function evaluation device 100 described below has.

FIG. 2 is a block diagram showing a characteristic functional configuration of the eating and swallowing function evaluation system 200 according to the embodiment. The eating and swallowing function evaluation device 100 includes an acquisition section 110, a calculation section 120, an evaluation section 130, an output section 140, a suggestion section 150, and a storage section 160.

The acquisition unit 110 acquires audio data obtained by non-contact collection of the voice uttered by the person U being evaluated by the mobile terminal 300 . The voice is a voice in which the person being evaluated U utters a predetermined syllable or a predetermined sentence. Further, the acquisition unit 110 may further acquire the personal information of the person U to be evaluated. For example, personal information is information input into the mobile terminal 300, and includes age, weight, height, gender, BMI (Body Mass Index), dental information (for example, number of teeth, presence or absence of dentures, location of occlusal support, etc.) , serum albumin level or eating rate. Note that the personal information may be obtained by a swallowing screening tool called EAT-10, a Seireishiki swallowing questionnaire, an interview, or the like. The acquisition unit 110 is, for example, a communication interface that performs wired or wireless communication.

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

The calculation unit 120 calculates feature amounts from the audio data acquired by the acquisition unit 110. The feature amount is a numerical value indicating the feature of the voice of the person to be evaluated U calculated from the voice data used by the evaluation unit 130 to evaluate the eating and swallowing function of the person to be evaluated U. Details of the calculation unit 120 will be described later.

The evaluation unit 130 compares the feature amount calculated by the calculation unit 120 with the reference data 161 stored in the storage unit 160, and evaluates the eating and swallowing function of the person U to be evaluated. For example, the evaluation unit 130 may evaluate the eating and swallowing function of the person U to be evaluated after distinguishing between the preparatory stage, the oral cavity stage, and the pharyngeal stage. Specifically, the evaluation unit 130 is realized by a processor, a microcomputer, or a dedicated circuit. Details of the evaluation unit 130 will be described later.

The output unit 140 outputs the evaluation result of the eating and swallowing function of the person U evaluated by the evaluation unit 130 to the proposal unit 150. Further, the output unit 140 outputs the evaluation result to the storage unit 160, and the evaluation result is stored in the storage unit 160. Specifically, the output unit 140 is realized by a processor, a microcomputer, or a dedicated circuit.

The proposal unit 150 makes a proposal regarding eating and swallowing to the person to be evaluated U by comparing the evaluation result output by the output unit 140 with predetermined proposal data 162. Further, the proposal unit 150 may also compare the personal information acquired by the acquisition unit 110 with the proposal data 162 and make a proposal regarding eating and swallowing to the person U to be evaluated. The proposal unit 150 outputs the proposal to the mobile terminal 300. The proposal unit 150 is realized by, for example, a processor, a microcomputer, a dedicated circuit, and a communication interface that performs wired or wireless communication. Details of the proposal unit 150 will be described later.

The storage unit 160 stores reference data 161 indicating the relationship between the feature amount and the person's eating and swallowing function, proposal data 162 indicating the relationship between the evaluation result of the eating and swallowing function and the proposal content, and the above-mentioned information of the person U to be evaluated. This is a storage device that stores personal information data 163 indicating personal information. The reference data 161 is referred to by the evaluation unit 130 when evaluating the degree of the eating and swallowing function of the person U to be evaluated. The proposal data 162 is referred to by the proposal unit 150 when a proposal regarding eating and swallowing is made to the person U to be evaluated. The personal information data 163 is, for example, data acquired via the acquisition unit 110. Note that the personal information data 163 may be stored in the storage unit 160 in advance. The storage unit 160 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 160 also includes programs executed by the calculation unit 120, the evaluation unit 130, the output unit 140, and the proposal unit 150, and the evaluation results used when outputting the evaluation results of the eating and swallowing function of the person U. Also stored are image data showing the content of the proposal, and data such as images, videos, audio, or text showing the content of the proposal. Further, the storage unit 160 may also store an instruction image to be described later.

Although not shown, the eating and swallowing function evaluation device 100 may include an instruction section for instructing the person to be evaluated U to pronounce a predetermined syllable or a predetermined sentence. Specifically, the instruction unit acquires image data and audio data of an instruction image stored in the storage unit 160 for instructing to pronounce a predetermined syllable or a predetermined sentence, and The image data and the audio data are output to the mobile terminal 300.

[Processing procedure of eating and swallowing function evaluation method]
Next, specific processing steps in the eating and swallowing function evaluation method executed by the eating and swallowing function evaluation device 100 will be described.

FIG. 3 is a flowchart showing a processing procedure for evaluating the eating and swallowing function of the person U to be evaluated using the eating and swallowing function evaluation method according to the embodiment. FIG. 4 is a diagram showing an outline of a method for acquiring the voice of the person U to be evaluated using the eating and swallowing function evaluation method.

First, the instruction unit instructs to pronounce a predetermined syllable or a predetermined sentence (a sentence including a specific sound) (step S100). For example, in step S<b>100 , the instruction unit acquires image data of an image for instructions to the person to be evaluated U stored in the storage unit 160 , and outputs the image data to the mobile terminal 300 . Then, as shown in FIG. 4(a), an image for instructions to the person being evaluated U is displayed on the mobile terminal 300. In FIG. 4(a), the prescribed sentence to be instructed is "Kita kara kita kata tatakiki", but "Kitakaze to taiyou", "Aiueo", "Papapapapa...", It may be "tata tata...", "kaka kaka kaka...", "lalalalala...", "panda katataki", etc. In addition, pronunciation instructions do not have to be given in a predetermined sentence, but are given in a predetermined syllable of a single character such as "ki", "ta", "ka", "ra", "ze" or "pa". It's okay to be hurt. Further, the pronunciation instruction may be an instruction to utter a meaningless phrase consisting only of vowels of two or more syllables, such as "eo" and "eea". The pronunciation instruction may be an instruction to repeatedly utter such a meaningless phrase.

The instruction unit also acquires audio data of the voice for instructions to the person being evaluated U stored in the storage unit 160, and outputs the audio data to the mobile terminal 300 to instruct the user to pronounce the sound. The above-mentioned instruction may be given using an instruction sound that instructs to pronounce the pronunciation without using an instruction image. Furthermore, an evaluator (family member, doctor, etc.) who wants to evaluate the eating and swallowing function of the person U, without using images and sounds to instruct the person to pronounce the words, can use his or her own voice to tell the person U the above. You may give instructions.

For example, a predetermined syllable may be composed of a consonant and a vowel following the consonant. For example, in Japanese, such predetermined syllables are "ki", "ta", "ka", "ze", etc. "Ki" is composed of a consonant "k" and a vowel "i" following the consonant. "Ta" is composed of the consonant "t" and the vowel "a" following the consonant. "Ka" is composed of a consonant "k" and a vowel "a" following the consonant. "Ze" is composed of a consonant "z" and a vowel "e" following the consonant.

Further, for example, a predetermined sentence may include a syllable portion consisting of a consonant, a vowel following the consonant, and a consonant following the vowel. For example, in Japanese, such a syllable part is the "kaz" part in "kaze". Specifically, the syllable portion consists of a consonant "k", a vowel "a" following the consonant, and a consonant "z" following the vowel.

Further, for example, the predetermined sentence may include a string of consecutive syllables including vowels. For example, in Japanese, such a character string is "aiueo" or the like.

Further, for example, the predetermined sentence may include a predetermined word. For example, in Japanese, such words are "taiyo: sun", "kitakaze: north wind", etc.

Further, for example, the predetermined sentence may include a phrase in which syllables made up of a consonant and a vowel following the consonant are repeated. For example, in Japanese, such phrases are "papapapapa...", "tatatatata...", "kakakakakaka...", or "raralarara...". "Pa" is composed of a consonant "p" and a vowel "a" following the consonant. "Ta" is composed of the consonant "t" and the vowel "a" following the consonant. "Ka" is composed of a consonant "k" and a vowel "a" following the consonant. "Ra" is composed of the consonant "r" and the vowel "a" following the consonant.

Next, as shown in FIG. 3, the acquisition unit 110 acquires the voice data of the person to be evaluated U who received the instruction in step S100 via the mobile terminal 300 (step S101). As shown in FIG. 4B, in step S101, for example, the person to be evaluated U utters a predetermined sentence such as "Kita kara kata tatakiki" toward the mobile terminal 300. The acquisition unit 110 acquires a predetermined sentence or a predetermined syllable uttered by the person to be evaluated U as audio data.

Next, the calculation unit 120 calculates the feature amount from the audio data acquired by the acquisition unit 110 (step S102), and the evaluation unit 130 calculates the eating and swallowing behavior of the person U to be evaluated based on the feature amount calculated by the calculation unit 120. The function is evaluated (step S103).

