JP2023095114A - Health state evaluation device - Google Patents

Abstract

To evaluate the health state of a target site more accurately.SOLUTION: A health state evaluation device 10 includes: a video data acquisition unit 11 for acquiring plural pieces of video data about different actions related to a target site of a subject whose health state is to be evaluated; a state score calculation unit 13 for calculating at least one state score showing the state of the action from each video data; and a site-specific score calculation unit 14 for calculating a site-specific score related to the health state of the target site on the basis of the state score.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to a health condition assessment device.

With the increase in the number of elderly people, various techniques for assisting improvement of physical functions are being studied. For example, Patent Literature 1 discloses a technique of acquiring image data related to a predetermined function of a target user using a camera, extracting feature amounts related to the predetermined function from the image data, and determining an exercise program based on the feature amounts. is described.

Japanese Patent Application Laid-Open No. 2021-26650

However, in the method described in Patent Literature 1, although the predetermined function of the target site is evaluated, evaluation of the health condition of the target site from a broader perspective is not considered.

An object of the present disclosure is to provide a technique capable of more accurately evaluating the health condition of a target site.

A health condition evaluation apparatus according to an embodiment of the present disclosure includes a moving image data acquisition unit that acquires a plurality of moving image data obtained by capturing mutually different motions related to a target part of a subject whose health condition is to be evaluated; a state score calculation unit that calculates one or more state scores indicating the state of motion from each of the moving image data; and

According to the above-described health condition evaluation device, one or more condition scores indicating the condition of a motion are calculated from each of a plurality of video data obtained by imaging different motions, and based on these condition scores, the health condition of the target part is evaluated. A site-specific score relating to the state is calculated. In this way, since the site-specific score indicating the health condition of each site is calculated from a plurality of video data obtained by capturing different motions, the health of the target site can be improved compared to the case of focusing on the specific motion of the site. The condition can be evaluated more multilaterally and accurately.

ADVANTAGE OF THE INVENTION According to this invention, the technique which can evaluate the health condition of a target site|part more correctly is provided.

FIG. 1 is a diagram illustrating an example of a schematic configuration of a health condition evaluation system including a health condition evaluation device. FIG. 2 is a diagram showing an example of a correspondence relationship between an action performed by a subject and a state detected by a state detection unit. FIGS. 3A and 3B are diagrams for explaining an example of a state score calculation method. FIG. 4 is a diagram illustrating an example of a method for calculating a site-specific score. FIG. 5 is a diagram illustrating an example of the hardware configuration of the health condition evaluation device. FIG. 6 is a flow chart showing an example of a health condition evaluation method. FIG. 7 is a diagram showing an example of the configuration of a health condition evaluation program.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and overlapping descriptions are omitted.

[Health condition evaluation system and health condition evaluation device]
FIG. 1 is a schematic configuration diagram of a health condition evaluation system 1 including a health condition evaluation device 10 according to one embodiment. The health condition evaluation system 1 is a system that captures a moving image of the motion of the subject X and evaluates the health condition of the target part of the subject X based on this moving image data. In the present embodiment, a case of evaluating the health condition of the "stomatognathic system" as a target part of the subject X will be described. The stomatognathic system encompasses four target parts of the tongue, lips, jaw, and cheeks. The health condition evaluation system 1 calculates the score D for each part as a score indicating the state of health for each of the above four parts, and also calculates the score indicating the health condition for all parts, that is, the stomatognathic system.

The health condition evaluation system 1 includes a health condition evaluation device 10 and an imaging device 20 . The imaging device 20 has a function of capturing a moving image related to the motion of the subject X's target part. The imaging device 20 is not limited as long as it has a moving image shooting function, and devices such as cameras, tablet terminals, and smartphones can be used.

The health condition evaluation device 10 includes a video data acquisition unit 11 , a condition detection unit 12 , a condition score calculation unit 13 , a site-specific score calculation unit 14 , a result output unit 15 , and a related information storage unit 16 .

