WO2021182455A1 - 情報処理方法、コンピュータプログラム、情報処理装置及び情報処理システム - Google Patents
情報処理方法、コンピュータプログラム、情報処理装置及び情報処理システム Download PDFInfo
- Publication number
- WO2021182455A1 WO2021182455A1 PCT/JP2021/009229 JP2021009229W WO2021182455A1 WO 2021182455 A1 WO2021182455 A1 WO 2021182455A1 JP 2021009229 W JP2021009229 W JP 2021009229W WO 2021182455 A1 WO2021182455 A1 WO 2021182455A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- motion
- operation information
- subject
- abnormal state
- Prior art date
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 85
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000004590 computer program Methods 0.000 title claims description 4
- 230000033001 locomotion Effects 0.000 claims abstract description 205
- 238000001514 detection method Methods 0.000 claims abstract description 180
- 230000002159 abnormal effect Effects 0.000 claims abstract description 116
- 206010008118 cerebral infarction Diseases 0.000 claims abstract description 61
- 208000026106 cerebrovascular disease Diseases 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims description 62
- 230000008569 process Effects 0.000 claims description 48
- 230000008859 change Effects 0.000 claims description 16
- 238000009795 derivation Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 description 27
- 238000010586 diagram Methods 0.000 description 16
- 230000005856 abnormality Effects 0.000 description 10
- 208000024891 symptom Diseases 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 201000006474 Brain Ischemia Diseases 0.000 description 5
- 206010008120 Cerebral ischaemia Diseases 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 5
- 230000017531 blood circulation Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000003183 myoelectrical effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 230000001680 brushing effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010411 cooking Methods 0.000 description 2
- 238000005401 electroluminescence Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 231100000862 numbness Toxicity 0.000 description 2
- 206010003591 Ataxia Diseases 0.000 description 1
- 102100030802 Beta-2-glycoprotein 1 Human genes 0.000 description 1
- 201000004569 Blindness Diseases 0.000 description 1
- 208000004552 Lacunar Stroke Diseases 0.000 description 1
- 206010051078 Lacunar infarction Diseases 0.000 description 1
- 208000000112 Myalgia Diseases 0.000 description 1
- 206010028851 Necrosis Diseases 0.000 description 1
- 206010029174 Nerve compression Diseases 0.000 description 1
- 206010033799 Paralysis Diseases 0.000 description 1
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 208000032109 Transient ischaemic attack Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 108010023562 beta 2-Glycoprotein I Proteins 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 210000001124 body fluid Anatomy 0.000 description 1
- 239000010839 body fluid Substances 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 210000005013 brain tissue Anatomy 0.000 description 1
- 230000001269 cardiogenic effect Effects 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 238000002570 electrooculography Methods 0.000 description 1
- 230000003073 embolic effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 230000000004 hemodynamic effect Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000013465 muscle pain Diseases 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 230000001338 necrotic effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 208000027765 speech disease Diseases 0.000 description 1
- 230000036262 stenosis Effects 0.000 description 1
- 208000037804 stenosis Diseases 0.000 description 1
- 230000001732 thrombotic effect Effects 0.000 description 1
- 201000010875 transient cerebral ischemia Diseases 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
- A61B5/4064—Evaluating the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1113—Local tracking of patients, e.g. in a hospital or private home
- A61B5/1114—Tracking parts of the body
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
- A61B5/1127—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using markers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7221—Determining signal validity, reliability or quality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/02—Details of sensors specially adapted for in-vivo measurements
- A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/04—Arrangements of multiple sensors of the same type
Definitions
- This technology relates to information processing methods, computer programs, information processing devices and information processing systems.
- Cerebral infarction is a state in which cerebral ischemia is caused by obstruction or stenosis of cerebral blood vessels and necrosis of brain tissue.
- the causes of cerebral infarction are mainly divided into thrombotic, embolic and hemodynamic, and specifically, atherothrombotic cerebral infarction, cardiogenic cerebral infarction, lacunar infarction and others.