For example, if the audio data acquired by the acquisition unit 110 is voice data obtained from the utterance of a predetermined syllable consisting of a consonant and a vowel following the consonant, the calculation unit 120 The sound pressure difference between is calculated as a feature quantity. This will be explained using FIG. 5.

FIG. 5 is a diagram illustrating an example of audio data representing the voice uttered by the person being evaluated. Specifically, FIG. 5 is a graph showing voice data when the person to be evaluated U utters "I came because I came here." The horizontal axis of the graph shown in FIG. 5 is time, and the vertical axis is power (sound pressure). Note that the unit of power shown on the vertical axis of the graph in FIG. 5 is decibel (dB).

The graph shown in Figure 5 includes ``ki'', ``ta'', ``ka'', ``ra'', ``ki'', ``ta'', ``ka'', ``ta'', ``ta'', ``ta'', and ``ki''. ”, changes in sound pressure corresponding to “ki” are confirmed. In step S101 shown in FIG. 3, the acquisition unit 110 acquires the data shown in FIG. 5 as voice data from the person being evaluated U. For example, in step S102 shown in FIG. 3, the calculation unit 120 calculates each sound pressure of "k" and "i" in "ki (ki)" included in the audio data shown in FIG. The sound pressures of "t" and "a" in "(ta)" are calculated. Further, when the person U to be evaluated utters "Kitakaze to Taiyou", the calculation unit 120 calculates the sound pressure of each of "z" and "e" in "ze". The calculation unit 120 calculates the sound pressure difference ΔP1 between “t” and “a” as a feature quantity from the calculated sound pressures of “t” and “a”. Similarly, the calculation unit 120 calculates the sound pressure difference ΔP3 between "k" and "i" and the sound pressure difference (not shown) between "z" and "e" as feature quantities.

The reference data 161 includes a threshold corresponding to each sound pressure difference, and the evaluation unit 130 evaluates the eating and swallowing function, for example, depending on whether each sound pressure difference is greater than or equal to the threshold.

For example, in order to say "ki", the base of the tongue needs to touch the soft palate. By evaluating the function of bringing the base of the tongue into contact with the soft palate (sound pressure difference between "k" and "i"), the motor function of the tongue (including tongue pressure, etc.) during the pharyngeal stage can be evaluated.

For example, in order to say "ta", the tip of the tongue needs to touch the upper jaw behind the front teeth. By evaluating the function of bringing the tip of the tongue into contact with the upper jaw behind the front teeth (sound pressure difference between "t" and "a"), the motor function of the tongue during the preparatory period can be evaluated.

For example, in order to say "ze", the tip of the tongue needs to touch or approach the upper front teeth. The presence of teeth is important for the sides of the tongue, as they are supported by rows of teeth. By evaluating the presence of the dentition including the upper front teeth (sound pressure difference between "z" and "e"), it is possible to estimate whether there are many or few remaining teeth, and if there are few remaining teeth, it can affect masticatory ability, etc. The occlusal condition of teeth can be evaluated.

Further, for example, when the audio data acquired by the acquisition unit 110 is voice data obtained from the utterance of a predetermined sentence including a consonant, a vowel following the consonant, and a syllable portion consisting of the consonant following the vowel, The calculation unit 120 calculates the time required to utter the syllable portion as a feature amount.

For example, when evaluator U utters a predetermined sentence that includes "kaze", the predetermined sentence includes the consonant "k", the vowel "a" following the consonant, and the consonant "z" following the vowel. Contains a syllable part consisting of. The calculation unit 120 calculates the time required to utter such a syllable portion consisting of "kaz" as a feature quantity.

The reference data 161 includes a threshold value corresponding to the time required to utter the syllable part, and the evaluation unit 130 determines, for example, whether the time required to utter the syllable part is equal to or greater than the threshold value. Eating and swallowing function will be evaluated depending on whether the patient is present or not.

For example, the time required to utter a syllable consisting of "consonant-vowel-consonant" varies depending on the motor function of the tongue (tongue dexterity, tongue pressure, etc.). By evaluating the time required to utter the syllable, it is possible to evaluate the motor function of the tongue in the preparatory stage, the motor function of the tongue in the oral stage, and the motor function of the tongue in the pharyngeal stage.

Further, for example, if the audio data acquired by the acquisition unit 110 is voice data obtained from the utterance of a predetermined sentence including a string of consecutive syllables including vowels, the calculation unit 120 calculates the The amount of change in the obtained first formant frequency, second formant frequency, etc. is calculated as a feature amount, and the variation in the first formant frequency, second formant frequency, etc. obtained from the spectrum of the vowel part is calculated as a feature amount.

The first formant frequency is the first amplitude peak frequency seen from the low-frequency side of human speech, and is known to easily reflect characteristics related to tongue movements (especially up-and-down movements). In addition, it is also known that characteristics related to jaw opening are likely to be reflected.

The second formant frequency is the second amplitude peak frequency seen from the low frequency side of human speech, and it is the second formant frequency that occurs when the vocal cord sound source is the vocal tract, the oral cavity such as the lips and tongue, and the nasal cavity. It is known that the influence of the position (especially the front and rear positions) is likely to be reflected. Furthermore, for example, since it is not possible to speak correctly when teeth are not present, it is thought that the occlusal state (number of teeth) of the teeth during the preparation period has an effect on the second formant frequency. Furthermore, for example, since it is difficult to speak correctly when there is little saliva, it is thought that the salivary secretion function during the preparatory period has an effect on the second formant frequency. In addition, the motor function of the tongue, the secretion function of saliva, or the occlusal state of the teeth (the number of teeth) can be determined from either the feature value obtained from the first formant frequency or the feature value obtained from the second formant frequency. It may be calculated.

FIG. 6 is a frequency spectrum diagram for explaining formant frequencies. Note that the horizontal axis of the graph shown in FIG. 6 is frequency [Hz], and the vertical axis is amplitude.

As shown by broken lines in FIG. 6, a plurality of peaks are confirmed in the data obtained by converting the horizontal axis of audio data into frequency. Among the plurality of peaks, the frequency of the lowest peak is the first formant frequency F1. Further, the next lowest frequency peak frequency after the first formant frequency F1 is the second formant frequency F2. Further, the next lowest frequency peak frequency after the second formant frequency F2 is the third formant frequency F3. In this way, the calculation unit 120 extracts the vowel part from the audio data acquired by the acquisition unit 110 using a known method, and converts the audio data of the extracted vowel part into amplitude with respect to frequency. The formant frequency obtained from the spectrum of the vowel part is calculated.

The graph shown in FIG. 6 is calculated by converting the audio data obtained from the person U to be evaluated into data of amplitude with respect to frequency, and determining the envelope thereof. For example, cepstral analysis, linear predictive coding (LPC), etc. are used to calculate the envelope.

FIG. 7 is a diagram showing an example of a time change in formant frequency. Specifically, FIG. 7 is a graph for explaining an example of a temporal change in frequency of the first formant frequency F1, the second formant frequency F2, and the third formant frequency F3.

For example, the person being evaluated U is made to utter a syllable including a plurality of consecutive vowels, such as "aiueo". The calculation unit 120 calculates the first formant frequency F1 and the second formant frequency F2 of each of a plurality of vowels from the audio data representing the voice uttered by the person U to be evaluated. Furthermore, the calculation unit 120 calculates the amount of change (amount of time change) in the first formant frequency F1 and the amount of change (amount of time change) in the second formant frequency F2 of the character string with consecutive vowels as feature amounts.

The reference data 161 includes a threshold corresponding to the amount of change, and the evaluation unit 130 evaluates the eating and swallowing function, for example, depending on whether the amount of change is greater than or equal to the threshold.

Looking at the first formant frequency F1, it shows, for example, the opening of the jaw and the vertical movement of the tongue, and the amount of change indicates the movement of the jaw and the vertical movement of the tongue in the preparatory, oral, and pharyngeal periods, which are affected by this movement. This indicates that the movement of Looking at the second formant frequency F2, it shows that there is an influence on the front and rear positions of the tongue, and that the movement of the tongue in the preparatory period, oral cavity period, and pharyngeal period, which is affected by this movement, is reduced. Looking at the second formant frequency F2, for example, it shows that the person has no teeth and cannot speak correctly, which means that the occlusal state of the teeth in the preparatory period has deteriorated. Further, looking at the second formant frequency F2, for example, it shows that the amount of saliva is low and it is not possible to speak correctly, which means that the salivary secretion function in the preparatory period is reduced. That is, by evaluating the amount of change in the second formant frequency F2, the salivary secretion function during the preparatory period can be evaluated.

Further, the calculation unit 120 calculates the variation in the first formant frequency F1 of a character string with consecutive vowels as a feature quantity. For example, if the audio data contains n vowels (n is a natural number), n first formant frequencies F1 are obtained, and the dispersion of the first formant frequency F1 is calculated using all or part of these. be done. The degree of variation calculated as a feature amount is, for example, a standard deviation.