The moving image data acquisition unit 11 has a function of acquiring a plurality of types of moving image data obtained by imaging the motion of the subject X from the imaging device 20 . The moving image data of the subject X is data obtained by capturing images of the subject X performing an action designated in advance for calculating the score of the target part. For example, the actions used to evaluate the health condition of the stomatognathic system include, for example, a pronunciation action of repeatedly pronouncing a single syllable for a predetermined period of time, a facial expression action of imitating a specified number of facial expressions, and a specified tongue movement. Orienting tongue movements are included. The target person X is caused to perform these actions, and the moving images thereof are acquired by the imaging device 20 . At this time, the imaging device 20 acquires moving image data including audio data, and transmits this data to the health condition evaluation device 10 . Using the moving image data acquired from the imaging device 20 by the moving image data acquiring unit 11, the subsequent analysis is performed.

The state detection unit 12 detects the state of the subject X using the video data acquired by the video data acquisition unit 11 . FIG. 2 is a diagram illustrating an example of the relationship between actions and states. The "state" to be detected is an index indicating how well the specified action is executed. One or more "states" are set for each action, and each of them is quantified. be. For example, with regard to the pronunciation operation, the number of pronunciations and the clearness of the pronunciation can be used as indicators by analyzing the voice data. Various techniques can be used as a method for analyzing voice data, and one example is an analysis method using machine learning. For example, a spectrogram may be created by spectrally analyzing speech data, and a feature amount may be extracted from the spectrogram using a CNN (Convolutional Neural Network). Furthermore, for this feature quantity, using a model using LSTM (Long Short-Term Memory) or RNN (Recurrent Neural Network), etc., the probability of occurrence of each state is obtained, and the pronounced sound , the number of pronunciations, the clarity of pronunciation, etc. can be obtained. These techniques are used in speech recognition methods, and by applying them, information on pronunciation can be obtained from speech data.

On the other hand, by performing image analysis on the moving image data of the sounding action, it is possible to quantify how large the jaw movement is and use it as a numerical value indicating the "state". An example of such analysis is the application of a state detection model using image data. For example, a judgment system model that determines jaw movements constructed by learning data with known conditions using ResNet (Residual Neural Network) in advance, and a measurement system model that measures the degree of opening and tilt of the mouth. By preparing and fitting the image data to these models, the movement of the jaw can be quantified. Note that the method of creating the determination system model and the measurement model is not limited to the ResNet described above, and a known machine learning technique can be used.

Similarly, with respect to facial expression actions, for example, the amount of exercise when one facial expression is designated and the duration of the facial expression can be used as numerical values indicating the state by performing image analysis. As for the tongue movement, for example, the amount of movement, the duration of the tongue sticking out in a specified direction, the openness of the mouth at rest, and the like can be used as numerical values indicating the state of the movement.

As described above, the state detection unit 12 quantifies each index indicating the state of the action by using various information included in the moving image data related to each action. It should be noted that the type of state to be digitized may be determined in advance, and this information may be held in the related information holding unit 16 .

The state score calculator 13 has a function of calculating a score from the numerical value of the index detected by the state detector 12 . FIG. 3 shows an example of the correspondence between index values and scores. FIG. 3(a) shows an example of calculating the state score according to the number of pronunciations of a predetermined sound in the pronunciation operation. An example is shown in which the score is set to 5 points when the number of pronunciations is up to 30 times, and the score is set to 10 points when the number of pronunciations is 31 times or more. In this way, the state score calculator 13 converts the numerical value for each index into a score.