- Patent Document 1 describes a method for detecting cerebral infarction by measuring the concentration of nick ⁇ 2 glycoprotein I in a body fluid sample.
- the purpose of the present disclosure is to provide the subject with an information processing method or the like that can determine the presence or absence of an abnormal state that may cause cerebral infarction.
- the information processing method acquires the motion information detected by the motion detection device that detects the motion of the target person, stores the acquired motion information in a storage unit, and stores the motion information in the stored predetermined period. Based on the information, the reference motion information of the left and right half of the subject is derived, and the derived reference motion information and the motion information of the left and right body of the subject at the time of detection after the predetermined period are derived. Based on the above, the subject is made to execute a process of determining whether or not the subject is in an abnormal state having a possibility of cerebral infarction.
- the computer program acquires the motion information detected by the motion detection device that detects the motion of the target person, stores the acquired motion information in the storage unit, and stores the motion information in the stored predetermined period. Based on the above, the reference motion information of the left and right half of the subject is derived, and the derived reference motion information and the motion information of the left and right body of the subject at the time of detection after the predetermined period are obtained. Based on the above, the subject is made to execute a process of determining whether or not the subject is in an abnormal state having a possibility of cerebral infarction.
- the information processing device includes an operation information acquisition unit that acquires operation information detected by an operation detection device that detects an operation of a target person, and a storage that stores the operation information acquired by the operation information acquisition unit.
- a derivation unit that derives reference operation information for the left and right half of the subject based on the operation information stored in the storage unit for a predetermined period, the reference operation information derived by the derivation unit, and the reference operation information. It is provided with a determination unit for determining whether or not the subject is in an abnormal state that may cause cerebral infarction based on the motion information of the left and right halves of the subject at the time of detection after a predetermined period. ..
- the information system includes a motion detection device that detects the motion of the target person and an information processing device that acquires motion information from the motion detection device, and the information processing device is the motion detection device.
- the operation information acquisition unit that acquires the operation information detected by
- the storage unit that stores the operation information acquired by the operation information acquisition unit, and the operation information stored by the storage unit in a predetermined period, the left of the target person.
- the derivation unit that derives the reference motion information of the half body and the right half body, the reference motion information derived by the derivation section, and the motion information of the left half body and the right half body of the subject at the time of detection after the predetermined period. Based on this, the subject is provided with a determination unit for determining whether or not the subject is in an abnormal state that may cause cerebral infarction.
- FIG. 1 is a schematic diagram of the information processing system 100 according to the first embodiment.
- the information processing system 100 of the present embodiment is a system for determining the possibility of cerebral infarction from the motion information of the subject.
- the information processing system 100 includes an information processing device 1 and an motion detection sensor 2a provided in the detection device 2.
- the information processing device 1 and the detection device 2 can transmit and receive information via a network N such as the Internet.
- the information processing device 1 is further communicated and connected to the terminal device 3 via the network N.
- the information processing device 1 determines the risk of cerebral infarction or cerebral ischemia symptoms or signs in the subject, that is, the possibility of cerebral infarction, based on the motion information of the subject acquired from the detection device 2.
- the information processing device 1 provides information according to the determination result via the terminal device 3 or the like.
- Operation information is a parameter that represents the amount of operation of the target person.
- the amount of movement is, for example, the amount of movement (movement speed) per unit time of each part such as the limbs and head of the subject, the distance traveled, the shaking, the angular velocity, etc. can get.
- the amount of motion is not limited to that obtained from an image, and may be data detected by a microwave sensor, a millimeter wave sensor, an ultrasonic sensor, an acceleration sensor, or the like.
- the detection device 2 is provided, for example, in the subject's residence or the like, and detects the movement of the subject in daily life.
- the detection device 2 includes a motion detection sensor (motion detection device) 2a, and transmits motion information detected by the motion detection sensor 2a to the information processing device 1. It is preferable that a plurality of motion detection sensors 2a are provided in a plurality of areas such as a living room, a dining room, a kitchen, a washroom, and a bedroom in the subject's residence.