The reference data 161 includes a threshold corresponding to the variation, and the evaluation unit 130 evaluates the eating and swallowing function, for example, depending on whether the variation is greater than or equal to the threshold.

A large variation in the first formant frequency F1 (above the threshold value) indicates, for example, that the vertical movement of the tongue is slow. This indicates a decline in the motor function of the tongue, which moves the mass into the pharynx. That is, by evaluating the variation in the first formant frequency F1, the motor function of the tongue during the oral period can be evaluated.

Further, for example, the calculation unit 120 calculates the pitch (height) of the voice of the person U who is being evaluated uttering a predetermined syllable or a predetermined sentence as a feature quantity.

The reference data 161 includes a threshold corresponding to the pitch, and the evaluation unit 130 evaluates the eating and swallowing function, for example, depending on whether the pitch is equal to or greater than the threshold.

For example, if the audio data acquired by the acquisition unit 110 is voice data obtained from the voice of a predetermined sentence containing a predetermined word, the calculation unit 120 calculates the time required to utter the predetermined word. Calculate as a feature quantity.

For example, when evaluator U utters a predetermined sentence that includes ``taiyo'', evaluator U recognizes the character string ``taiyo'' as the word ``sun'' and then utters ``taiyo''. Speak a string. If it takes time to utter a predetermined word, there is a possibility that the person being evaluated U has dementia. It is said that the number of teeth has an influence on dementia. This is because the number of teeth affects brain activity, and as the number of teeth decreases, stimulation to the brain decreases, increasing the risk of developing dementia. In other words, the fact that the person U to be evaluated is at risk of dementia corresponds to the number of teeth, and furthermore, to the occlusal state of the teeth for chewing and grinding food during the preparation period. Therefore, if the time required to utter a given word is long (greater than the threshold), it means that the person being evaluated is at risk of dementia.In other words, the occlusal state of the teeth during the preparation period has deteriorated. Indicates that That is, by evaluating the time required for the person U to be evaluated to utter a predetermined word, it is possible to evaluate the occlusal state of the teeth during the preparation period.

Note that the calculation unit 120 may calculate the time required to utter the entire predetermined sentence as the feature amount. Even in this case, the occlusal state of the teeth during the preparation period can be evaluated in the same way by evaluating the time required for the person U to utter the entire predetermined sentence.

Further, for example, if the audio data acquired by the acquisition unit 110 is voice data obtained from a predetermined sentence uttered that includes a phrase in which a syllable consisting of a stop consonant and a vowel following the stop consonant is repeated. , the calculation unit 120 calculates the number of times a repeated syllable is uttered within a predetermined period of time (for example, 5 seconds, etc.) as a feature quantity.

The reference data 161 includes a threshold corresponding to the number of times, and the evaluation unit 130 evaluates the eating and swallowing function, for example, depending on whether the number of times is equal to or greater than the threshold.

For example, evaluator U uses consonants such as "papapapapa...", "tatatatata...", "kakakakakaka...", or "ralalalara..." and the consonants that follow the consonant. Speak a predetermined sentence containing a phrase in which syllables made up of vowels are repeated.

For example, in order to say "pa", it is necessary to open and close the mouth (lips) up and down. If the ability to open and close the lips up and down is impaired, it becomes impossible to utter "pa" more than a predetermined number of times (threshold value) within a predetermined time. The action of opening and closing the lips up and down is similar to the action of taking food into the mouth without spilling it during the preparation period. Therefore, the ability to quickly utter "pa", that is, the ability to open and close the lips up and down quickly and repeatedly, corresponds to the motor function of facial muscles during the preparatory period to take food into the oral cavity without spilling it. There is. That is, by evaluating the number of times "pa" is uttered within a predetermined period of time, the motor function of the facial muscles during the preparation period can be evaluated.

For example, in order to say "ta", the tip of the tongue needs to touch the upper jaw behind the front teeth, as described above. The action of bringing the tip of the tongue into contact with the upper jaw behind the front teeth is the action performed during the preparatory stage when pressing food against the teeth or when mixing finely chopped food with saliva and organizing it, and the action during the oral stage when the tongue ( This is similar to the action performed when lifting the tip of the tongue to move the bolus from the oral cavity to the pharynx. For this reason, the ability to quickly utter "ta" (ta), that is, to repeatedly contact the tip of the tongue with the upper jaw behind the front teeth, is achieved by pressing food against the teeth during the preparatory period and mixing finely chopped food with saliva. This corresponds to the motor function of the tongue to collect the food and to move the bolus to the pharynx during the oral period. That is, by evaluating the number of times "ta" is uttered within a predetermined period of time, the motor function of the tongue in the preparatory period and the motor function of the tongue in the oral period can be evaluated.

For example, in order to utter "ka", the base of the tongue needs to come into contact with the soft palate, similar to the above-mentioned "ki". The action of bringing the base of the tongue into contact with the soft palate is similar to the action performed when a bolus passes through the pharynx (swallowing) during the pharyngeal stage. Furthermore, when taking food or drink into the mouth (preparation stage), and when chewing food in the mouth to reform the diet (oral stage), the base of the tongue comes into contact with the soft palate and the pharynx. The tongue performs actions to prevent inflow and choking, similar to the actions of the tongue when pronouncing "k". Therefore, the ability to quickly utter "ka", that is, to quickly and repeatedly contact the base of the tongue with the soft palate, is due to the function of the tongue (specifically, the base of the tongue) to allow the bolus to pass through the pharynx during the pharyngeal stage. This corresponds to the motor function of That is, by evaluating the number of times "ka" is uttered within a predetermined period of time, the motor function of the tongue in the preparatory period, oral cavity period, and pharyngeal period can be evaluated. The motor function of the tongue also corresponds to the function of preventing food from flowing into the pharynx and preventing choking.

For example, to say "ra" you need to arch your tongue. The action of arching the tongue is similar to the action of mixing food with saliva to form a bolus during the preparatory stage. Therefore, the ability to quickly utter the "ra" sound, that is, to quickly and repeatedly arch the tongue, corresponds to the motor function of the tongue to mix food with saliva and form a bolus during the preparatory period. That is, by evaluating the number of times "ra" is uttered within a predetermined period of time, the motor function of the tongue during the preparatory period can be evaluated.

In this way, the evaluation unit 130 evaluates the eating and swallowing function of the person U to be evaluated in the preparatory period, for example, the tongue motor function “in the preparatory period” or the tongue motor function “in the oral period”. Evaluation is made by distinguishing between the oral and pharyngeal stages of feeding and swallowing function. For example, the reference data 161 includes a correspondence relationship between types of feature amounts and eating and swallowing functions in at least one of the preparatory stage, the oral cavity stage, and the pharyngeal stage. For example, focusing on the sound pressure difference between "k" and "i" as a feature quantity, the sound pressure difference between "k" and "i" is associated with the motor function of the tongue in the pharyngeal stage. Therefore, the evaluation unit 130 can evaluate the eating and swallowing function of the person U after distinguishing which stage of the eating and swallowing function is the preparatory stage, the oral cavity stage, and the pharyngeal stage. By evaluating the eating and swallowing function of person U by distinguishing whether the eating and swallowing function is in the preparatory stage, the oral cavity stage, or the pharyngeal stage, it is possible to determine what kind of symptoms the person U is experiencing. You can see if there is a risk of this occurring. This will be explained using FIG. 8.

FIG. 8 is a diagram showing specific examples of eating and swallowing functions in the preparatory period, oral cavity period, and pharyngeal period, and symptoms when each function deteriorates.

As the motor function of facial muscles decreases during the preparatory period, symptoms of spilled food appear when swallowing. As the motor function of the tongue and the occlusal state of the teeth deteriorate during the preparatory period, symptoms such as inability to masticate correctly (inability to chew or grind food) occur during swallowing. As the salivary secretion function decreases during the preparatory period, symptoms occur in which food remains in pieces and cannot form a bolus during swallowing. Furthermore, due to a decline in the motor function of the tongue during the oral and pharyngeal stages, the patient is unable to properly swallow the bolus into the pharynx and esophagus during swallowing, resulting in symptoms of choking.

It is known that such symptoms occur when the eating and swallowing function deteriorates at each stage. By distinguishing between eating and swallowing functions and evaluating them, it becomes possible to develop detailed countermeasures for each corresponding symptom. Furthermore, although details will be described later, the proposal unit 150 can propose countermeasures to the person being evaluated U according to the evaluation results.

Next, as shown in FIG. 3, the output unit 140 outputs the evaluation result of the eating and swallowing function of the person to be evaluated U evaluated by the evaluation unit 130 (step S104). The output unit 140 outputs the evaluation result of the eating and swallowing function of the person U evaluated by the evaluation unit 130 to the proposal unit 150. Note that the output unit 140 may output the evaluation result to the mobile terminal 300. In this case, the output unit 140 may include, for example, a communication interface that performs wired or wireless communication. In this case, for example, the output unit 140 acquires image data of an image corresponding to the evaluation result from the storage unit 160 and transmits the acquired image data to the mobile terminal 300. Examples of the image data (evaluation results) are shown in FIGS. 9 to 12.