FIG. 3B shows an example of dynamically changing the relationship between the index (here, the number of pronunciations) and the score, in which the score assignment is changed according to the numerical distribution of the index. In this example, according to the distribution of the index of the subjects, a predetermined percentage (eg, 25%) of the subjects is given a score of 10 points, and a predetermined percentage (eg, 25%) of the subjects is given a score of 1. In this method, a standard is determined such that a target person's score is 5 points, and the relationship between the numerical value of the number of pronunciations and the score is adjusted so that the score is assigned to this ratio. As a result, in the example shown in FIG. 3(b), when the number of pronunciations is 1 to 7, the score is 1 point, when the number of pronunciations is 8 to 15, the score is 5 points, and the number of pronunciations is 16 times. In the above cases, the score is 10 points. In this way, when the score is calculated by the state score calculation unit 13, the relationship between the numerical value of the index and the score may be adjusted so that the difference in the numerical value relative to the other person is likely to appear in the score. . As for the score adjustment method, adjustment may be performed in consideration of variations in numerical values relating to the states of a large number of subjects as described above.

The part-by-part score calculation unit 14 has a function of calculating a condition score for each target part from the condition scores obtained in each of the above actions. The scores calculated above are for specific indicators in each movement, but each indicator can be associated with at least one of tongue, lips, jaw, and cheeks. For example, it can be estimated that the number of pronunciations in a pronunciation action is related to the health of the tongue, lips and jaws. In addition, it is presumed that the clarity of pronunciation in the pronunciation operation is related to the health condition of the tongue and lips. In addition, the amount of movement of facial expressions is presumed to be related to the health of lips, jaws and cheeks. In this way, among the state scores calculated from the respective motions described above, scores related to the target part are combined to calculate the score of the target part.

FIG. 4 shows an example of calculating the site-specific score. Here, the score is set to be calculated out of 100 points. For example, state scores related to the tongue include the number of pronunciations, clearness of pronunciation, amount of tongue movement, and tongue movement maintenance time. When a certain condition is out of 100 points, the score is calculated using the following formula (1).
(Total status score/(number of status scores x 10)) x 100 (1)
Here, it is assumed that each state score is set to a maximum of 10 points, and the condition for a state score to be a perfect score is the number of state scores (types of state scores)×10. However, when calculating the state score for each part, for example, weighting may be performed to set the predetermined state score to a maximum of 20 points. In this case, the part of (the number of state scores×10) in the above formula (1) is appropriately changed.

In addition, the state score is calculated for the lips shown in FIG. 4 in the same manner as for the tongue. Regarding the lips, among the state scores related to the sounding action, different scores are set for the number of soundings and clarity of sounding according to the type of sound that is sounded. In this way, the state score may be set by subdividing the action.

Furthermore, in FIG. 4, the total score is also calculated. Here, the average value of the scores for each region of the tongue, lips, chin, and cheeks is calculated as the condition score for all regions (the stomatognathic system). Using the average value is an example, and weighting may be changed for each part.

In this manner, the site-specific score calculation unit 14 calculates the site-specific score for each target site by combining the state scores obtained from the test motions. It should be noted that which state score of which motion is to be used when calculating the site-specific score is determined in advance. Also, these pieces of information may be held in the related information holding unit 16 .

The result output unit 15 has a function of outputting the site-specific score calculated by the site-specific score calculation unit 14 . The output destination and output method are not particularly limited. For example, the data may be output as data to an external device, or may be displayed on a monitor or the like.

The related information holding unit 16 has a function of holding various kinds of information used for calculating the site-specific score. The information held in the related information holding unit 16 includes the calculation method of the numerical value related to the above-mentioned state (for example, the image analysis method), the information related to the correspondence relationship between the numerical value related to the state and the score, and the method of calculating the score for each part. etc., but in addition to this, information used for each process in the health condition evaluation device 10 may be held.

[Hardware configuration]
For example, the health condition evaluation device 10 described above may function as a computer. FIG. 5 is a diagram showing an example of the hardware configuration of the health condition evaluation device 10 according to this embodiment. Physically, the health evaluation device 10 may be configured as a computer device including a processor C1, a memory C2, a storage C3, a communication device C4, an input device C5, an output device C6, a bus C7, and the like.

In the following description, the term "apparatus" can be read as a circuit, device, unit, or the like. The hardware configuration of the health condition evaluation device 10 may be configured to include one or more of each device shown in FIG. Moreover, it may be configured without including some of the devices.

