Subject evaluation device and subject evaluation system

Abstract

Provided are a subject evaluation device and a subject evaluation system that can perform processing suitable for various sensors in various places according to the needs of the places. A subject evaluation device (1) that evaluates a state of a subject (3) is characterized by having: one or more sensors (2) that measure the state of the subject (3); an acquisition section that acquires subject information and feature information of the subject (3) via the sensors (2); a conversion section that converts a subject information image into an evaluation target image on a two-dimensional plane according to the feature information of the sensors (2); a reference database that stores a correlation between a past evaluation target image obtained by performing image conversion in advance and reference information associated with the past evaluation target image; an evaluation section that generates an evaluation result for the evaluation target image with reference to the reference database; and an output section that outputs the evaluation result.

Description

TECHNICAL FIELD

[0001] The present application relates to a subject evaluation device and a subject evaluation system that evaluate a state of a subject. BACKGROUND

[0002] In the past, as a device that assists in evaluation of actions directed at a subject, for example, there has been proposed the determination device of Patent Literature 1.

[0003] The moving image processing device disclosed in Patent Literature 1 has an acquisition section that acquires moving image data of a subject in a living room, an analysis section that analyzes the moving image data acquired by the acquisition section to extract first information related to a person including the subject and second information related to an article in the living room, and a label addition processing section that, in order to assist in evaluation of a prescribed action directed at the subject, associates a plurality of labels related to the first information and the second information extracted by the analysis section with the moving image data, and the moving image processing device efficiently assists in evaluation of the prescribed action directed at the evaluation subject.

[0004] PRIOR ART DOCUMENTS

[0005] PATENT LITERATURE

[0006] Patent Literature 1: Japanese Patent Application Publication No. 2023-001531 SUMMARY

[0007] PROBLEMS TO BE SOLVED BY THE INVENTION

[0008] Here, in the moving image processing device like that of Patent Literature 1, for example, only analysis of the moving image data taken by the near-infrared camera in the living room is assumed. Therefore, it is difficult to perform processing suitable for a variety of sensors in various places according to the needs of the site in addition to the near-infrared camera.

[0009] Therefore, the present application is proposed in view of the above-described problems, and aims to provide a subject evaluation device and a subject evaluation system that can perform processing suitable for a variety of sensors in various places according to the needs of the site.

[0010] MEANS FOR SOLVING THE PROBLEMS

[0011] The subject person evaluation device of the first invention evaluates a state of a subject person, characterized by comprising: one or more sensors that measure a state of the subject person; an acquisition unit that acquires subject person information that shows at least any one of a physical condition and an action of the subject person and characteristic information that shows a characteristic of the sensor via the sensor; a conversion unit that converts the acquired subject person information into an evaluation target image on a two-dimensional plane according to the characteristic information of the sensor; a reference database that stores a correlation between a past evaluation target image obtained by performing image conversion in advance and reference information associated with the past evaluation target image; an evaluation unit that generates an evaluation result for the evaluation target image with reference to the reference database; and an output unit that outputs the evaluation result.

[0012] The subject person evaluation device of the second invention is characterized in that, in the first invention, the correlation is constructed by mechanical learning using the past evaluation target image and the reference information as learning data.

[0013] The subject person evaluation device of the third invention is characterized in that, in the first invention or the second invention, the subject person evaluation device further comprises an update unit that reflects a relationship between the past evaluation target image and the reference information into the correlation when the relationship is newly acquired.

[0014] The subject person evaluation system of the fourth invention evaluates a state of a subject person, characterized by comprising: one or more sensors that measure a state of the subject person; an acquisition unit that acquires subject person information that shows at least any one of a physical condition and an action of the subject person and characteristic information that shows a characteristic of the sensor via the sensor; a conversion unit that converts the acquired subject person information into an evaluation target image on a two-dimensional plane according to the characteristic information of the sensor; a reference database that stores a correlation between a past evaluation target image obtained by performing image conversion in advance and reference information associated with the past evaluation target image; an evaluation unit that generates an evaluation result for the evaluation target image with reference to the reference database; and an output unit that outputs the evaluation result.

[0015] Effects of the Invention

[0016] According to the first to third inventions, the acquisition unit acquires subject person information and characteristic information from one or more sensors that measure a state of a subject person. Therefore, it is possible to acquire subject person information that shows at least any one of a physical condition and an action of the subject person and characteristic information that shows a characteristic of the sensor via a plurality of sensors. Thus, it is possible to perform processing suitable for a variety of sensors at various sites according to the needs of the sites.

[0017] Further, according to the first to third inventions, the conversion section converts the acquired subject information image into an evaluation target image on a two-dimensional plane in accordance with the characteristic information of the sensor. Therefore, it is possible to generate an evaluation result for the evaluation target image with reference to the reference database. Thus, it is possible to perform processing suitable for various sensors at various sites in accordance with the needs of the sites.

[0018] In particular, according to the second invention, the correlation is constructed by using machine learning using past evaluation target images and reference information as learning data. Therefore, even in the case of evaluating an unknown evaluation target image different from the past evaluation target images, it is possible to perform quantitative evaluation. Thus, it is possible to perform processing suitable for various sensors at various sites in accordance with the needs of the sites.

[0019] In particular, according to the third invention, the update section reflects the relationship between the evaluation target image and the reference information into the correlation in the case where the relationship is newly acquired. Therefore, even in the case of evaluating a new evaluation target image different from the past evaluation target images, it is possible to perform quantitative evaluation. Thus, it is possible to achieve further improvement of evaluation accuracy, and it is possible to perform processing suitable for various sensors at various sites in accordance with the needs of the sites.

[0020] According to the fourth invention, the evaluation unit generates an evaluation result for the evaluation target image with reference to the reference database. The reference information includes body information. Therefore, it is possible to generate an evaluation result based on the result of the state of the past evaluation target. Thus, it is possible to improve the accuracy of the state of the evaluation target, and it is possible to perform processing suitable for various sensors at various sites in accordance with the needs of the sites. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 is a schematic view showing an example of a subject evaluation system of the present embodiment.

[0022] Figure 2 (a) of FIG. 1 is a schematic view showing an example of the operation of a site A of a subject evaluation device of the present embodiment. Figure 2 (b) of FIG. 1 is a schematic view showing an example of the operation of a site B of a subject evaluation device of the present embodiment.