- the motion detection sensor 2a may be installed at a position where the subject can live without being aware of the sensor.
- the detection device 2 may include a biometric information detection sensor (biological information detection device) 2b in addition to the motion detection sensor 2a.
- the biological information detection sensor 2b will be described in detail in another embodiment.
- the motion detection sensor 2a is, for example, a camera that captures an image in the imaging target area.
- the motion detection sensor 2a has an image sensor such as a CCD (Charge Coupled Device) image sensor, a lens, and the like, and the light incident through the lens is photoelectrically converted by the image sensor to acquire motion information which is image data. ..
- the motion detection sensor 2a may be a stereo camera including a plurality of image pickup elements.
- the motion detection sensor 2a is not limited to the one using the above-mentioned camera, and may detect the position and shape of the target person by using, for example, an ultrasonic sensor, a microwave sensor, a millimeter wave sensor, a laser radar sensor, or the like. ..
- the motion detection sensor 2a may use the line-of-sight detection sensor to measure the eye movement of the subject and detect the line-of-sight direction, the viewpoint, and the like.
- the detection device 2 acquires the detection value of the motion detection sensor 2a.
- the detection device 2 may be configured as a wearable device and may be worn by the subject.
- the detection device 2 has, for example, a spectacle-shaped shape.
- the detection device 2 includes a motion sensor 2a that measures acceleration, angular velocity, and geomagnetism on three axes, respectively, and detects the motion of the target person.
- the detection device 2 may include a myoelectric potential sensor, which is a motion detection sensor 2a, at a position where it comes into contact with the nose, head, or the like of the subject in the worn state, and may detect the facial myoelectric potential of the subject.
- the detection device 2 is provided as a motion detection sensor 2a with a myoelectric potential sensor at a position where it abuts on the nose of the subject in the worn state, and detects motions such as the line-of-sight direction and blinking by detecting the electro-oculography of the subject. You may.
- the detection device 2 is not limited to the one having a spectacle-shaped shape, and may have, for example, a band shape and may be worn on the hand, foot, waist, or the like of the subject.
- the detection device 2 has, for example, a stretchable sheet shape and may be attached to the body of the subject. Further, the detection device 2 may be configured as a cabitus device such as a contact lens type or a mouthpiece type, and may be attached to the body cavity of the subject.
- a plurality of detection devices 2 may be attached to the target person.
- the detection device 2 is composed of a combination of a plurality of types of motion detection sensors 2a, and may acquire detection values by the plurality of types of sensors.
- the camera may detect the information of the entire imaging region including the target person, and the laser radar sensor or the like may detect the operation of the specified target person based on the detected imaging data.
- the motion detection sensor 2a detects motion information related to the motion that the target person repeatedly performs on a daily basis.
- the motion state of the left half of the subject and the motion state of the right half of the body are acquired, and the motion state of the subject is compared with the normal motion state of the left body and the right half of the subject.
- Determine the possibility of cerebral infarction For example, the appearance of symptoms such as a sudden face, numbness in the limbs, difficulty in seeing, and inability to rotate, especially on one side of the body, is likely to be due to the malfunction of a part of the brain. Therefore, it is possible to identify the possibility of the onset or sign of cerebral infarction or cerebral ischemia by detecting the occurrence of a sudden laterality in the movement of the subject.
- the configuration and detailed processing contents of such an information processing system 100 will be described below.
- FIG. 2 is a block diagram showing the configuration of the information processing device 1.
- the information processing device 1 uses a server computer.
- the information processing device 1 includes a control unit 10, a storage unit 11, and a communication unit 12.
- the information processing device 1 is described as one server computer for ease of explanation, but the functions or processes may be distributed among a plurality of server computers, and the information processing device 1 is virtually generated by one large computer. It may be one of a plurality of server computers (instances).