9 to 12 are diagrams showing examples of evaluation results. For example, the evaluation result is a two-level evaluation result of OK or NG. OK means normal, NG means abnormal. Note that the evaluation result is not limited to a two-level evaluation result, but may be a detailed evaluation result in which the degree of evaluation is divided into three or more levels. That is, the threshold value corresponding to each feature amount included in the reference data 161 stored in the storage unit 160 is not limited to one threshold value, but may be a plurality of threshold values. Specifically, for a certain feature, if it is equal to or greater than the first threshold, the evaluation result will be normal; if it is smaller than the first threshold and greater than the second threshold, the evaluation result will be slightly abnormal, and if it is equal to or less than the second threshold. In this case, the evaluation result may be abnormal. Further, a circle mark or the like may be shown instead of OK (normal), a triangle mark or the like may be shown instead of slightly abnormal, and a cross mark or the like may be shown instead of NG (abnormal). Furthermore, as shown in FIGS. 9 to 12, normal and abnormal states may not be shown for each eating and swallowing function; for example, only items suspected of having a decreased eating and swallowing function may be shown.

The image data of the image corresponding to the evaluation result is, for example, a table as shown in FIGS. 9 to 12. The person U to be evaluated can check such a table showing the evaluation results after distinguishing between the preparatory stage, the oral cavity stage, and the pharyngeal stage of the eating and swallowing function. For example, if the assessee U knows in advance what measures should be taken when the functions of eating and swallowing deteriorate in the preparatory stage, oral cavity stage, and pharyngeal stage, By checking such a table, U will be able to develop detailed countermeasures.

However, the person being evaluated U may not know in advance what kind of eating and swallowing measures should be taken when the eating and swallowing function deteriorates at each stage. Therefore, as shown in FIG. 3, the proposal unit 150 makes a proposal regarding eating and swallowing for the evaluated person U by comparing the evaluation results output by the output unit 140 with predetermined proposal data 162. . (Step S105). For example, the proposal data 162 includes proposal contents regarding eating and swallowing for the evaluated person U, corresponding to each combination of evaluation results for each of the eating and swallowing functions in the preparatory period, the oral cavity period, and the pharyngeal period. Furthermore, the storage unit 160 includes data (for example, images, videos, audio, text, etc.) indicating the content of the proposal. The proposal unit 150 makes a proposal regarding eating and swallowing to the person being evaluated U using such data.

Below, the evaluation results of evaluating person U's eating and swallowing function after distinguishing between the preparatory stage, the oral cavity stage, and the pharyngeal stage are shown in Figures 9 to 12. We will explain the contents of each proposal in the case of the results shown in .

In the evaluation results shown in FIG. 9, the motor function of the tongue in the preparation period and the motor function of the tongue in the oral and pharyngeal periods were NG, and the other eating and swallowing functions were OK. In this case, there may be a problem with masticatory ability due to poor tongue motor function during the preparatory period. This can lead to nutritional imbalances due to avoiding foods that are difficult to eat, or it can take longer to eat. In addition, poor tongue motor function during the oral and pharyngeal stages may cause problems in swallowing the bolus. This can cause you to choke or take a long time to swallow.

On the other hand, the proposal unit 150 makes a proposal corresponding to the combination by comparing the combination of the evaluation results and the proposal data 162. Specifically, the suggestion unit 150 suggests reducing the amount of food that is put into the mouth at one time, such as by making hard foods softer. This is because by reducing the amount of food that you put in your mouth at one time, you will be able to masticate it more easily, and the bolus will be smaller, making it easier to swallow. For example, the suggestion unit 150 may send an image, text, or voice message via the mobile terminal 300 saying, ``Reduce the amount you put in your mouth and eat slowly.If you feel tired, it may be a good idea to take a break and then resume eating.'' Make suggestions such as "I can't do it." The suggestion unit 150 also suggests thickening the liquid contained in the food. This is because by thickening the liquid, it becomes easier to masticate the food, and the flow rate of the liquid in the pharynx becomes slower, thereby suppressing choking. For example, the proposal unit 150 makes a proposal such as "Let's thicken liquids such as soup and soup stock" using images, text, or audio via the mobile terminal 300.

In the evaluation results shown in FIG. 10, the saliva secretion function during the preparatory period was NG, and the other eating and swallowing functions were OK. In this case, there may be a problem of oral dryness due to poor saliva secretion function during the preparatory period. As a result, the food bolus cannot be formed properly, making it difficult to swallow dry food, resulting in unbalanced nutrition due to the avoidance of dry food, and making it take longer to eat.

On the other hand, the proposal unit 150 makes a proposal corresponding to the combination by comparing the combination of the evaluation results and the proposal data 162. Specifically, when eating foods that absorb water in the mouth (bread, cake, grilled fish, rice crackers, etc.), it is suggested that you eat while ingesting water. This is because the water ingested instead of saliva makes it easier to form a food bolus, eliminating difficulty in swallowing. For example, the proposal unit 150 may send messages such as "When eating bread, etc., drink water" or "When eating grilled fish, etc., pour dashi soup over it" through the mobile terminal 300 through images, text, or audio. Let's try it. It might be a good idea to make it with bean paste."

In the evaluation results shown in FIG. 11, the occlusal state of the teeth during the preparation period was NG, and the other eating and swallowing functions were OK. In this case, there may be a problem with masticatory ability and occlusal ability due to the poor occlusal state of the teeth during the preparation period. As a result, avoiding hard foods can lead to imbalanced nutrition and take longer to eat.

On the other hand, the proposal unit 150 makes a proposal corresponding to the combination by comparing the combination of the evaluation results and the proposal data 162. Specifically, when eating hard foods (vegetables, meat, etc.), it is suggested that they be chopped into small pieces or softened before eating. This is because they will be able to eat hard foods even if they have problems with their chewing and occlusal abilities. For example, the proposal unit 150 may send messages such as ``Chop hard and difficult to eat foods into small pieces'' or ``Leafy vegetables are difficult to eat'' through images, text, or audio via the mobile terminal 300. "Rather than avoid eating it, let's actively eat it by softening it, chopping it, etc. so that the nutrition is not biased."

In the evaluation results shown in FIG. 12, the saliva secretion function during the preparatory period was OK, and the other eating and swallowing functions were NG. In this case, there is a possibility that the eating and swallowing functions are decreased in each of the preparatory stage, oral cavity stage, and pharyngeal stage. For example, the muscle strength of the lips weakens due to a decline in the motor function of facial muscles during the preparatory period, the masseter muscle weakens due to the deterioration of the occlusal condition of the teeth during the preparatory period, and the tongue motor function declines during the preparatory, oral, and pharyngeal stages. It is predicted that the muscle strength of the patient is weakened, suggesting the possibility of sarcopenia.

On the other hand, the proposal unit 150 makes a proposal corresponding to the combination by comparing the combination of the evaluation results and the proposal data 162. Specifically, we suggest eating protein and doing rehabilitation. This is because it can eliminate muscle weakness. At this time, the proposal unit 150 may use the personal information (for example, age, weight) of the person to be evaluated U acquired by the acquisition unit 110. For example, the proposal unit 150 sends an image, text, or voice message via the mobile terminal 300 saying, ``Let's eat protein.My current weight is 60 kg, so I eat 20 g to 24 g of protein per meal, total of 3 meals. "Let's eat 60g to 72g of food. When eating, make sure to thicken liquids such as soups and soup stock so that you don't choke." Further, the proposal unit 150 proposes specific training contents regarding rehabilitation. For example, the proposal unit 150 provides whole-body muscle strength training (training that repeats standing and sitting), lip muscle strength recovery training (training that repeats standing and sitting, etc.) according to the age of the person U, using videos and audio via the mobile terminal 300. (training that involves repeating exhalation and inhalation), tongue muscle recovery training (training that involves pushing the tongue in and out, moving it up, down, left and right, etc.). Also, for example, installation of an app for such rehabilitation may be suggested. Furthermore, the details of training actually performed during rehabilitation may be recorded. This allows an expert (such as a doctor, dentist, speech therapist, or nurse) to confirm the recorded content, thereby allowing it to be reflected in rehabilitation by the expert.

Note that the evaluation unit 130 does not need to evaluate the eating and swallowing function of the person U to be evaluated after distinguishing between the preparatory stage, the oral cavity stage, and the pharyngeal stage. That is, the evaluation unit 130 may evaluate which eating and swallowing function of the person U to be evaluated has deteriorated.

In addition, although not shown, the proposal unit 150 may make proposals as described below depending on the combination of evaluation results for each of the eating and swallowing functions.