Each function in the health condition evaluation device 10 is performed by the processor C1 by loading predetermined software on hardware such as the processor C1 and the memory C2, and the communication by the communication device C4, the memory C2, and the storage C3 It is realized by controlling reading and/or writing of data.

The processor C1, for example, operates an operating system to control the entire computer. The processor C1 may be configured with a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like. Moreover, the processor C1 may be configured including a GPU (Graphics Processing Unit). For example, each functional unit of the health condition evaluation device 10 may be realized by the processor C1.

The processor C1 also reads programs (program codes), software modules and data from the storage C3 and/or the communication device C4 to the memory C2, and executes various processes according to these. As the program, a program that causes a computer to execute at least part of the operations described in the above embodiments is used. For example, each functional unit of the health condition evaluation device 10 may be implemented by a control program stored in the memory C2 and operated by the processor C1. Although it has been explained that the various processes described above are executed by one processor C1, they may be executed simultaneously or sequentially by two or more processors C1. Processor C1 may be implemented with one or more chips. Note that the program may be transmitted from a network via an electric communication line.

The memory C2 is a computer-readable recording medium, for example, at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. may be configured. The memory C2 may also be called a register, cache, main memory (main storage device), or the like. The memory C2 can store executable programs (program codes), software modules, etc. for implementing the health condition evaluation method according to one embodiment of the present invention.

The storage C3 is a computer-readable recording medium, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (for example, a compact disk, a digital versatile disk, a Blu-ray ray disk), smart card, flash memory (eg, card, stick, key drive), floppy disk, magnetic strip, and/or the like. Storage C3 may be called an auxiliary storage device. The aforementioned storage medium may be, for example, a database, server or other suitable medium including memory C2 and/or storage C3.

The communication device C4 is hardware (transmitting/receiving device) for communicating between computers via a wired and/or wireless network, and is also called a network device, network controller, network card, communication module, or the like.

The input device C5 is an input device (for example, keyboard, mouse, microphone, switch, button, sensor, etc.) that receives input from the outside. The output device C6 is an output device (for example, display, speaker, LED lamp, etc.) that outputs to the outside. Note that the input device C5 and the output device C6 may be integrated (for example, a touch panel).

Devices such as the processor C1 and the memory C2 are connected by a bus C7 for communicating information. The bus C7 may be composed of a single bus, or may be composed of different buses between devices.

[Health condition evaluation method]
A health condition evaluation method by the health condition evaluation device 10 will be described with reference to FIG.

First, the health condition evaluation device 10 executes step S01. In step S<b>01 , the moving image data acquisition unit 11 acquires moving image data from the imaging device 20 .

Next, the health condition evaluation device 10 executes step S02. In step S02, the state detection unit 12 detects a preset state from the moving image data. The result is a numerical value that is indicative of a particular condition. As described above, one or more states are detected from one moving image data. Furthermore, when there is a plurality of moving image data, similar processing is performed for each moving image data.

Next, the health condition evaluation device 10 executes step S03. In step S03, the state score calculation unit 13 converts the numerical value related to the state detected by the state detection unit 12 into a state score. This processing is performed for each numerical value obtained for each state.

Note that step S02 (state detection) and step S03 (state score calculation) may be performed in parallel. For example, after detecting the state of one video data, converting the state into a state score (S03), the processing of detecting the state of other video data (S02) may be performed in parallel.

Next, the health condition evaluation device 10 executes step S04. In step S<b>04 , part-specific score calculation section 14 calculates a part-specific score by combining and aggregating the state scores calculated by state score calculation section 13 . As a result, a site-specific score D indicating the health condition of each site is obtained. At this stage, the condition score of the entire multiple types of target regions (in the case of the above embodiment, the entire stomatognathic system) may be calculated.

Finally, the health condition evaluation device 10 executes step S05. In step S<b>05 , the result output unit 15 outputs the site-specific score D calculated by the site-specific score calculation unit 14 . Accordingly, the operator of the health condition evaluation device 10, the subject X, and the like can confirm the result.