[0023] Figure 3 (a) of FIG. 2 is a schematic view showing an example of sensor data of a subject evaluation system of the present embodiment. Figure 3 (b) of FIG. 2 is a schematic view showing an example of an evaluation target image of a subject evaluation system of the present embodiment.

[0024] Figure 4(a) is a schematic diagram showing an example of the structure of the subject evaluator of the present embodiment, Figure 4 (b) is a schematic diagram showing an example of the function of the subject evaluator of the present embodiment.

[0025] Figure 5 is a schematic diagram showing an example of the reference database of the present embodiment.

[0026] Figure 6 is a flowchart showing an example of the action of the subject evaluation system of the present embodiment. DETAILED DESCRIPTION

[0027] Hereinafter, an example of a subject evaluation system and a subject evaluator to which the present embodiment is applied will be described with reference to the drawings.

[0028] Reference Figure 1 An example of the subject evaluation system 100 and the subject evaluator 1 of the present embodiment will be described.

[0029] For example, as shown in Figure 1 , the subject evaluation system 100 of the present embodiment has the subject evaluator 1. The subject evaluator 1 can be connected to other terminals 5 and servers 6 via, for example, a communication network 4, in addition to being connected to sensors 2 (2a to 2f), for example.

[0030] The subject evaluation system 100 evaluates the state of the subject 3. The subject evaluation system 100 can be used for evaluation performed after diagnosis or observation of the subject 3 at a place A (for example, medical examination or treatment performed by a doctor or the like in a nursing facility, observation performed by a caregiver or the like in home nursing), for example.

[0031] Further, the subject evaluation system 100 can also perform evaluation in scenarios other than medical care and nursing, and can be used for evaluation of the state of the subject 3 at the time of work in various scenarios such as transfer of the subject 3, eating, bathing, medication, toilet, rehabilitation, vital sign examination, sputum suction, respiratory assistance, drip infusion, blood transfusion, and distribution work at a logistics site, assembly work at a manufacturing site, business work at a sales site, and the like, for example.

[0032] Furthermore, the subject evaluation system 100 can also evaluate the future state from the current state of the subject 3. The subject evaluation system 100 can be used for evaluation such as evaluation of "state recovery, so there is no problem with home nursing" from evaluation performed after diagnosis of the subject 3 in a nursing facility, or evaluation of "nursing is required in a nursing facility" from evaluation performed after observation of the subject 3 in home nursing, for example.

[0033] Here, reference Figure 2An example of the actions of the evaluation device 1 at location A will be explained. First, in Figure 2 (a) shows an example of the action of the object evaluation device 1, for example, with place A (bedroom) as the object. Figure 2 As shown in (a), the subject evaluation device 1 uses, for example, one or more sensors 2 (2a to 2f) to measure the state of the subject 3 when he / she is asleep to measure data related to the state of the subject 3 when he / she is asleep.

[0034] In sensor 2, for example, sensor 2a is a motion sensor that measures and quantifies the movements of the subject 3. Similarly, sensor 2b is a near-infrared or non-contact vital signs sensor that measures and quantifies the body temperature or vital signs of the subject 3. Furthermore, sensor 2c is a near-infrared or non-contact vital signs sensor that measures and quantifies the posture or center of gravity of the subject 3. Additionally, sensor 2c may be mounted on a bed leg or similar location, and its measurement and quantification may be based on the subject 3's body orientation, posture, and center of gravity.

[0035] The subject evaluation device 1 acquires various measurement data measured by each sensor 2 (2a-2c). For example, when acquiring the various measurement data measured by each sensor 2 (2a-2c), the subject evaluation device 1 also acquires characteristic information showing the characteristics of each sensor (e.g., sensor ID, measurement data ID, measurement data characteristics, measurement date and time, measurement location, etc.). For example, the subject evaluation device 1 can pre-set acquisition conditions such as the date and time to be sent to the subject evaluation device 1 and the measurement data to be sent for each sensor 2 (2a-2c), and each sensor 2 sends data to the subject evaluation device 1 according to the set acquisition conditions.

[0036] Next, in Figure 2 (b) shows an example of the action of the object evaluation device 1, for example, in place B (living room). Figure 2 As shown in (b), for example, for the action state of subject 3 getting up and moving from place A, subject evaluation device 1 uses one or more sensors 2 (2e to 2f) to measure data related to the action state of subject 3.

[0037] In sensor 2, for example, sensor 2e is a motion sensor that measures and quantifies the actions of the subject 3. Furthermore, for example, sensor 2f is a wearable sensor worn by the subject 3, which measures and quantifies the subject 3's steps, hand and foot movements, heart rate, respiratory rate, etc.

[0038] Figure 2 The sensors 2 (2a to 2f) indicated by (a) and (b) can be provided in multiple numbers in a facility or in a home, for example. As to the installation site, it can be installed at a ceiling, a wall, a table, a bed, a chair, a wheelchair, a car, or the like, or can be worn on the body by an evaluator, for example. In the case where the installation site is a bathroom, for example, the acquisition of image data of the state of the body of the subject 3 can not be performed, and sensor data can be acquired by a near-infrared camera or the like. Thus, the state of the subject 3 can be acquired by various sensors in various places and the like according to the situation or the needs of the situation.

[0039] The subject evaluator 1 acquires various measurement data measured by the respective sensors 2 (2e to 2f). The subject evaluator 1 acquires, for example, characteristic information (for example, a sensor ID, a measurement data ID, a measurement data characteristic, a measurement date and time, a measurement site, and the like) indicating the characteristics of the respective sensors at the same time as the acquisition of the various measurement data measured by the respective sensors 2 (2e to 2f). The subject evaluator 1 can set, for example, a date and time of transmission to the subject evaluator 1, measurement data to be transmitted, and the like as acquisition conditions for the respective sensors 2 (2e to 2f) in advance, and the respective sensors 2 transmit to the subject evaluator 1 according to the set acquisition conditions.

[0040] The subject evaluator 1 acquires subject information indicating at least any one of the physical condition and the action of the subject 3 via the sensors 2 and characteristic information indicating the characteristics of the sensors 2, and converts the acquired subject information image into an evaluation target image on a two-dimensional plane according to the characteristic information of the sensors.