- the control unit 10 is a processor using one or more CPUs (Central Processing Unit), GPU (Graphics Processing Unit), etc., and uses a built-in memory such as ROM (Read Only Memory) or RAM (Random Access Memory). , Control each component to execute processing.
- CPUs Central Processing Unit
- GPU Graphics Processing Unit
- RAM Random Access Memory
- the communication unit 12 is a communication interface that realizes communication via the network N.
- the control unit 10 can transmit and receive information to and from the detection device 2, other external devices, and the like via the network N by the communication unit 12.
- the storage unit 11 includes, for example, a hard disk or a non-volatile memory such as an SSD (Solid State Drive).
- the storage unit 11 stores programs and data referred to by the control unit 10 including the program 1P.
- the control unit 10 reads and executes the program 1P to make a general-purpose server computer function as an information processing device peculiar to the present disclosure.
- the program 1P stored in the storage unit 11 may be recorded on a recording medium so that it can be read by a computer.
- the storage unit 11 stores the program 1P read from the recording medium 1A by a reading device (not shown). Further, the program 1P may be downloaded from an external computer (not shown) connected to a communication network (not shown) and stored in the storage unit 11.
- the storage unit 11 may be composed of a plurality of storage devices, or may be an external storage device connected to the information processing device 1.
- the storage unit 11 stores the target person information DB (Data Base: database) 111, the detected value DB 112, the reference operation information DB 113, and the like.
- FIG. 3A is an explanatory diagram illustrating the record layout of the target person information DB 111
- FIG. 3B is an explanatory diagram illustrating the record layout of the detected value DB 112
- FIG. 3C is an explanatory diagram illustrating the record layout of the reference operation information DB 113.
- the target person information DB 111 is a database that stores information on the target person who uses the information processing system 100.
- the target person information DB 111 contains the target person ID of each of the plurality of target persons, the name, age, address of the target person, image data obtained by photographing the face of the target person, a notification destination, and an emergency notification.
- Information such as the destination is associated and stored.
- the notification destination includes a notification destination that outputs a notification when an abnormal condition that may cause a cerebral infarction occurs in the subject.
- the MAC address, e-mail address, etc. of the terminal device 3 owned by the target person are stored in the notification destination.
- Emergency contacts include emergency contacts that are likely to cause a stroke to the subject.
- the telephone number of a person other than the target person is stored in the emergency contact information.
- the detection value DB 112 is a database that stores the detection value, the operation information, and the like detected by the operation detection sensor 2a. As shown in FIG. 3B, information such as the detection date and time, sensor information, detection value, operation information, target person ID, operation pattern, and the like are associated and stored in time series in the detection value DB 112. Each operation information stored in the detection value DB 112 is acquired and stored by the control unit 10 each time the control unit 20 of the detection device 2 acquires the operation information and transmits the acquired operation information to the information processing device 1.
- the sensor information includes identification information that identifies the motion detection sensor 2a that outputs the detected value, and stores, for example, a unique ID of the sensor.
- the detected value of the motion detection sensor 2a is stored in the detected value.
- the operation information string includes a left operation information column and a right operation information column.
- motion information indicating the motion of the left half body and the right half body of the target person is stored.
- the left motion information and the right motion information are parameters indicating the amount of motion of the relevant part of the subject, and are data such as the moving speed, moving distance, shaking, and angular velocity of the corresponding part as described above.
- the relevant part is a part of the human body such as a joint that is a characteristic point for specifying the posture of the subject.
- the movement amount (movement speed) per unit time of the left hand and the right hand of the target person is stored in the left motion information string and the right motion information string.
- the target person ID includes identification information for identifying the target person in the operation information, for example, the target person ID is stored.
- the target person ID is specified by extracting the facial feature amount of the subject from the image taken for detecting the motion information and performing pattern matching with the face feature amount of the target person registered in advance.
- the subject ID may be specified by using other methods such as machine learning.
- the movement pattern is a type of movement that the subject can perform on a daily basis, and may include, for example, sleeping, eating, brushing teeth, watching TV, cooking, walking, and the like.