[Health condition assessment program]
As shown in FIG. 7, the health condition evaluation program P1 includes a main module m10 for overall control of processing related to score calculation in the health condition evaluation device 10, a moving image data acquisition module m11, a condition detection module m12, and a condition score calculation module. It comprises a module m13, a region-specific score calculation module m14, and a result output module m15. Each of the modules m11 to m15 implements the respective functions of the moving image data acquisition unit 11, the condition detection unit 12, the condition score calculation unit 13, the part-specific score calculation unit 14, and the result output unit 15.

The health condition evaluation program P1 may be transmitted via a transmission medium such as a communication line, or may be stored in a recording medium M1 as shown in FIG. .

[Action]
The above-described health condition evaluation apparatus 10 calculates one or more condition scores indicating the condition of the motion from each of a plurality of video data obtained by imaging different motions, and based on these condition scores, determines the health condition of the target part. is calculated. In this way, in the health condition evaluation apparatus 10, since a region-specific score indicating the health condition of each region is calculated from a plurality of moving image data obtained by capturing mutually different actions, compared with the case of focusing on a specific action of the region. By doing so, the health condition of the target part can be evaluated in a more multifaceted manner.

Conventionally, as a method of evaluating the state of health, an evaluation based on whether or not a specific action can be performed has been performed. In addition, it has been considered to perform the above based on moving image data obtained by imaging the action. However, it may be difficult to accurately grasp the health condition of the target part of the subject X only by performing a specific action. On the other hand, the above-described health condition evaluation apparatus 10 calculates condition scores from motion data relating to a plurality of motions and combines them to calculate a score for each part, so that the condition of the target part can be evaluated more accurately. be able to.

The condition score calculation unit 13 of the health condition evaluation device 10 may calculate multiple types of condition scores from each of the plurality of moving image data. Further, the region-specific score calculation unit 14 may calculate the region-specific score based on a plurality of types of state scores obtained from each of a plurality of moving image data. With such a configuration, a plurality of state scores can be obtained from video data obtained by imaging one action, so that one action can be evaluated using more state scores. Therefore, the health condition of the target part can be evaluated more accurately.

Further, as described in the above embodiment, the moving image data may be data obtained by imaging motions related to a plurality of target parts. Further, the site-specific score calculation unit 14 may calculate the site-specific score for each target site based on a part of the state scores related to the target site. With the above configuration, it is possible to calculate the site-specific score for a plurality of target sites of the subject. In addition, since these target parts are parts related to the same motion, they are strongly related to each other. It is also possible to make a more detailed evaluation considering the difference in the score for each part of the body.

The part-specific score calculation unit 14 may calculate the overall score from the part-specific scores of a plurality of target parts. By adopting such a configuration, it is possible to obtain more comprehensive information on the health condition of the subject's body part including a plurality of target parts, and it is possible to grasp the trend of the health condition not limited to a specific part. .

In addition, like the data obtained by imaging the pronunciation movement in the above embodiment, the moving image data may include the moving image data obtained by imaging the vocalization movement. At this time, the state score calculation unit 13 calculates a first state score (in the above embodiment, the number of pronunciations, clarity of pronunciation, etc.) obtained from the audio information included in the video data, and a second state score obtained from the image information. (in the above-described embodiment, movement of the jaw, etc.) may be calculated. By adopting such a configuration, it is possible to obtain two state scores from the moving image data using the audio information and the image information, and it is possible to obtain more detailed information about the moving image data based on the utterance action. In addition, as described in the above embodiment, the configuration may be such that three or more state scores are obtained. In addition, all of the plurality of video data does not have to be video data containing audio data, and if at least one video data contains audio data, the condition score is calculated based on information other than image analysis, and this Since the site-specific score is calculated based on the above, it is possible to perform a more detailed evaluation of the target site as described above.