[0041] The subject evaluation system 100 generates an evaluation result for the evaluation target image with reference to a reference database that stores the correlation between past evaluation target images obtained by image conversion in advance and reference information associated with the past evaluation target images, for example. Thus, the state of the subject 3 can be evaluated using the evaluation target image of the subject 3 at present. A plurality of evaluation target images can be combined and evaluated, for example. Various states of the subject 3 or the prediction of future occurrence can be confirmed from among a plurality of evaluation target images according to the combination of evaluation target images having characteristics, for example.

[0042] The subject evaluation system 100 has an output unit that outputs the evaluation result, and generates an evaluation result for the evaluation target image with reference to a reference database described later after acquiring the evaluation target information including the measurement data. The subject evaluator 1 outputs the generated evaluation result to the display unit 109 or the like.

[0043] The evaluation result shows, in addition to the state of the present situation of the subject 3 as an evaluation object, a prediction result of an unconfirmed state that can occur or develop in the future, and the like. With respect to the evaluation result, in addition to an evaluation result of a state related to the body or action of the subject 3 such as "normal", "abnormal", "observation required", and the like, for example, a tendency of a case, a disease, care required, and the like that can occur in the subject 3, or a state, a disease, care required, and the like that can develop in the future with a probability can be shown such as "has a tendency of having an OO symptom", "the possibility of an OO symptom is 60%" and the like. Thereby, for example, a caregiver of the subject 3 can make preparations for the care and nursing of the subject 3 in the future and the like by confirming these evaluation results.

[0044] As the subject evaluation device 1, in addition to using an electronic device such as a personal computer (PC) and the like, an electronic device such as a smartphone, a tablet terminal, a wearable terminal, an IoT (Internet of Things) device, a single board computer such as Raspberry Pi (registered trademark), and the like can be used, and a sensor 2 can be built in, for example. For example, in a case where an HMD (Head Mounted Display) in which the sensor 2 is built in is used as the subject evaluation device 1, an evaluator or the like can recognize the evaluation result of the subject 3 by visually confirming the subject 3 through the display. Therefore, it is possible to reduce the degree of difficulty of the physical evaluation work for the subject 3, and it is also possible to shorten the evaluation work time.

[0045] Here, with reference to Figure 3 , an example of the sensor data of the subject evaluation system 100 of the present embodiment will be described. Figure 3 (a) of FIG. 1 is an example of the sensor data of the subject evaluation system 100 of the present embodiment, and various sensor data measured by the plurality of sensors 2 is acquired by the subject evaluation device 1.

[0046] As the sensor data measured by the various sensors 2, for example, the sensor 2a measures the state of the subject 3 (for example, action information in bed, and the like) and records as the sensor data 200a. For example, the coordinates and values of actions of each position or action showing the position of the head (XX.XX), the position of the right shoulder (XX.XX), the position of the left shoulder (XX.XX), the position of the right upper arm (XX.XX), the position of the left upper arm (XX.XX), and the like of the subject 3 are measured in time series as the sensor data 200a, and the plurality of sensor data 200a measured is recorded.

[0047] The sensor 2a measures and digitizes the action of the subject 3, for example, using a known motion sensor or the like. The measurement of the sensor data 200a can be performed using a near-infrared sensor, an image sensor, or the like (not shown), in addition to using a known motion sensor, for example, using a known measurement technique.

[0048] The sensor data 200a measured by the sensor 2a is acquired by the subject evaluation device 1, for example, and is recorded in the subject evaluation device 1 as a plurality of pieces of sensor data 200a, in addition to which it can be recorded in the other terminal 5 or the server 6 or the like, for example.

[0049] Also, the sensor 2b measures the state of the subject 3 (for example, vital information in bed, and the like) and records it as the sensor data 201a. For example, the values of the individual vital information of the body temperature (35.50), the respiratory rate (18.00), the blood pressure value High (130.00), the blood pressure value Low (85.00), the pulse rate (70.00), and the like of the subject 3 are measured in time series as the sensor data 201a, and a plurality of pieces of the measured sensor data 201a are recorded.

[0050] The sensor 2b measures and digitizes the vital information of the subject 3, for example, using a known near-infrared or non-contact vital sensor or the like. The measurement of the sensor data 201a can be performed using various image sensors or the like (not shown), in addition to using a known vital sensor, for example, using a known measurement technique.

[0051] The sensor data 201a measured by the sensor 2b is acquired by the subject evaluation device 1, for example, and is recorded in the subject evaluation device 1 as a plurality of pieces of sensor data 201a, in addition to which it can be recorded in the other terminal 5 or the server 6 or the like, for example.

[0052] In addition to the sensor data 200a of the sensor 2a and the sensor data 201a of the sensor 2b, the individual sensor data of the other sensors 2c to 2f is measured, and a plurality of pieces of the individual sensor data are recorded in the subject evaluation device 1, in addition to which it can be recorded in the other terminal 5 or the server 6 or the like, for example.

[0053] Also, Figure 3 (b) is an example of the evaluation target image of the subject evaluation system 100 of the present embodiment, and the various sensor data measured by the sensors 2 is image-converted into the evaluation target images 200b to 202b on a two-dimensional plane in accordance with the characteristic information (model, model, conversion parameter, performance and characteristics, visualization characteristics, format, and the like) of the individual sensors 2.

[0054] The evaluation target image 200b is obtained by, for example, converting the sensor data 200a image into an evaluation target image 200b on a two-dimensional plane in accordance with the characteristic information of the sensor 2a. The image conversion is, for example, a known charting process or the like, and shows a state in which the sensor data measured in a time series is charted in accordance with a certain specific parameter or the like.

[0055] The evaluation target image 200b is obtained by, for example, converting the sensor data 200a image into an evaluation target image 200b on a two-dimensional plane in accordance with the characteristic information of the sensor 2a. The image conversion is, for example, a known charting process or the like, and shows a state in which the sensor data measured in a time series is charted in accordance with a certain specific parameter or the like.

[0056] Similarly, the evaluation target image 201b is obtained by, for example, converting the sensor data 201a into an evaluation target image 201b on a two-dimensional plane in accordance with the characteristic information of the sensor 2b, for example, converting the changes in each vital sign information in a time series into an evaluation target image 201b on a two-dimensional plane.