- the motion pattern is specified, for example, by pattern matching the position, posture, or motion amount of the subject in the room.
- the operation pattern may be specified by using other methods such as machine learning.
- the reference operation information DB 113 is a database that stores reference operation information indicating the operation of the target person in the normal state. In determining the possibility of cerebral infarction of the subject, the information processing device 1 acquires the reference motion information obtained by collecting the motion information of the subject in a predetermined period and stores it in the reference motion information DB 113. The information processing device 1 compares the reference operation information with the operation information acquired in real time to determine the presence or absence of an abnormal state. As shown in FIG. 3C, for example, the reference operation information DB 113 stores information such as a target person ID, an operation pattern, a reference operation information, a reference period, and an update date and time in association with each other.
- the motion pattern includes information for identifying the motion pattern, and stores names indicating motion patterns such as sleeping, eating, brushing teeth, watching TV, cooking, and walking.
- the reference operation information includes the operation information of the reference state of the target person obtained by analyzing the operation information for a predetermined period.
- the reference motion information may include left reference motion information indicating the motion of the left half of the body and right reference motion information indicating the motion of the right half of the body.
- left reference motion information and the right reference motion information for example, by collecting motion information including left motion information and right motion information for the same motion pattern of the target person in a predetermined period, and calculating a range and an average value, respectively.
- the reference operation information may include a plurality of operation information associated with information regarding the time.
- the reference period includes a period for collecting operation information for deriving the reference operation information.
- the reference period is, for example, 7 days.
- the update date and time includes the latest information on the date and time when the reference operation information was updated.
- the reference operation information is updated as needed based on the operation information detected in real time.
- FIG. 4 is a block diagram showing the configuration of the detection device 2.
- the detection device 2 includes a control unit 20, a storage unit 21, a communication unit 22, and an operation information detection unit 23.
- the control unit 20 is a processor using one or a plurality of CPUs, GPUs, etc., and uses a built-in memory such as a ROM or RAM to control each component unit to execute processing.
- the storage unit 21 includes a non-volatile memory such as a flash memory.
- the storage unit 21 stores information referred to by the control unit 20.
- the communication unit 22 is a communication interface that realizes communication with the information processing device 1 via the network N.
- the operation information detection unit 23 acquires a detection signal using the operation detection sensor 2a.
- the motion information detection unit 23 may include an A / D conversion function and output the measured value obtained from the motion detection sensor 2a to the control unit 20.
- FIG. 5 is a block diagram showing the configuration of the terminal device 3.
- the terminal device 3 for example, a smartphone, a tablet terminal, or the like is used.
- the terminal device 3 may be an information terminal device such as a personal computer.
- the terminal device 3 includes a control unit 30, a storage unit 31, a communication unit 32, a display unit 33, and an operation unit 34.
- the control unit 30 includes a processor such as a CPU or GPU and a memory or the like.
- the control unit 30 may be configured as one piece of hardware (SoC: System On a Chip) in which a processor, a memory, a storage unit 31, and a communication unit 32 are integrated.
- SoC System On a Chip
- the control unit 30 controls each component unit to execute processing based on the program stored in the storage unit 31.
- the storage unit 31 includes a non-volatile memory such as a flash memory.
- the storage unit 31 stores the program and data referred to by the control unit 30.
- the communication unit 32 is a communication interface that realizes communication with the information processing device 1 via the network N.
- the display unit 33 includes a display device such as a liquid crystal panel and an organic EL (Electro Luminescence) display.
- the display unit 33 displays various information according to the instruction from the control unit 30.
- the operation unit 34 is an interface that accepts user operations, and includes, for example, a physical button, a mouse, a touch panel device with a built-in display, a speaker, a microphone, and the like.
- the operation unit 34 receives an operation input from the user and sends a control signal according to the operation content to the control unit 30.
- FIG. 6 is a flowchart showing an example of a processing procedure for acquiring reference operation information.