For example, when proposing the meal content, the proposal unit 150 may present a code indicating the food form, such as a code of "Swallowing Adjustment Food Classification 2013" by the Japanese Society for Eating and Swallowing Rehabilitation. For example, when Evaluate U purchases a product for dysphagia, it is difficult to explain the "food form" in words, but by using the above code, it is possible to have a one-to-one correspondence with the above code. Products in food form can be easily purchased. Further, the suggestion unit 150 may present a site for purchasing such products so that the products can be purchased using the Internet. For example, after the eating and swallowing function is evaluated through the mobile terminal 300, it may be possible to purchase the product using the mobile terminal 300. Furthermore, the suggestion unit 150 may suggest other products to supplement nutrition so that the nutrition of the person U to be evaluated is not biased. At that time, the proposal unit 150 uses the personal information of the person U acquired by the acquisition unit 110 (for example, weight, BMI (Body Mass Index), serum albumin level, or eating rate) to After determining the nutritional status of the person, products that supplement nutrition may be presented.

Further, for example, the suggestion unit 150 may suggest a posture when eating. This is because the ease of swallowing food changes depending on the posture. For example, the proposing unit 150 suggests eating in a stooped position, where the angle from the pharynx to the trachea is unlikely to be a straight line.

Further, for example, the proposal unit 150 may present a menu that takes into account nutritional imbalance due to a decline in the eating and swallowing function (presents a menu site that includes such a menu). A menu site is a site that describes ingredients and cooking procedures necessary to complete a menu. At this time, the proposal unit 150 may present a menu that takes into account nutritional bias while considering the menu that the person U to be evaluated wants to eat that has been input by the person U to be evaluated and acquired by the acquisition unit 110. Furthermore, the suggestion unit 150 may present a nutritionally balanced menu for a specific period, such as one week.

Further, for example, the proposal unit 150 may transmit information indicating the degree to which the food is to be finely chopped or softened to an IoT (Internet of Things) cooking device. This allows you to properly grind and soften food. In addition, it is possible to save the effort of the evaluator U and others to grind or soften the food themselves.

[Modification 1]
In the above-mentioned embodiment, the predetermined sentence instructed to the evaluator U is ``I came here, I came here, smack,'' etc., but the predetermined sentence is ``I decided to draw a picture.'' There may be. FIG. 13 is a diagram showing an outline of a method for acquiring the voice of the person to be evaluated U using the eating and swallowing function evaluation method according to the first modification.

First, in step S100 in FIG. 3, the instruction unit acquires image data of an image for instructing the person to be evaluated U stored in the storage unit 160, and transfers the image data to the mobile terminal 300 (in FIG. In the example, output to a tablet device). Then, as shown in FIG. 13(a), an image for instructions to the person U to be evaluated is displayed on the mobile terminal 300. In FIG. 13(a), the predetermined sentence that is instructed is "I decided to draw a picture."

Next, in step S101 of FIG. 3, the acquisition unit 110 acquires, via the mobile terminal 300, the voice data of the person to be evaluated U who received the instruction in step S100. As shown in FIG. 13(b), in step S101, for example, the person being evaluated U utters "I have decided to draw a picture" toward the mobile terminal 300. The acquisition unit 110 acquires the sentence "I decided to draw" uttered by the person being evaluated U as voice data. FIG. 14 is a diagram illustrating an example of audio data representing the voice uttered by the person being evaluated in Modification 1.

Subsequently, in step S102 of FIG. 3, the calculation unit 120 calculates the feature amount from the voice data acquired by the acquisition unit 110, and the evaluation unit 130 calculates the feature amount of the person U to be evaluated from the feature amount calculated by the calculation unit 120. Eating and swallowing function is evaluated (step S103).

As the feature amount, for example, the sound pressure difference when uttering [ka (ka)], [to (to)], and [ta (ta)] as shown in FIG. 14 is used.

For example, in order to produce the "k" sound, the base of the tongue must firmly attach to the soft palate. Therefore, by evaluating the sound pressure difference between "k" and "a", the motor function of the tongue (including tongue pressure, etc.) in the pharyngeal stage can be evaluated. In addition, as mentioned above, by evaluating the sound pressure difference between "k" and "a", food can be delivered during the preparation stage, oral stage (function to prevent liquids and solids from flowing into the pharynx, function to prevent choking), and pharyngeal stage. Strength (swallowing ability) can be assessed. Furthermore, by evaluating the sound pressure difference between "k" and "a", tongue pressure is also involved, and the ability to crush food during mastication can also be evaluated. Furthermore, although "ka" is illustrated in Figure 14, similar evaluations can be made using "ku", "ko", and "ki" in the example sentences. May be performed.

Furthermore, in order to produce the sound "ta" (ta), the tip of the tongue needs to touch the upper jaw behind the front teeth. The same applies to "to". Therefore, by evaluating the function of bringing the tip of the tongue into contact with the upper jaw behind the front teeth (the sound pressure difference between "t" and "a" or the sound pressure difference between "t" and "o"), it is possible to Motor function can be evaluated.

Further, as the feature quantity, the amount of time required from the start to the end of the utterance "I decided to draw a picture" (that is, the time T in FIG. 14) may be used. Such time T can be used for evaluation as speech speed. For example, by using the number of uttered characters per unit time as a feature quantity, it is possible to evaluate the speed of tongue movement, that is, the state of tongue dexterity. This feature value may be evaluated as speaking speed as it is, or it can be used in conjunction with other feature values to evaluate things other than tongue dexterity. For example, if the speaking speed is slow (the tongue moves slowly) and the vertical movement of the jaw is small (feature value of the amount of change in the first formant), the overall movement including the cheeks is weak and the movement of the tongue and cheeks is weak. Muscle weakness may be suspected.

Furthermore, the amount of formant change when the person U to be evaluated utters "picture" may be used as the feature amount. More specifically, the amount of formant change is the difference between the minimum and maximum values of the first formant frequency while the person U is saying “picture”, or the difference between the minimum value and the maximum value of the first formant frequency while the person being evaluated U is saying “picture”. This is the difference between the minimum and maximum second formant frequencies during the utterance of .

The amount of second formant change when the person being evaluated U utters "picture" indicates the back and forth movement of the tongue. Therefore, by evaluating the amount of second formant change when saying "picture", it is possible to evaluate the ability to send food to the back of the mouth. In this case, the larger the amount of formant change, the higher the ability to transport food to the back of the mouth.

Moreover, the amount of formant change when the person U to be evaluated says "I decided" may be used as the feature amount. More specifically, the formant change amount is the difference between the minimum value and the maximum value of the first formant frequency while the evaluator U utters "I decided", or the difference between the minimum value and the maximum value of the first formant frequency while the evaluator U says "I decided". This is the difference between the minimum and maximum second formant frequencies during the utterance of .

The amount of change in the first formant when the person U to be evaluated utters "I decided" indicates the degree of opening of the jaw and the vertical movement of the tongue. Therefore, by evaluating the amount of change in the first formant when saying "I have decided," it is possible to evaluate the movement of the force that moves the jaw (facial muscles). The larger the amount of change in the first formant, the better, but the amount of change in the first formant will also be large when the facial muscles are weak and unable to support the jaw, so the ability to masticate food in combination with other feature values is You can evaluate whether it is high or not.

Note that the ``ta'' in ``I decided to draw a picture'' may not be uttered with sufficient sound pressure depending on the person being evaluated. Specifically, this is the case where only "t" is uttered instead of "ta". In order to avoid variations in evaluation in such cases, the given sentences should be sentences that can be clearly stated, such as ``I decided to draw pictures'' or ``I decided to draw pictures.'' There may be.

Furthermore, the sentence "I decided to draw a picture" may include the syllables "pa" or "la". Specifically, "My dad decided to draw a picture," "I decided to draw a picture of a poppy," "I decided to draw a picture of a police car," and "The rapper decided to draw a picture." An example is "I decided to draw it."

In this way, if the syllables ``pa line'' or ``la line'' are included, then the above-mentioned ``papapapa...'', ``tatatata...'', ``kakakaka...'', ``ralalara...'' Estimation of tongue movement, etc. can be realized without measuring things such as ``.

[Modification 2]
In the above embodiment, an example was described in which the eating and swallowing function evaluation device 100 evaluates the number of predetermined syllables uttered by the person U to be evaluated (also called oral diadochokinesis). In Modification 1, a method for accurately counting the number of syllables in oral diadochokinesis will be described. FIG. 15 is a flowchart showing the processing procedure of the eating and swallowing function evaluation method according to the second modification.

First, the acquisition unit 110 acquires voice data of the evaluator U's vocal practice (S201). FIG. 16 is a diagram illustrating an example of voice data of the person being evaluated U during vocal practice. In FIG. 16, as an example, voice data is shown when the person to be evaluated U practices speaking "Pa, Pa, Pa, Pa...". In the vocal practice, the person being evaluated U is required to speak clearly, but not quickly.