[0057] Further, the evaluation target image 202b can be obtained by, for example, converting the sensor data measured by the other sensor 2 into an evaluation target image 202b on a two-dimensional plane in accordance with the characteristic information of the sensor 2. Alternatively, it can be obtained by, for example, aggregating each value measured by the plurality of sensors 2 and converting the proportion or the like into an evaluation target image 201b on a two-dimensional plane.

[0058] With respect to the evaluation target image shown in (b) of Figure 3 The evaluation target image shown in (b) of

[0059] The subject evaluator system 100 displays the evaluation target images 200b to 202b, the plurality of two-dimensional planes on which the other images are converted, on the display section 109. For example, in a case where a plurality of sensor data is measured using one sensor 2, the subject evaluator 1 can generate evaluation results for the subject 3 respectively, and can display the evaluation results for the subject 3 on the display section 109. Further, for example, in a case where one evaluation result for the subject 3 is generated, it can be based on a plurality of sensor data. Further, for example, the category or the number of the plurality of evaluation target images which are combined and displayed is arbitrary.

[0060] The sensor data can be generated using, for example, an RGB camera or the like. The sensor data can be generated using, for example, a multispectral camera in which an arbitrary wavelength is selected, for example, can be generated based on imaging via a polarizing filter. The sensor data can be extracted from a part of a moving image and converted into an evaluation target image by image conversion.

[0061] Regarding the object information, it can be directly input into the object evaluation device 1 by an evaluator or the like, for example, by associating it with sensor data acquired by the object evaluation device 1. Alternatively, multiple object information entries can be pre-stored in the object evaluation device 1, and the object evaluation device 1 can select one based on the image of the object being evaluated. When the object evaluation device 1 selects the object information, for example, a learning model pre-stored in the object evaluation device 1 can be used to select the object and sensor 2 based on the acquired image of the object being evaluated. In this case, the learning model is generated using known machine learning methods that use pre-prepared images of the object being evaluated and the object information as learning data.

[0062] The subject information includes information related to at least one of the following: the date and time of observation of the subject 3 as measured by sensor data, posture and movement, the observer, and the predetermined date and time of observation of the subject 3. For example, the subject information may include information related to the subject 3's physical strength, training, diet, and other aspects of daily life.

[0063] Regarding the information about the subject, for example, it can be directly input into the subject evaluation device 1 by the evaluator or the like in a way that is associated with the sensor data obtained by the subject evaluation device 1. Alternatively, it can be sent from other terminals such as 5.

[0064] (Subject evaluation device 1)

[0065] Next, refer to Figure 4 An example of the subject evaluation device 1 of this embodiment will be described. Figure 4 (a) is a schematic diagram showing an example of the structure of the object evaluation device 1 according to this embodiment. Figure 4 (b) is a schematic diagram illustrating an example of the function of the object evaluation device 1 in this embodiment.

[0066] For example Figure 4 As shown in (a), the object evaluation device 1 includes a housing 10, a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a storage unit 104, and I / F units 105 to 107. Each of the structures 101 to 107 is connected via an internal bus 110.

[0067] The CPU 101 controls the entire object evaluator 1. The ROM 102 stores the operation codes of the CPU 101. The RAM 103 is a work area used when the CPU 101 operates. The storage section 104 stores various information such as the evaluation target image and the reference database. As the storage section 104, in addition to using, for example, an HDD (Hard Disk Drive), a data storage device such as an SSD (Solid State Drive) can also be used. Furthermore, for example, the object evaluator 1 can also have a GPU (Graphics Processing Unit) that is not illustrated. By having a GPU, high-speed arithmetic processing can be performed compared to usual.

[0068] The I / F 105 is an interface for transmitting and receiving various information with the sensor 2, and can also be an interface for transmitting and receiving various information with other terminals 5 or servers 6 and the like via a communication network 4 such as the Internet, for example.

[0069] The I / F 106 is an interface for transmitting and receiving information with the input section 108. As the input section 108, for example, a keyboard is used, and various information or control instructions of the object evaluator 1 and the like are input by an evaluator using the object evaluator 1 and the like via the input section 108.

[0070] The I / F 107 is an interface for transmitting and receiving various information with the display section 109. The display section 109 outputs various information such as the evaluation result stored in the storage section 104 or the processing status of the object evaluator 1 and the like. As the display section 109, a display is used, and can be, for example, a touch panel type.

[0071] <Reference Database>

[0072] In the reference database stored in the storage section 104, the correlation between the past evaluation target image and the reference information associated with the past evaluation target image that is acquired in advance is stored, and a learning model having the correlation, for example, is stored. In the reference database, the past evaluation target image and the reference information can also be stored, for example. For example, the past evaluation target image and the reference information are learned as a set of learning data, and the correlation is constructed by machine learning using a plurality of learning data. As the learning method, deep learning such as a convolutional neural network is used, for example.

[0073] In this case, the relevance, for example, indicates a degree of association between a plurality of data included in the past evaluation target image and a plurality of data included in the reference information. The relevance is appropriately updated in the process of machine learning. That is, the relevance, for example, shows a function that is optimized in accordance with the past evaluation target image (image data on a two-dimensional plane) and the reference information. Therefore, the evaluation result for the evaluation target image is generated using the relevance constructed from all results according to the state of the evaluator 3 in the past. Thus, even in a case where the physical condition or the action of the target person 3 is in various states, an optimal evaluation result can be generated.

[0074] Also, in addition to a case where the evaluation target image is the same as or similar to the past evaluation target image, an optimal evaluation result can be quantitatively generated in a case where it is not similar. Furthermore, by improving the generalization ability at the time of machine learning, the evaluation accuracy for an unknown evaluation target image can be improved.

[0075] Further, the relevance, for example, can have a plurality of degrees of association indicating a degree of association between a plurality of data included in the past evaluation target image and a plurality of data included in the reference information. For example, in a case where the learning model is constructed by a neural network, the degree of association can correspond to a weight variable.

[0076] The past evaluation target image shows information of the same kind as the above-described evaluation target image. The past evaluation target image, for example, includes a plurality of evaluation target images acquired when the evaluator 3 in the past evaluated.

[0077] The reference information is associated with the past evaluation target image and shows information related to the state of the target person 3. The reference information can include, in addition to showing an evaluation based on the state of the target person 3 (for example, "normal", "abnormal", "need to be observed", "have a tendency to have a symptom of ○○", "the possibility of a symptom of ○○ is 60%", and the like), physical information, coping information, preparation information, prediction information, and the like related to a cause of the state of the target person 3.