- the process of FIG. 6 is executed by the control unit 10 of the information processing device 1 and the control unit 20 of the detection device 2.
- the execution timing of the process is, for example, the timing at which the signal is detected by the motion detection sensor 2a.
- the control unit 20 of the detection device 2 acquires an image of the target person taken from the motion detection sensor 2a in real time or at a predetermined detection interval (for example, every 1 minute) (step S10).
- the control unit 20 detects the feature points corresponding to the corresponding parts of the target person from the acquired image (step S11). For example, the control unit 20 detects the right hand and the left hand of the target person as feature points.
- the control unit 20 acquires operation information including right operation information and left operation information based on the detection result of feature points in each image acquired in time series (step S12). Specifically, the control unit 20 acquires time. By comparing the image data acquired in the series, the movement amount of the corresponding part in the right half body and the left half body included in the images at the previous time and the current time is calculated. For example, the detection device 2 compares the coordinates of the left hand and the right hand in the previous frame with the coordinates of the left hand and the right hand in the current frame, respectively, and acquires the movement speed calculated from the movement distance and the detection time as operation information.
- control unit 20 specifies the operation pattern of the target person and the target person (step S13). For example, the control unit 20 detects each part such as a limb and a head as a feature point in step S11, and from the coordinate value of each detected feature point, the position, posture, and movement (gesture) of the target person in the room. The operation pattern is specified by performing pattern matching. Further, the control unit 20 stores (registers) the target person ID and the target person's face feature amount in advance in association with each other, extracts the face feature amount from step S10, and has a pattern with the stored face feature amount. The target person ID is specified by performing matching. The control unit 20 outputs operation information to the information processing device 1 in association with the specified operation pattern, target person ID, detection date and time, sensor ID, detection value, and the like (step S14).
- the control unit 10 of the information processing device 1 acquires operation information by the communication unit 12 (step S15).
- the control unit 10 associates the acquired operation information with the target person ID, the operation pattern, and the like, and stores the acquired operation information in the detection value DB 112 (step S16).
- the control unit 10 derives reference operation information indicating the normal operation of the target person based on the collected operation information (step S17). Specifically, the control unit 10 refers to the detection value DB 112 and acquires the operation information of the same target person detected within a predetermined period (for example, 7 days) and stored in the detection value DB 112. In this case, since the control unit 10 derives the reference operation information for each operation pattern, it is preferable to extract the operation information including the same operation pattern. For example, when deriving the basic operation information for the operation pattern "meal", the control unit 10 sets the detection date and time including the most recent week from the time of derivation, the same subject ID, and the same operation pattern "meal". Extract the including operation information.
- the control unit 10 calculates the average value of each of the extracted motion information based on the left motion information and the right motion information, thereby indicating the left reference motion information indicating the reference motion of the left half body and the reference motion of the right half body.
- the reference operation information including the right reference operation information is derived.
- control unit 10 compares the derived reference operation information with the previously recorded reference operation information, and determines whether or not to correct the reference operation information (step S18). Specifically, the control unit 10 determines the magnitude relationship between the derived reference operation information and the recorded reference operation information difference value and the preset threshold value, and determines whether or not the difference value is equal to or greater than the threshold value. To judge. When it is determined that the reference operation information is not corrected because the difference value is less than the threshold value (step S18: NO), the control unit 10 skips the correction processing of the reference operation information.
- step S18 When it is determined that the reference operation information is corrected because the difference value is equal to or greater than the threshold value (step S18: YES), the control unit 10 executes correction to change the recorded reference operation information to the newly derived reference operation information. (Step S19).
- the control unit 10 may correct the value of the recorded reference state information based on a predetermined rule.
- the control unit 10 stores the corrected reference operation information, update date and time, and other information in the reference operation information DB 113 (step S20), and ends a series of processes.