Next, the calculation unit 120 calculates a reference sound pressure difference based on the acquired vocal practice audio data (S202). Specifically, the calculation unit 120 extracts a plurality of parts corresponding to "pa" from the waveform of the audio data, and calculates the sound pressure difference for each of the extracted parts. The reference sound pressure difference is, for example, the average value of a plurality of calculated sound pressure differences x a predetermined percentage (70%, etc.). The calculated reference sound pressure difference is stored in the storage unit 160, for example.

Next, the acquisition unit 110 acquires the voice data to be evaluated by the person U to be evaluated (S203). FIG. 17 is a diagram illustrating an example of voice data to be evaluated by the person U to be evaluated.

Next, the calculation unit 120 counts the number of syllables whose peak value is equal to or greater than the reference sound pressure difference, which are included in the acquired speech data to be evaluated (S204). Specifically, the calculation unit 120 counts the number of parts included in the waveform of the audio data that correspond to "pa" and whose peak value is equal to or greater than the reference sound pressure difference calculated in step S202. do. In other words, only clearly uttered "pa" are counted. On the other hand, a portion corresponding to "pa" included in the waveform of the audio data and whose peak value is less than the reference sound pressure difference calculated in step S202 is not counted.

The evaluation unit 130 then evaluates the eating and swallowing function of the person U to be evaluated based on the number counted by the calculation unit 120 (S205).

As described above, the eating and swallowing function evaluation device 100 determines the number of portions of the acquired speech data to be evaluated that correspond to a predetermined syllable and whose peak value exceeds the reference sound pressure difference. Evaluate person U's eating and swallowing function based on the following. According to this, the eating and swallowing function evaluation device 100 can evaluate the eating and swallowing function of the person U to be evaluated more accurately. Note that in Modification 1, the reference sound pressure difference is determined by actual measurement, but a threshold value corresponding to the reference sound pressure difference may be determined in advance experimentally or empirically.

[Modification 3]
In Modification 3, another example of displaying evaluation results and advice based on the evaluation results will be described. An image as shown in FIG. 18 is displayed on the display of the mobile terminal 300 as the evaluation result. FIG. 18 is a diagram showing an example of an image for presenting evaluation results. The image shown in FIG. 18 can be printed by, for example, a multifunction device (not shown) that is communicatively connected to the mobile terminal 300.

In the image of FIG. 18, seven evaluation items regarding the eating and swallowing function are displayed in the form of a radar chart. Specifically, the seven items are tongue movement, jaw movement, swallowing movement, lip strength, ability to hold food together, ability to prevent choking, and ability to chew hard foods. Note that the number of items is not limited to seven, and may be six or less, or eight or more. Items other than the above seven include, for example, cheek movements and dryness of the mouth.

The evaluation values for these seven items are expressed in three stages: 1: Caution required, 2: Slight caution, and 3: Normal. Note that the evaluation value may be expressed in four or more stages.

The solid line in the radar chart indicates the measured evaluation value of the eating and swallowing function of the person to be evaluated U determined by the evaluation unit 130. Each of the measured evaluation values for the seven items is determined by the evaluation unit 130 by combining one or more of the various evaluation methods described in the above embodiments and other evaluation methods.

On the other hand, the broken line in the radar chart is an evaluation value determined based on the results of a questionnaire administered to the person U to be evaluated. In this way, if the measured evaluation value and the evaluation value based on the questionnaire results are displayed simultaneously, the person U to be evaluated can easily recognize the difference between his/her subjective symptoms and the actual symptoms. Note that instead of the evaluation value based on the questionnaire results, the past measured evaluation value of the person U to be evaluated may be displayed as a comparison target.

Further, when the number of times a predetermined syllable (for example, "pa", "ta", "ka") is uttered is used in the evaluation, number information indicating these times is displayed (the right part of FIG. 18).

When the “meal suggestion” portion is selected while the image in FIG. 18 is being displayed, the suggestion unit 150 displays an image showing advice regarding meals based on the evaluation results. In other words, the proposal unit 150 makes a proposal regarding a meal corresponding to the evaluation result of the eating and swallowing function. FIG. 19 is a diagram illustrating an example of an image for presenting dietary advice.

In the image of FIG. 19, advice regarding meals is displayed in each of a first display area 301, a second display area 302, and a third display area 303. Each display area displays the main text (upper row) and specific advice (lower row).

The displayed advice is the advice associated with the item whose actual measured evaluation value is determined to be "1: Caution required." If three or more items are determined to be "1: Caution required", advice for the top three items is displayed according to a predetermined priority order for the seven items.

In order to display advice in this manner, at least one advice is prepared in advance for each of the seven items described above and is stored in the storage unit 160 as proposal data 162. Note that multiple patterns of advice (for example, three patterns of advice) may be prepared for each of the seven items. In this case, which pattern of advice is displayed is determined randomly, for example, but may also be determined according to a predetermined algorithm. The advice includes, for example, how to prepare the meal (specifically, how to cook it), how to set up the environment for the meal (specifically, how to sit and posture, etc.), and what to be careful about while eating (specifically, how to chew the food thoroughly, how to take a bite, etc.). It is prepared in advance, taking into consideration things such as how much to use, etc.

Further, the advice regarding meals may include advice regarding nutrition, or may provide information regarding places to eat. For example, information on restaurants that provide swallowing-adjusted meals may be provided as advice regarding meals.

In addition, when the actual measurement evaluation values of all seven items are determined to be "3: normal", for example, the first constant type corresponding to "3: normal" is displayed in the first display area 301 and the second display area 302. Advice will be displayed. In addition, if there is no item that has been determined as "1: Caution" but there is an item that has been determined as "2: Slightly Caution," a second standard format corresponding to "2: Slight Caution" is displayed in the first display area 301. Advice is displayed, and in the second display area 302 and the third display area 303, advice associated with the item determined to be "2: Slightly Caution" among the seven items is displayed. When it is determined that two or more items are "2: Slightly Caution," advice is displayed that is associated with the top two items according to a predetermined priority order for the seven items.

When the "exercise suggestion" portion is selected while the image of FIG. 19 is being displayed, the suggestion unit 150 displays an image for presenting advice regarding exercise based on the evaluation results. In other words, the proposal unit 150 makes a proposal regarding exercise corresponding to the evaluation result of the eating and swallowing function. FIG. 20 is a diagram showing an example of an image for presenting advice regarding exercise.

FIG. 20 is an image displayed when the "tongue movement" is determined to be "1: Caution required." The image showing the advice regarding exercise includes an explanation of the exercise method and an illustration showing the exercise method.

Note that if there are multiple items determined as "1: Caution required", by selecting the "Next" part of the image in Figure 20, the image in Figure 20 will be changed to the image in Figure 21 and the image in Figure 22. Switch to images to present other exercise advice, such as images. FIG. 21 is a diagram showing an example of an image for presenting advice regarding exercise, which is displayed when the item "Swallowing movement" is determined to be "1: Caution required." FIG. 22 is a diagram showing an example of an image for presenting advice regarding exercise, which is displayed when the item "Ability to prevent choking" is determined to be "1: Caution required."

The display examples of evaluation results and advice based on the evaluation results have been described above. All such evaluation results and advice based on the evaluation results (both dietary advice and exercise advice) can be printed by a printing device. Although not shown, the advice based on the evaluation results may include advice regarding medical institutions. That is, the proposal unit 150 may make a proposal regarding a medical institution corresponding to the evaluation result of the eating and swallowing function. In this case, the image for presenting advice regarding the medical institution may include, for example, map information of the medical institution.

[Effects etc.]
As explained above, the eating and swallowing function evaluation method according to the present embodiment collects the sound of the person U uttering a predetermined syllable or a predetermined sentence in a non-contact manner, as shown in FIG. an acquisition step (step S101) of acquiring voice data obtained by and an evaluation step (step S103) for evaluating the function.

According to this, the eating and swallowing function of the person U to be evaluated can be easily evaluated by acquiring sound data suitable for evaluating the eating and swallowing function collected in a non-contact manner. In other words, the eating and swallowing function of the person U can be evaluated simply by the person U uttering a predetermined syllable or a predetermined sentence toward a sound collection device such as the mobile terminal 300.

Furthermore, in the evaluation step, at least one of the motor function of facial muscles, the motor function of the tongue, the saliva secretion function, and the occlusal state of the teeth may be evaluated as the eating and swallowing function.

According to this, for example, the motor function of facial muscles during the preparatory period, the motor function of the tongue during the preparatory period, the occlusal state of the teeth during the preparatory period, the secretion function of saliva during the preparatory period, the motor function of the tongue during the oral period, or The motor function of the tongue during the pharyngeal stage can be evaluated.

Further, the predetermined syllable may be composed of a consonant and a vowel following the consonant, and in the calculation step, the sound pressure difference between the consonant and the vowel may be calculated as the feature amount.

According to this, the person U to be evaluated can easily prepare by simply uttering a predetermined syllable composed of a consonant and a vowel following the consonant toward a sound collection device such as the mobile terminal 300. It is possible to evaluate the motor function of the tongue during the stage, the occlusal state of the teeth during the preparation stage, or the motor function of the tongue during the pharyngeal stage.