[0078] The reference information, for example, can also show a tendency of a case, a disease, a care required, and the like that the target person 3 can have, or show a disease state, a disease, a care required, and the like that can occur in the future with a probability. In addition, the specific content included in the reference information can be arbitrarily set.

[0079] Regarding the physical information, if it is an elderly person, for example, a name of a specific state of a cause such as dementia, a symptom of dehydration, a walking disorder, a mental and psychological disorder, a moving ability disorder, an excretion function disorder, a sensory disorder, a disorder of nutrient intake, and the like is shown. Various causes are generally associated with at least a part of the physical condition or the action of the target person 3.

[0080] For example, as Figure 5As shown, the correlation can indicate a degree of correlation between the past evaluation target image and the reference information. In this case, by using the correlation, it is possible to store each of a plurality of data (in the present embodiment, "image data A" to "image data C") included in the past evaluation target image and a degree of correlation of each of a plurality of data (in the present embodiment, "reference A" to "reference C") included in the reference information. Therefore, for example, it is possible to correlate one data included in the past evaluation target image and a plurality of data included in the reference information via the correlation, and it is possible to generate a variety of evaluation results. Figure 5 Figure 5

[0081] Further, the correlation has, for example, a plurality of degrees of correlation that respectively correlate a plurality of data included in the past evaluation target image and a plurality of data included in the reference information. The degree of correlation is expressed, for example, by three or more stages such as a percentage, 10 stages, or 5 stages, or is expressed, for example, by a characteristic of a line (such as thickness). For example, "image data A" included in the past evaluation target image shows a degree of correlation AA "85%" with "reference A" included in the reference information, and shows a degree of correlation AB "55%" with "reference B" included in the reference information. That is, the "degree of correlation" indicates a degree of correlation between each image data, and for example, the higher the degree of correlation, the stronger the correlation of each data. Further, when the correlation is constructed by the above-described machine learning, it can also be configured such that the correlation has a degree of correlation of three or more stages.

[0082] The past evaluation target image can be stored in the reference database by, for example, dividing the past image data A to C and the past physical condition information or the action information. In this case, the degree of correlation is calculated from a relationship between a combination of the past image data and the past physical condition information or the action information and the reference information. Further, the past evaluation target image can also be stored in the reference database by, for example, dividing the past observation information (various sensor data, etc.) in addition to the above.

[0083] Further, the past evaluation target image can also include synthetic data and a degree of similarity. The synthetic data is expressed by three or more stages of similarity between the past image data or the past physical condition information or the action information. The synthetic data can be stored in the reference database in the form of an image, a character string, etc. in addition to being stored in the form of a numerical value, a matrix, or a histogram, etc.

[0084] Figure 4 (b) is a schematic diagram showing an example of a function of the subject evaluation device 1. The subject evaluation device 1 has an acquisition unit 11, a conversion unit 12, an evaluation unit 13, and an output unit 14, and can also have an update unit 16. Further, the subject evaluation device 1 can also have a display unit 15. Figure 4 ​​Each function shown in (b) is realized by the CPU 101 executing a program stored in the storage section 104 or the like with the RAM 103 as a work area, and can be controlled by artificial intelligence, for example.

[0085] <Acquisition section 11>

[0086] The acquisition section 11 acquires subject information showing at least any one of the physical condition and the action of the subject 3 and characteristic information showing the characteristics of the sensor 2 via one or more sensors that measure the state of the subject 3. The acquisition section 11 can acquire image data of the subject 3, spatial image data of the place, or the like from the sensor 2, in addition to the sensor data showing the subject information of the subject 3 from the sensor 2 or the like, for example, in the case where a camera is built in. The acquisition section 11 acquires the characteristic information that identifies the sensor 2, in addition to the physical condition information and the action information of the subject 3 that are input in advance from the evaluator or the like.

[0087] The acquisition section 11 acquires the characteristic information of the sensor 2 together with the sensor data, for example, in the case of acquiring the sensor data. In addition, the frequency and the period of acquisition of the subject information and the characteristic information by the acquisition section 11 are arbitrary.

[0088] The acquisition section 11 receives various information including the sensor data and the characteristic information of the evaluator measured by the sensor 2. The acquisition section 11 can receive various information such as the physical condition information and the action information of the subject 3, the observation information, the environment information related to the place, and the like transmitted from the external terminal such as the other terminal 5 via the communication network 4 and the I / F 105, for example.

[0089] The acquisition section 11 can refer to the learning model stored in the storage section 104, for example, and select the physical condition information and the action information corresponding to the sensor 2, the sensor data, and the characteristic information, and acquire as the evaluation target image.

[0090] <Conversion section 12>

[0091] The conversion section 12 converts the subject information image acquired by the acquisition section 11 into an evaluation target image on a two-dimensional plane according to the characteristic information of the sensor 2. As shown in (b), the conversion section 12 converts the sensor data 200a image measured by the various sensors 2a, for example, into an evaluation target image 200b. The conversion section 12 converts the image into a graph such as a radar chart, for example, according to the sensor characteristic information of the sensor 2a or various information as characteristic information of the sensor data (such as the model, the model, the conversion parameter, the performance and the characteristics, the visualization characteristics, the format, and the like). Figure 3 Figure 3

[0092] ​​The conversion section 12 performs image conversion by charting, for example, based on the head position (XX.XX), right shoulder position (XX.XX), left shoulder position (XX.XX), right upper arm position (XX.XX), left upper arm position (XX.XX), and values of each item, which are items showing the state of the subject 3 acquired using the sensor 2a. The conversion section 12 can refer to a charting correspondence table (not shown) to chart the sensor data 200a measured by the sensor 2a, for example, and perform image conversion.

[0093] If the measured sensor data 200a has a characteristic in a local part, for example, the conversion section 12 can chart only the range of the local characteristic and the value. The conversion section 12 can chart the sensor data of the sensor 2 of the subject based on an instruction from another terminal 5, for example, and perform image conversion. The conversion section 12 performs the same image conversion for the sensor 2b and other sensors 2, for example. The conversion section 12 can combine the values measured by a plurality of sensors 2 to generate a new chart, and use the combined chart as an evaluation target image, for example.