- control unit 10 executes the processing of step S17 or less when the feature amount indicating the operation pattern included in the acquired operation information is equal to or more than a predetermined value based on the analysis result of step S15. It's okay. That is, the control unit 10 may execute the derivation process of the reference operation information when the acquired operation information corresponds to the preset operation pattern.
- the detection device 2 may substantially include the information processing device 1.
- the control unit 20 of the detection device 2 may only output the detection value detected by the motion detection sensor 2a, and the control unit 10 of the information processing device 1 may perform the subsequent processing.
- the control unit 10 of the information processing device 1 and the control unit 20 of the detection device 2 may cooperate with each other to execute a series of processes by performing interprocess communication, for example.
- FIG. 7 is a flowchart showing an example of an abnormal state determination processing procedure.
- the process of FIG. 7 is executed by the control unit 10 of the information processing device 1 and the control unit 30 of the terminal device 3.
- the execution timing of the process is, for example, the timing at which new operation information is stored in the detection value DB 112.
- the control unit 10 of the information processing device 1 refers to the detection value DB 112 and acquires new operation information acquired and stored from the detection device 2 in real time (step S21).
- the operation information is associated with a target person ID, an operation pattern, and the like.
- the control unit 10 acquires reference operation information for comparison with the acquired operation information (step S22).
- the control unit 10 refers to the reference operation information DB 113 and acquires the reference operation information including the same target person ID and operation pattern as the acquired operation information.
- the control unit 10 compares the acquired motion information with the reference motion information, and determines whether or not the subject has a possibility of cerebral infarction, that is, whether or not the subject's motion information is in an abnormal state (step S23). ).
- the control unit 10 analyzes the left motion information in the left half of the body and the right motion information in the right half of the body, and detects an action different from the normal time in only one of the left and right half of the subject. Determines to be an abnormal condition with the possibility of cerebral infarction.
- the control unit 10 compares the acquired left operation information with the left reference operation information of the reference operation information, and compares the acquired right operation information with the right reference operation information of the reference operation information, and left and right. For each half of the body, it is determined whether or not the difference between the operation information and the reference operation information is equal to or greater than the threshold value.
- FIG. 8 is an explanatory diagram relating to the determination process of the abnormal state.
- the time series changes of the reference motion information for example, the moving speeds of the left hand and the right hand
- the operation information is on the vertical axis and the time is on the horizontal axis.
- the control unit 10 derives the reference operation information for each of the left and right halves from the operation information collected in the predetermined period, and stores the reference operation information in the reference operation information DB 113.
- the control unit 10 compares the operation information of each of the left and right halves with the reference operation information, and calculates the difference value from the reference operation information for each of the left and right halves. That is, the control unit 10 calculates the difference between the right reference operation information shown by the solid line in FIG. 8 and the current right operation information shown by the thick line. Similarly, the control unit 10 calculates the difference between the left reference operation information and the current left operation information.
- the control unit 10 compares the calculated difference value between the left and right halves with a predetermined threshold value, and determines whether or not there is an abnormality in the left and right halves for each of the left and right halves. Specifically, when the difference value is equal to or greater than the threshold value, it is determined that there is an abnormality. For example, the control unit 10 may make a determination by comparing the difference between the instantaneous values at a certain time with the threshold value, or set the integrated value or the average value of the difference at a certain unit time (for example, 5 minutes) as the threshold value. The judgment may be made by comparison.
- the control unit 10 finally determines whether or not the subject is in an abnormal state that may cause a cerebral infarction, based on the determination results of the left and right hips. Specifically, when the control unit 10 determines that one half of the body has an abnormality and the other half of the body has no abnormality, the control unit 10 determines that the condition is abnormal. When the control unit 10 determines that there is no abnormality in both half bodies, it determines that there is no abnormality. Further, the control unit 10 also determines that there is no abnormal state even when it is determined that there is an abnormality in both half bodies. For example, when there is a difference between both the left and right motion information and the reference motion information, it is determined that the possibility of cerebral infarction is low because it is not an abnormality on only one side.