In the above embodiment, the case of evaluating the health condition assuming the stomatognathic system has been described, but the health condition evaluation device 10 using moving image data can be applied to other than the stomatognathic system. For example, body tissues related to vocalization can be cited as sites related to vocalization as well as the stomatognathic system. For example, since the cricothyroid muscle is a muscle that controls the vocal cords, the condition score can be calculated from the sound quality and pitch of the vocal cords. In addition, since the diaphragm has a function to control breathing that is performed at the same time as vocalization, the state score can be calculated from the number of vocalizations and the rise and fall of the vicinity of the diaphragm and shoulders. Furthermore, since abdominal muscles, back muscles, etc. also contribute to vocalization, the state score can be calculated from the clearness of pronunciation, the pitch, and the movements of the abdomen and back. In this way, when evaluating not only the stomatognathic system but also the part involved in vocalization, the score for each part can be calculated based on a plurality of moving image data, similarly to the health condition evaluation device 10 described above. Also, in this case, the imaging range of the moving image data is not limited to the vicinity of the mouth, but is, for example, the upper half of the body. In this manner, the imaging range is appropriately changed according to the target site.

[others]
The block diagrams used in the description of the above embodiments show blocks for each function. These functional blocks (components) are implemented by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be implemented using one device physically or logically coupled, or directly or indirectly using two or more physically or logically separated devices (e.g. , wired, wireless, etc.) and may be implemented using these multiple devices. A functional block may be implemented by combining software in the one device or the plurality of devices. Also, the term "apparatus" described in this embodiment can be read as a circuit, a device, a unit, or the like.

Functions include judging, determining, determining, calculating, calculating, processing, deriving, examining, searching, checking, receiving, transmitting, outputting, accessing, resolving, selecting, choosing, establishing, comparing, assuming, expecting, assuming, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc. can't For example, a functional block (component) that makes transmission work is called a transmitting unit or a transmitter. In either case, as described above, the implementation method is not particularly limited.

The processing procedures, sequences, flowcharts, etc. of each aspect/embodiment described in this disclosure may be rearranged as long as there is no contradiction. For example, the methods described in this disclosure present elements of the various steps using a sample order, and are not limited to the specific order presented.

Input/output information and the like may be stored in a specific location (for example, memory), or may be managed using a management table. Input/output information and the like can be overwritten, updated, or appended. The output information and the like may be deleted. The entered information and the like may be transmitted to another device.

The determination may be made by a value represented by one bit (0 or 1), by a true/false value (Boolean: true or false), or by numerical comparison (for example, a predetermined value).

Each aspect/embodiment described in the present disclosure may be used alone, may be used in combination, or may be used by switching according to execution. In addition, the notification of predetermined information (for example, notification of “being X”) is not limited to being performed explicitly, but may be performed implicitly (for example, not notifying the predetermined information). good too.

Software, whether referred to as software, firmware, middleware, microcode, hardware description language or otherwise, includes instructions, instruction sets, code, code segments, program code, programs, subprograms, and software modules. , applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.

Software, instructions, information, etc. may also be sent and received over a transmission medium. For example, the software uses wired technology (coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), etc.) and/or wireless technology (infrared, microwave, etc.) to access websites, Wired and/or wireless technologies are included within the definition of transmission medium when sent from a server or other remote source.

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

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

As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Judgement", "determination" are, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiry (eg, lookup in a table, database, or other data structure); Also, “judgment” and “determination” are used to refer to receiving (e.g., receiving information), transmitting (e.g., transmitting information), input, output, access (Accessing) (for example, accessing data in memory) may include deeming that a "judgment" or "decision" has been made. In addition, "judgment" and "decision" refer to resolving, selecting, choosing, establishing, comparing, etc. as "judgment" and "decision". can contain. In other words, "judgment" and "decision" may include considering that some action is "judgment" and "decision". Also, "judgment (decision)" may be read as "assuming", "expecting", "considering", or the like.

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

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

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

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

In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean that "A and B are different from C". Terms such as "separate," "coupled," etc. may also be interpreted in the same manner as "different."