Further, the predetermined sentence includes a syllable portion consisting of a consonant, a vowel following the consonant, and a consonant following the vowel, and in the calculation step, the time required to utter the syllable portion is calculated as a feature quantity. good.

According to this, the evaluator U simply speaks a predetermined sentence including a consonant, a vowel following the consonant, and a syllable portion consisting of the consonant following the vowel into a sound collection device such as the mobile terminal 300. , it is possible to easily evaluate the tongue motor function of the person U to be evaluated during the preparatory period, the tongue motor function during the oral period, or the tongue motor function during the pharyngeal period.

Furthermore, the predetermined sentence may include a character string in which syllables including vowels are continuous, and in the calculation step, the amount of change in the second formant frequency F2 obtained from the spectrum of the vowel portion may be calculated as the feature amount.

According to this, the person U to be evaluated can simply speak a predetermined sentence containing a string of consecutive syllables including vowels to a sound collection device such as the mobile terminal 300, and the preparation period for the person U to be evaluated can be easily completed. The salivary secretion function or the occlusal state of the teeth during the preparatory stage can be evaluated.

Further, the predetermined sentence may include a plurality of syllables including vowels, and in the calculation step, variations in the first formant frequency F1 obtained from the spectrum of the vowel portion may be calculated as the feature quantity.

According to this, by simply uttering a predetermined sentence containing a plurality of syllables including vowels to a sound collection device such as the mobile terminal 300, the evaluationee U can easily improve the oral stage in the preparation period. The motor function of the tongue can be evaluated.

Furthermore, in the calculation step, the pitch of the voice may be calculated as the feature quantity.

According to this, the saliva secretion function of the person U to be evaluated during the preparation period can be easily evaluated by simply saying a predetermined syllable or a predetermined sentence to a sound collection device such as the mobile terminal 300. can.

Further, the predetermined sentence may include a predetermined word, and in the calculation step, the time required to utter the predetermined word may be calculated as the feature amount.

According to this, the occlusal state of the teeth of the assessee U during the preparation period can be easily determined by the assessee U simply speaking a predetermined sentence including a predetermined word toward a sound collection device such as the mobile terminal 300. It can be evaluated.

Further, in the calculation step, the time required to utter the entire predetermined sentence may be calculated as a feature amount.

According to this, the occlusal state of the teeth of the person U to be evaluated in the preparatory period can be easily evaluated simply by the person U being evaluated to utter a predetermined sentence toward the sound collection device such as the mobile terminal 300.

Further, the predetermined sentence includes a phrase in which a syllable consisting of a consonant and a vowel following the consonant is repeated, and in the calculation step, the number of times the syllable is uttered within a predetermined time is calculated as a feature quantity. You can.

According to this, the evaluator U simply speaks a predetermined sentence including a consonant and a phrase in which syllables made up of a vowel following the consonant are repeated to a sound collection device such as the mobile terminal 300. It is possible to easily evaluate the motor function of the facial muscles of the person U to be evaluated during the preparatory period, the motor function of the tongue during the preparatory period, the motor function of the tongue during the oral period, or the motor function of the tongue during the pharyngeal period.

Furthermore, in the calculation step, the number of portions of the acquired audio data that correspond to syllables and whose peak value exceeds the threshold value is determined as the number of times the syllable was uttered.

According to this, the eating and swallowing function of the person U to be evaluated can be evaluated more accurately.

Moreover, the eating and swallowing function evaluation method may further include an output step (step S104) of outputting the evaluation result.

According to this, it becomes possible to check the evaluation results.

The eating and swallowing function evaluation method further includes a proposal step (step S105) of making a proposal regarding eating and swallowing to the person being evaluated U by comparing the outputted evaluation results with predetermined data. You can stay there.

According to this, the person U to be evaluated can receive suggestions on what measures to take regarding eating and swallowing when the eating and swallowing function deteriorates at each stage. For example, if Evaluate U undergoes rehabilitation based on the proposal or follows a diet based on the proposal, aspiration pneumonia can be prevented by suppressing aspiration, and the eating and swallowing function can be improved. It is possible to improve malnutrition caused by low nutritional value.

Further, in the proposal step, at least one of a proposal regarding a meal corresponding to the evaluation result of the eating and swallowing function and a proposal regarding exercise corresponding to the evaluation result of the eating and swallowing function is made.

According to this, the person U to be evaluated can receive suggestions about what kind of meal he should take or what kind of exercise he should do when his eating and swallowing function has deteriorated.

Moreover, in the acquisition step, personal information of the person U to be evaluated may be further acquired.

According to this, for example, in a proposal regarding eating and swallowing, a more effective proposal can be made to the person being evaluated U by combining the evaluation results of the person being evaluated U's eating and swallowing function with personal information. Can be done.

Furthermore, the eating and swallowing function evaluation device 100 according to the present embodiment acquires audio data obtained by non-contact collecting the voice of the evaluated person U uttering a predetermined syllable or a predetermined sentence. a calculation unit 120 that calculates a feature amount from the audio data acquired by the acquisition unit 110; and an evaluation unit 130 that evaluates the eating and swallowing function of the person U from the feature amount calculated by the calculation unit 120. An output unit 140 that outputs the evaluation result evaluated by the evaluation unit 130 is provided.

According to this, it is possible to provide the eating and swallowing function evaluation device 100 that enables the evaluation of the eating and swallowing function of the person U to be evaluated in a simple manner.

In addition, the eating and swallowing function evaluation system 200 according to the present embodiment includes the eating and swallowing function evaluation device 100 and a sound collector that collects the sound of the person U uttering a predetermined syllable or a predetermined sentence in a non-contact manner. A sound device (mobile terminal 300 in this embodiment). The acquisition unit 110 of the eating and swallowing function evaluation device 100 acquires audio data obtained by non-contact collection of the voice of the evaluated person U uttering a predetermined syllable or a predetermined sentence using a sound collection device.

According to this, it is possible to provide the eating and swallowing function evaluation system 200 that allows the evaluation of the eating and swallowing function of the person U to be evaluated in a simple manner.

(Other embodiments)
Although the eating and swallowing function evaluation method and the like according to the embodiments have been described above, the present invention is not limited to the above embodiments.

For example, the reference data 161 is predetermined data, but may be updated based on an evaluation result obtained when an expert actually diagnoses the eating and swallowing function of the person U to be evaluated. Thereby, it is possible to improve the evaluation accuracy of the eating and swallowing function. Note that machine learning may be used to improve the evaluation accuracy of the eating and swallowing function.

Further, for example, although the proposal data 162 is predetermined data, the person U to be evaluated may evaluate the proposal content and it may be updated based on the evaluation result. In other words, for example, if a proposal is made for the inability to masticate based on a certain feature amount even though the person being evaluated is able to masticate without any problems, the person being evaluated is Evaluate it as wrong. Then, by updating the proposal data 162 based on this evaluation result, erroneous proposals as described above are not made based on the same feature amount. In this way, the content of the proposal regarding eating and swallowing for the person U to be evaluated can be made more effective. Note that machine learning may be used to make suggestions regarding eating and swallowing more effective.

Furthermore, for example, the evaluation results of the eating and swallowing function may be accumulated together with personal information as big data and used for machine learning. Further, the content of suggestions related to eating and swallowing may be accumulated as big data together with personal information and used for machine learning.

Further, for example, in the embodiment described above, the eating and swallowing function evaluation method included the suggestion step (step S105) for making a proposal regarding eating and swallowing, but it does not have to be included. In other words, the eating and swallowing function evaluation device 100 does not need to include the suggestion unit 150.

Further, for example, in the above embodiment, the personal information of the person to be evaluated U is acquired in the acquisition step (step S101), but the personal information does not have to be acquired. In other words, the acquisition unit 110 does not need to acquire the personal information of the person U to be evaluated.

Further, for example, in the embodiment described above, the evaluationee U is described as speaking in Japanese, but the evaluationee U may speak in a language other than Japanese, such as English. In other words, it is not essential that Japanese audio data be subjected to signal processing, and audio data in languages other than Japanese may be subjected to signal processing.

Further, for example, the steps in the eating and swallowing function evaluation method may be executed by a computer (computer system). Further, the present invention can be realized as a program for causing a computer to execute the steps included in those methods. Further, the present invention can be realized as a non-transitory computer-readable recording medium such as a CD-ROM on which the program is recorded.

For example, when the present invention is implemented as a program (software), each step is executed by executing the program using hardware resources such as a computer's CPU, memory, and input/output circuits. . That is, each step is executed by the CPU acquiring data from a memory or an input/output circuit, etc., performing calculations, and outputting the calculation results to the memory, input/output circuit, etc.

Further, each component included in the eating and swallowing function evaluation device 100 and the eating and swallowing function evaluation system 200 of the above embodiments may be realized as a dedicated or general-purpose circuit.