[0094] Also, the conversion section 12 can chart the proportions or changes of each value measured by a plurality of sensors 2, for example, and perform image conversion. If the sensor data is measured in chronological order, for example, and there is a tendency for significant increase or decrease in a certain period, the conversion section 12 can chart the tendency and store the period, values, and parameters at the time of charting, various setting information, and the like. Thus, the evaluation target image can be confirmed by tracing the charted period, and image conversion processing suitable for a plurality of sensors can be performed in various places according to the needs of the site.

[0095] <Evaluation Section 13>

[0096] The evaluation section 13 refers to the reference database to generate an evaluation result for the evaluation target image. The evaluation section 13 selects the optimal reference information that is disassociated from the evaluation target image based on the relevance calculation, for example, using the evaluation target image as input data, and generates an evaluation result based on the optimal reference information.

[0097] The evaluation section 13 selects data (e.g., "image data A" as the first data) that is the same as or similar to the data included in the evaluation target image, for example, when referring to the reference database shown in FIG. 8. Figure 5 As the first data, in addition to selecting image data that is locally or completely identical to the evaluation target image, similar image data can be selected, for example. In the case where the evaluation target image is shown by numerical values in a matrix or the like, the range of values included in the first data to be selected can be set in advance.

[0098] The evaluation section 13 selects the reference information associated with the selected first data and the degree of association (first degree of association) between the selected first data and the reference information, and generates an evaluation result based on the selected reference information and the first degree of association. In addition, with respect to the first degree of association, it can be calculated by the evaluation section 13 in addition to being selected from the degrees of association constructed in advance.

[0099] For example, the evaluation section 13 selects the data "reference A" included in the reference information associated with the first data "image data A" and the first degree of association (degree of association AA) "85%" between "image data A" and "reference A". In addition, the reference information and the first degree of association can include a plurality of data. In this case, in addition to the above-described "reference A" and "85%", the reference information "reference B" associated with the first data "image data A" and the first degree of association (degree of association AB) "55%" between "image data A" and "reference B" can be selected, and an evaluation result can be generated based on "reference A" and "85%" and "reference B" and "55%".

[0100] The evaluation result can include the evaluation target image. The evaluation result can express, for example, a factor of the state (physical condition or action) of the subject 3 shown in probability using the reference information and the degree of association.

[0101] The evaluation section 13 generates an evaluation result that expresses a form (for example, a character string) that enables the evaluator or the like to understand the above-described selected reference information and the first degree of association or the like, using, for example, form data of an output format or the like stored in advance in the storage section 104 or the like. In addition, the setting of the form at the time of generating the evaluation result or the like can use, for example, a publicly known technique.

[0102] The evaluation section 13 determines the content of the evaluation result based on, for example, the selected first degree of association. For example, the evaluation section 13 can be set to generate an evaluation result based on the reference information associated with a first degree of association of "50%" or more, and not to reflect the reference information associated with a first degree of association of less than "50%" in the evaluation result. In addition, with respect to the determination criteria based on the first degree of association, for example, a threshold value or the like can be set in advance by the evaluator or the like, and the range of the threshold value or the like can be arbitrarily set. Furthermore, the evaluation section 13 can determine the content of the evaluation result based on, for example, a result obtained by calculating two or more first degrees of association, or a comparison of two or more first degrees of association.

[0103] <Output section 14>

[0104] The output section 14 outputs the evaluation result. The output section 14 transmits the evaluation result to, for example, the other terminal 5 or the like via the I / F 105 in addition to transmitting the evaluation result to the display section 109 via the I / F 107. The output section 14, for example, transmits the evaluation result to the other terminal 5 via the I / F 105, and the other terminal 5 displays the evaluation result on the display section 109. Figure 3The evaluation target image of the subject 3, the data of the optimal evaluation result, recommendation, and the like corresponding to the physical condition and the action of the subject 3 are output to the display section 109 and the like.

[0105] The output section can display, for example, physical information, coping information, preparation information, prediction information, and the like related to the cause of the current or future state of the subject 3, in addition to the result of the evaluation based on the state of the subject 3 (for example, "normal", "abnormal", "need to be observed", "tendency to have OO symptoms", "60% possibility of OO symptoms", and the like).

[0106] <Storage section 15>

[0107] The storage section 15 extracts various information saved in the storage section 104 as needed. The storage section 15 saves various information acquired or generated by each structure 11, 13 to 15 in the storage section 104.

[0108] <Update section 16>

[0109] The update section 16 reflects the relationship in the correlation, for example, in a case where the relationship between the past evaluation target image and the reference information is newly acquired. The update section 16 updates the correlation stored in the reference database according to the determination result, for example, in a case where the subject evaluation device 1 acquires a determination result of the accuracy of the evaluation result generated by the evaluation section 13 according to the evaluation result of the evaluator or the like.

[0110] <Display section 109>

[0111] The display section 109 displays the evaluation result. The display section 109 displays the evaluation target images 200b to 202b and the evaluation result, for example, as illustrated in Figure 3 The evaluation target images 200b to 202b are displayed according to the subject information acquired by the acquisition section 11 via the sensor 2 and the characteristic information showing the characteristics of the sensor 2, and the evaluation result, which is obtained by converting the subject information image into the evaluation target image on a two-dimensional plane according to the characteristic information of the sensor 2.

[0112] In addition, the display section 109 can display the evaluation result using only a list, a string, for example. The above-described display method can use a publicly known technology. In addition, for example, in a case where the HMD is used as the subject evaluation device 1, a transmissive display is used as the display section 109. At this time, the display section 109 can display the evaluation target image and the evaluation result with respect to the subject 3 who visually confirms the display section 109, for example.

[0113] <Update section 16>

[0114] The update section 16 updates, for example, the reference database. The update section 16 reflects the relationship between the past evaluation target image and the reference information in the correlation in a case where the relationship is newly acquired. For example, in a case where the subject evaluation device 1 acquires a determination result of the accuracy of the content of the evaluation result by the evaluator or the like based on the evaluation result generated by the evaluation section 13, the update section 16 updates the correlation included in the reference database based on the determination result.

[0115] <sensor 2>

[0116] The sensor 2 is a publicly known various sensor that measures the state of the physical condition and the action of the subject 3 and generates sensor data. As the sensor 2, for example, various sensors such as a motion sensor, a near-infrared camera, an RGB camera, an ultrasonic sensor, a discrimination part sensor, and the like are used, and a plurality of sensors can be used in cooperation at the same time or at different places. The sensor 2 can be built in the subject evaluation device 1, for example, or can be held or worn by the subject 3.