[Appendix]
A health condition evaluation apparatus according to one aspect includes a moving image data acquisition unit that acquires a plurality of moving image data obtained by capturing different motions related to a target part of a subject whose health condition is to be evaluated, and the plurality of moving image data. a state score calculation unit that calculates one or more state scores indicating the state of motion from each of the above, a region-specific score calculation unit that calculates a region-specific score related to the health state of the target region based on the state score, have

According to the above-described health condition evaluation device, one or more condition scores indicating the condition of a motion are calculated from each of a plurality of video data obtained by imaging different motions, and based on these condition scores, the health condition of the target part is evaluated. A site-specific score relating to the state is calculated. In this way, since the site-specific score indicating the health condition of each site is calculated from a plurality of video data obtained by capturing different motions, the health of the target site can be improved compared to the case of focusing on the specific motion of the site. The condition can be evaluated in a more multifaceted manner.

The condition score calculation unit calculates a plurality of types of condition scores from each of the plurality of video data, and the site-specific score calculation unit calculates the plurality of types of condition scores obtained from each of the plurality of video data. Based on this, the site-specific score may be calculated.

With the above configuration, a plurality of state scores can be obtained from video data obtained by imaging one action, so that one action can be evaluated using more state scores. Therefore, the health condition of the target part can be evaluated more accurately.

The moving image data is data in which motions related to a plurality of target parts are imaged, and the part-specific score calculation unit calculates, for each target part, part of the condition scores related to the target part. Based on this, the site-specific score may be calculated.

With the above configuration, it is possible to calculate the site-specific score for a plurality of target sites of the subject. In addition, since these target parts are parts related to the same motion, they are strongly related to each other. It is also possible to make a more detailed evaluation considering the difference in the score for each part of the body.

The site-specific score calculation unit may calculate an overall score from the site-specific scores relating to the plurality of target sites.

With the above configuration, it is possible to obtain more comprehensive information on the health condition of a body part including a plurality of target parts of the subject, and to grasp the tendency of the health condition not limited to a specific part.

The moving image data includes moving image data obtained by capturing an utterance action, and the state score calculating unit calculates a first state score obtained from voice information included in the moving image data, a second state score obtained from image information, may be calculated.

With the above configuration, two state scores can be obtained from the moving image data using the audio information and the image information, and more detailed information can be obtained for the moving image data based on the utterance action.

DESCRIPTION OF SYMBOLS 1... Health condition evaluation system 10... Health condition evaluation apparatus 11... Video data acquisition part 12... Condition detection part 13... Condition score calculation part 14... Part-specific score calculation part 15... Result output part 16... Related information holding part.

Claims (5)

a moving image data acquisition unit that acquires a plurality of moving image data obtained by capturing different motions related to a target part of a subject whose health condition is to be evaluated;
a state score calculation unit that calculates one or more state scores indicating a state of motion from each of the plurality of moving image data;
a region-specific score calculation unit that calculates a region-specific score related to the health condition of the target region based on the state score;
A health condition evaluation device. The state score calculation unit calculates a plurality of types of state scores from each of the plurality of moving image data,
2. The health condition evaluation device according to claim 1, wherein said site-specific score calculation unit calculates said site-specific score based on a plurality of types of condition scores obtained from each of said plurality of moving image data. The moving image data is data obtained by capturing motions related to a plurality of target parts,
3. The part-specific score calculation unit according to claim 1, wherein the part-specific score calculation unit calculates the part-specific score for each target part based on a part of the condition scores related to the target part. Health condition assessment device. 4. The health condition evaluation device according to claim 3, wherein the part-specific score calculation unit calculates an overall score from the part-specific scores of the plurality of target parts. The moving image data includes moving image data related to vocalization,
The state score calculator according to any one of claims 1 to 4, wherein the state score calculation unit calculates a first state score obtained from audio information included in the moving image data and a second state score obtained from image information. The health condition assessment device described.

Images