Further, each component included in the eating and swallowing function evaluation device 100 and the eating and swallowing function evaluation system 200 of the above embodiments is realized as an LSI (Large Scale Integration) that is an integrated circuit (IC). Good too.

Further, the integrated circuit is not limited to an LSI, and may be realized by a dedicated circuit or a general-purpose processor. A programmable FPGA (Field Programmable Gate Array) or a reconfigurable processor in which connections and settings of circuit cells inside the LSI can be reconfigured may be used.

Furthermore, if an integrated circuit technology that replaces LSI emerges due to advances in semiconductor technology or other derivative technologies, it will naturally be possible to incorporate this technology into the eating and swallowing function evaluation device 100 and the eating and swallowing function evaluation system 200. Each component may be integrated into an integrated circuit.

In addition, forms obtained by making various modifications to the embodiments that those skilled in the art can think of, and forms realized by arbitrarily combining the constituent elements and functions of each embodiment without departing from the spirit of the present invention. are also included in the present invention.

100 Eating and swallowing function evaluation device 110 Acquisition unit 120 Calculation unit 130 Evaluation unit 140 Output unit 161 Reference data 162 Proposed data (data)
200 Eating and swallowing function evaluation system 300 Mobile terminal (sound collection device)
F1 First formant frequency F2 Second formant frequency U Evaluate

Claims (19)

An eating and swallowing function evaluation method performed by an eating and swallowing function evaluation device, the method comprising:
an acquisition step in which the acquisition unit included in the eating and swallowing function evaluation device acquires audio data obtained by non-contact collecting the voice of the person to be evaluated uttering a predetermined syllable or a predetermined sentence;
a calculation step in which a calculation unit included in the eating and swallowing function evaluation device calculates a feature amount from the audio data acquired by the acquisition unit;
an evaluation step in which the evaluation unit included in the eating and swallowing function evaluation device evaluates the eating and swallowing function of the person to be evaluated from the feature amount calculated by the calculation unit;
In the evaluation step, the evaluation unit evaluates at least one of the motor function of facial muscles, the motor function of the tongue, the secretion function of saliva, and the occlusal state of the teeth as the eating and swallowing function,
The predetermined syllable is composed of a consonant and a vowel following the consonant,
In the calculation step, a sound pressure difference between the consonant and the vowel is calculated as the feature amount.
Eating and swallowing function evaluation method. An eating and swallowing function evaluation method performed by an eating and swallowing function evaluation device, the method comprising:
an acquisition step in which the acquisition unit included in the eating and swallowing function evaluation device acquires audio data obtained by non-contact collecting the voice of the person to be evaluated uttering a predetermined syllable or a predetermined sentence;
a calculation step in which a calculation unit included in the eating and swallowing function evaluation device calculates a feature amount from the audio data acquired by the acquisition unit;
an evaluation step in which the evaluation unit included in the eating and swallowing function evaluation device evaluates the eating and swallowing function of the person to be evaluated from the feature amount calculated by the calculation unit;
In the evaluation step, the evaluation unit evaluates at least one of the motor function of facial muscles, the motor function of the tongue, the secretion function of saliva, and the occlusal state of the teeth as the eating and swallowing function,
The predetermined sentence includes a string of consecutive syllables including vowels,
In the calculation step, the amount of change in the second formant frequency obtained from the spectrum of the vowel part is calculated as the feature amount.
Eating and swallowing function evaluation method. An eating and swallowing function evaluation method performed by an eating and swallowing function evaluation device, the method comprising:
an acquisition step in which the acquisition unit included in the eating and swallowing function evaluation device acquires audio data obtained by non-contact collecting the voice of the person to be evaluated uttering a predetermined syllable or a predetermined sentence;
a calculation step in which a calculation unit included in the eating and swallowing function evaluation device calculates a feature amount from the audio data acquired by the acquisition unit;
an evaluation step in which the evaluation unit included in the eating and swallowing function evaluation device evaluates the eating and swallowing function of the person to be evaluated from the feature amount calculated by the calculation unit;
In the evaluation step, the evaluation unit evaluates at least one of the motor function of facial muscles, the motor function of the tongue, the secretion function of saliva, and the occlusal state of teeth as the eating and swallowing function,
The predetermined sentence includes a plurality of syllables including vowels,
In the calculation step, the variation in the first formant frequency obtained from the spectrum of the vowel part is calculated as the feature amount.
Eating and swallowing function evaluation method. The predetermined syllable is composed of a consonant and a vowel following the consonant,
In the calculation step, a sound pressure difference between the consonant and the vowel is calculated as the feature amount.
The eating and swallowing function evaluation method according to claim 2 or 3 . The predetermined sentence includes a syllable portion consisting of a consonant, a vowel following the consonant, and a consonant following the vowel,
In the calculation step, the time required to utter the syllable part is calculated as the feature amount.
The method for evaluating eating and swallowing function according to any one of claims 1 to 4 . The predetermined sentence includes a string of consecutive syllables including vowels,
In the calculation step, the amount of change in the second formant frequency obtained from the spectrum of the vowel part is calculated as the feature amount.
The method for evaluating eating and swallowing function according to any one of claims 1 and 3 to 5 . The predetermined sentence includes a plurality of syllables including vowels,
In the calculation step, the variation in the first formant frequency obtained from the spectrum of the vowel part is calculated as the feature amount.
The method for evaluating eating and swallowing function according to any one of claims 1 , 2, 4 to 6 . In the calculation step, the pitch of the voice is calculated as the feature amount,
The method for evaluating eating and swallowing function according to any one of claims 1 to 7 . the predetermined sentence includes a predetermined word,
In the calculation step, the time required to utter the predetermined word is calculated as the feature amount.
The method for evaluating eating and swallowing function according to any one of claims 1 to 8 . In the calculation step, the time required to utter the entire predetermined sentence is calculated as the feature amount.
The method for evaluating eating and swallowing function according to any one of claims 1 to 9 . The predetermined sentence includes a phrase in which a syllable consisting of a consonant and a vowel following the consonant is repeated,
In the calculation step, the number of times the syllable is uttered within a predetermined time is calculated as the feature amount.
The method for evaluating eating and swallowing function according to any one of claims 1 to 10 . In the calculation step, the number of portions of the acquired audio data that correspond to the syllable and have a peak value exceeding a threshold value is determined as the number of times the syllable is uttered.
The eating and swallowing function evaluation method according to claim 11 . The eating and swallowing function evaluation method further includes an output step of outputting the evaluation result.
The eating and swallowing function evaluation method according to any one of claims 1 to 12 . In the eating and swallowing function evaluation method, the proposal unit included in the eating and swallowing function evaluation device further compares the evaluation results output in the output step with predetermined data, thereby providing a solution for the evaluated person. a suggestion step for making suggestions regarding feeding and swallowing;
The eating and swallowing function evaluation method according to claim 13 . In the proposal step, at least one of a proposal regarding diet corresponding to the evaluation result of the eating and swallowing function and a proposal regarding exercise corresponding to the evaluation result of the eating and swallowing function is made.
The eating and swallowing function evaluation method according to claim 14 . In the acquisition step, the personal information of the evaluator is further acquired;
The eating and swallowing function evaluation method according to any one of claims 1 to 15 . A program for causing a computer to execute the eating and swallowing function evaluation method according to any one of claims 1 to 16 . an acquisition unit that acquires audio data obtained by non-contact collecting the voice of a person being evaluated uttering a predetermined syllable or a predetermined sentence;
a calculation unit that calculates a feature amount from the audio data acquired by the acquisition unit;
an evaluation unit that evaluates the eating and swallowing function of the person to be evaluated from the feature amount calculated by the calculation unit;
an output unit that outputs the evaluation result evaluated by the evaluation unit,
The evaluation unit evaluates at least one of the motor function of facial muscles, the motor function of the tongue, the secretion function of saliva, and the occlusal state of teeth as the eating and swallowing function,
The predetermined syllable is composed of a consonant and a vowel following the consonant, and the calculation unit calculates a sound pressure difference between the consonant and the vowel as the feature amount.
or
The predetermined sentence includes a character string in which syllables including vowels are continuous, and the calculation unit calculates the amount of change in the second formant frequency obtained from the spectrum of the vowel part as the feature amount.
or
The predetermined sentence includes a plurality of syllables including vowels, and the calculation unit calculates a variation in first formant frequency obtained from a spectrum of the vowel part as the feature amount.
Eating and swallowing function evaluation device. The eating and swallowing function evaluation device according to claim 18 ,
a sound collection device that collects the sound of the person being evaluated uttering the predetermined syllable or the predetermined sentence in a non-contact manner;
The acquiring unit of the eating and swallowing function evaluation device acquires audio data obtained by non-contact collecting the sound of the evaluated person uttering a predetermined syllable or a predetermined sentence.
Eating and swallowing function evaluation system.

Images