[0117] <communication network 4>

[0118] The communication network 4 is, for example, the Internet or the like that connects the subject evaluation device 1, the plurality of sensors 2, and the like via a communication circuit. The communication network 4 can be constituted by a so-called optical fiber communication network. Also, the communication network 4 can be realized by a publicly known communication network such as a wireless communication network in addition to a wired communication network.

[0119] <other terminal 5>

[0120] As the other terminal 5, for example, a device that is embodied by an electronic device is used similarly to the subject evaluation device 1. As the other terminal 5, for example, a central control device or the like that is capable of communicating with a plurality of subject evaluation devices 1 is shown. The other terminal 5 can be connected to a plurality of subject evaluation devices 1, for example, and can acquire the evaluation result generated by each subject evaluation device 1. Thereby, for example, the evaluation result of the subject 3 measured at a plurality of sites can be analyzed, and the improvement of the state of the body of the subject 3 or the like can be realized.

[0121] <server 6>

[0122] The server 6 stores, for example, various information described above. In the server 6, for example, various sensor data or various information related to the plurality of sensors 2 transmitted via the communication network 4 is stored. In the server 6, for example, the same information as the storage section 104 can be held, and various sensor data, various information related to the plurality of sensors 2, image data, evaluation results, and the like are transmitted and received with one or more subject evaluation devices 1 via the communication network 4. That is, the server 6 can be used instead of the storage section 104 by the subject evaluation device 1.

[0123] (Action of the subject evaluation system 100)

[0124] Next, an example of the action of the subject evaluation system 100 according to the present embodiment will be described. Figure 6 is a flowchart showing an example of the action of the subject evaluation system 100 according to the present embodiment.

[0125] <Acquisition unit S110>

[0126] As shown in Figure 6 , the subject image and the feature information are acquired (acquisition unit S110). The acquisition unit 11 acquires, for example, the subject information showing at least any one of the physical condition and the action of the subject 3 and the feature information showing the feature of the sensor 2 from one or more sensors 2 that measure the state of the subject 3 via the sensor 2. The acquisition unit 11 saves, for example, the evaluation target information and the feature information in the storage unit 104 via the storage unit 15.

[0127] The acquisition unit 11 acquires, for example, the subject information showing at least any one of the physical condition and the action of the subject 3 and the feature information showing the feature of the sensor 2. The acquisition unit 11 can be, for example, a plurality of sensors 2. As for the subject information and the feature information, they are input to the subject evaluation device 1 by the evaluator or the like in association with the image data or the like, and in addition thereto, for example, each information appropriate for the image data can be selected by the acquisition unit 11 from the image data. In this case, the acquisition unit 11 selects each information appropriate for the image data from a plurality of pieces of information (sensor data or the like) of the observed subject 3 that are previously saved in the storage unit 104.

[0128] For example, in a case where a plurality of sensors 2 are used to photograph one subject 3, the acquisition unit 11 acquires a plurality of pieces of sensor data (subject information) measured by the plurality of sensors 2 and the feature information as the conversion source data of one evaluation target image to be subjected to image conversion. The acquisition unit 11 can acquire the sensor data in accordance with the pattern of the life and the action of the subject 3 in addition to the sensor data (subject information and feature information) showing the state of the subject 3 in accordance with the pattern of the physical condition and the action of the evaluator.

[0129] The acquisition unit 11 can convert the image of the sensor data of the sensor 2 measured in an arbitrary period into the evaluation target image on the acquired two-dimensional plane in such a manner that it is received at a time. Further, in a case where the feature information of each sensor 2 has been previously acquired by the subject evaluation device 1 and is not changed, only the sensor data of the subject information can be acquired from the sensor 2. In this case, the subject evaluation device 1 can identify the sensor data acquired from the sensor 2 and additionally acquire the feature information of the sensor 2 in association with the sensor data.

[0130] <Conversion unit S120>

[0131] Next, the conversion unit 12 image-converts the evaluation target image on a two-dimensional plane (conversion unit S120). The conversion unit 12, for example, image-converts the subject information (sensor data) of the subject 3 acquired by the acquisition unit 11 via the sensor 2 into an evaluation target image that is visualized as a graph on a two-dimensional plane, in accordance with the characteristic information of the corresponding sensor 2. The conversion unit 12, for example, image-converts the subject information acquired by the acquisition unit 11 into a graph and the like as an evaluation target image on a two-dimensional plane, in accordance with the characteristic information of a plurality of sensors 2.

[0132] In addition, the conversion unit 12 image-converts into a graph as a subject image on a two-dimensional plane, but can also be converted into an image other than a graph, for example. The evaluation target image image-converted by the conversion unit 12 is an image that two-dimensionally visualizes the state of the subject 3, and the type, scale, number, and expression of the graph are arbitrary.

[0133] <Evaluation unit S130>

[0134] Next, the evaluation unit 13 image-converts the evaluation target image on a two-dimensional plane with reference to the reference database (evaluation unit S130). The evaluation unit 13 acquires the evaluation target image acquired by the acquisition unit 11, for example, from the reference database stored in the storage unit 104. The evaluation unit 13, for example, selects the optimal reference information that is disassociated with the solution calculated in accordance with the correlation indicated by a function or the like, using the evaluation target image as input data, and generates an evaluation result based on the optimal reference information. At this time, the evaluation unit 13 can select a plurality of reference information for one evaluation target image, for example.

[0135] The evaluation unit 13 can generate one evaluation result for a plurality of evaluation target images, in addition to generating one evaluation result for one evaluation target image, for example. The evaluation unit 13 generates an evaluation result using the form data in the output format stored in the storage unit 104, for example. The evaluation unit 13 stores the evaluation result in the storage unit 104 via the storage unit 15, for example.

[0136] <Output unit S140>

[0137] Next, the output unit 14 outputs the evaluation result (output unit S140). The output unit 14 outputs the evaluation result to the display unit 109 or the like. The output unit 14 can also output to another terminal 5 or server 6 via the communication network 4, for example.

[0138] The output section 14 can output, for example, information for causing the display section 109 to display the following to the display section 109: the subject 3 based on the image data; the sensor 2 capable of measuring the subject information of the subject 3; a display image reflecting the sensor data measured by the sensor 2, the sensed condition and the sensed result of the sensor 2, and the plurality of evaluation target images, the evaluation result of the subject 3 based on the combination of the evaluation target images, the recommendation information based on the evaluation result, and the like; a designation section (not shown) that designates the subject 3 as the evaluation target in the display image; and the evaluation result for the subject 3 that becomes the evaluation target via the designation section. Thereby, the display image, the designation section, and the evaluation result are displayed on the display section 109.

[0139] Thereby, the operation of the subject evaluation system 100 of the present embodiment ends. Furthermore, the timing at which the update section 16 implements the update is arbitrary.

[0140] According to the present embodiment, the evaluation section 13 refers to the reference database to generate the evaluation result for the evaluation target image. The reference information contains various physical information and action information of the subject 3. Therefore, it is possible to generate the evaluation result based on the result of the past evaluation of the state of the subject 3. Thereby, it is possible to improve the accuracy of the state of the subject 3, and it is possible to perform the processing suitable for a variety of sensors at various sites according to the needs of the site.

[0141] Also, according to the present embodiment, the evaluation target image contains the physical condition information. Therefore, it is possible to implement the evaluation based on the characteristics of the state factor that differs depending on the sensor 2 and the physical condition of the subject 3. Thereby, it is possible to further improve the accuracy of the state of the subject 3, and it is possible to perform the processing suitable for a variety of sensors at various sites according to the needs of the site.

[0142] Also, according to the present embodiment, the evaluation target image contains the action information. Therefore, it is possible to implement the evaluation based on the surface posture of the subject 3 that differs depending on the sensor 2 and the measurement condition of the subject 3. Thereby, it is possible to further improve the accuracy of the state of the subject 3, and it is possible to perform the processing suitable for a variety of sensors at various sites according to the needs of the site.

[0143] Also, according to the present embodiment, it is possible to obtain the evaluation result associated with the kind of the sensor 2 of the subject 3, the specification of the sensor 2, and the condition of the arrangement, and therefore it is possible to determine the condition that is a factor of the abnormality of the body of the subject 3, and grasp the body change accompanying the change of the observation condition, and the like. Thereby, it is possible to implement the body improvement of the subject 3 and the reduction of the nursing burden, and the like.

[0144] Further, according to the present embodiment, the evaluation target image contains feature information. Therefore, evaluation based on a measured feature of a cause that differs depending on the type, characteristics, number, arrangement of the sensor 2 can be implemented. Thereby, the accuracy of the state of the evaluation target person 3 can be further improved, and processing suitable for various sensors can be performed at various sites according to the needs of the site.

[0145] Further, according to the present embodiment, the relevance is constructed by using machine learning that uses past evaluation target images and reference information as learning data. Therefore, even in a case where an unknown evaluation target image that is different from the past evaluation target images is evaluated, quantitative evaluation can be implemented. Thereby, further improvement of the evaluation accuracy can be implemented.

[0146] Further, according to the present embodiment, the update unit 16 reflects the relationship between the past evaluation target image and the reference information into the relevance in a case where the relationship is newly acquired. Therefore, the relevance can be easily updated, and continuous improvement of the evaluation accuracy can be implemented.

[0147] Further, according to the present embodiment, the evaluation unit S130 refers to the reference database to generate an evaluation result for the evaluation target image. The reference information contains information related to the body. Therefore, an evaluation result based on the result of the state of the past evaluation target person 3 can be generated. Thereby, the accuracy of the state of the evaluation target person 3 can be improved.

[0148] The embodiments of the present application have been described, but the embodiments are suggested as examples, and are not intended to limit the scope of the application. These new embodiments can be implemented in other various ways, and various omissions, substitutions, changes can be made within the scope of the gist of the application. These embodiments and modifications thereof are included in the scope and gist of the application, and are included in the scope of the application and equivalents thereof recited in the claims.

[0149] Explanation of Reference Signs

[0150] 1: subject evaluation device; 2: sensor; 2a-2f: sensor; 3: subject; 4: communication network; 5: other terminal; 6: server; 10: housing; 11: acquisition section; 12: conversion section; 13: evaluation section; 14: output section; 15: storage section; 16: update section; 100: subject evaluation system; 101: CPU; 102: ROM; 103: RAM; 104: holding section; 105: I / F; 106: I / F; 107: I / F; 108: input section; 109: display section; 110: internal bus; 200a: sensor data; 201a: sensor data; 200b: evaluation target image; 201b: evaluation target image; 202b: evaluation target image; A: place; B: place; S110: acquisition unit; S120: conversion unit; S130: evaluation unit; S140: output unit.

Claims

1.An object evaluator that evaluates a state of an object, characterized by comprising: one or more sensors that measure the state of the object; an acquisition unit that acquires, via the sensors, object information that shows at least any one of a physical condition and an action of the object and feature information that shows a feature of the sensors; a conversion unit that converts the acquired object information image into an evaluation target image on a two-dimensional plane according to the feature information of the sensors; a reference database that stores a correlation between a past evaluation target image obtained by performing image conversion in advance and reference information associated with the past evaluation target image; an evaluation unit that generates an evaluation result for the evaluation target image with reference to the reference database; and an output unit that outputs the evaluation result. 2.The object evaluator according to claim 1, characterized in that: the correlation is constructed by mechanical learning using the past evaluation target image and the reference information as learning data. 3.The object evaluator according to claim 1 or 2, characterized in that: the object evaluator further comprises an update unit that reflects a relationship between the past evaluation target image and the reference information into the correlation when the relationship is newly acquired. 4.An object evaluation system that evaluates a state of an object, characterized by comprising: one or more sensors that measure the state of the object; an acquisition unit that acquires, via the sensors, object information that shows at least any one of a physical condition and an action of the object and feature information that shows a feature of the sensors; a conversion unit that converts the acquired object information image into an evaluation target image on a two-dimensional plane according to the feature information of the sensors; a reference database that stores a correlation between a past evaluation target image obtained by performing image conversion in advance and reference information associated with the past evaluation target image; an evaluation unit that generates an evaluation result for the evaluation target image with reference to the reference database; and an output unit that outputs the evaluation result. ​ ​ ​ ​

Images