- step S23 NO
- step S24 determines whether or not the abnormal state is a false abnormal state
- the pseudo-abnormal state is a state in which a predetermined change is temporarily generated in the movement of the left or right half of the body due to a factor other than the cerebral infarction, and unlike the abnormal state, the possibility of cerebral infarction is low.
- factors of the pseudo-abnormal state include temporary and partial blood flow when sleeping for a long time with either the left half of the body or the right half of the body down, numbness due to nerve compression, and only one side due to exercise. Muscle pain and the like.
- operation information with a difference between the left and right may be detected from the subject in these false abnormal states.
- the control unit 10 stores a false abnormal state information DB (not shown) that stores false abnormal state information in which operation information in the false abnormal state is defined in advance.
- the false abnormal state information DB stores operation information and other conditions that define the false abnormal state indicated in a predetermined operation.
- the control unit 10 compares the operation information of the false abnormal state information DB with the acquired operation information of the target person, and determines whether or not the abnormal state of the target person is a false abnormal state. For example, when the time when one side of the body is down at bedtime is equal to or longer than a predetermined value, and the difference between the left motion information or the right motion information and the reference motion information is less than the predetermined value. Corresponds to false abnormal state information.
- the control unit 10 may determine whether or not it is in a false abnormal state by using another machine learning method.
- the control unit 10 creates in advance a learning model that outputs an identification result of whether or not it is in a false abnormal state when operating information is input, stores it in the storage unit 11, and uses this learning model to store the learning model in a false abnormal state. It may be determined whether or not there is.
- step S24 When it is determined that the abnormal state is a false abnormal state, that is, the possibility of cerebral infarction is low because the motion information of the subject corresponds to the false abnormal state information (step S24: YES), the control unit 10 processes. Is returned to step S21, and acquisition of operation information is continued.
- the control unit 10 is the communication unit. 12 outputs notification information for notifying the occurrence of an abnormal state to the terminal device 3 (step S25).
- the control unit 10 refers to the target person information DB 111 to specify a notification destination when the target person is in an abnormal state, and outputs the notification information to the specified notification destination using, for example, a mail function or the like.
- the control unit 30 of the terminal device 3 acquires notification information for notifying the occurrence of an abnormal state by the communication unit 32 (step S26). Based on the acquired notification information, the control unit 30 displays a notification screen 330 including information indicating the occurrence of an abnormal state on the display unit 33 (step S27), and ends a series of processes.
- the control unit 10 may perform a loop process of performing step S21 after the process of step S25.
- FIG. 9 is a diagram showing an example of the notification screen 330 displayed on the display unit 33.
- the control unit 30 displays the notification screen information based on the notification information acquired from the information treatment device 1 on the display unit 33.
- the notification screen 330 includes a notification regarding the operation information determined to be in an abnormal state.
- the notification screen 330 may further include a notification prompting confirmation of the determination of the operation information determined to be in the abnormal state.
- the notification screen 330 includes information indicating the detection date and time of the operation information, the detection location, and the like, the operation graph 331 showing the detected operation information, the confirmation button 334 prompting the confirmation of the screen contents, and the like. Is included.
- the notification screen 330 may further include a message or the like for notifying support information (for example, content for urging a medical institution) to the target person according to the determination result.
- the operation graph 331 includes a reference value curve 332 showing the reference operation information of the subject, and a detection value curve 333 showing the operation information related to the detected abnormal state.
- the control unit 10 of the information processing device 1 refers to the reference operation information stored in the reference operation information DB 113 and the operation information stored in the detection value DB 112, and associates the time information with the reference value curve 332 and the detected value.
- the curve 333 is generated and displayed on the operation graph 331.
- control unit 10 refers to the detection value DB 112, acquires the detection date / time, the detection location, etc. of the operation information related to the abnormal state, generates text information displaying the acquired detection date / time, the detection location, etc., and generates the notification screen 330. Display above.
- the control unit 10 may further read the detection value of the motion detection sensor 2a related to the abnormal state from the detection value DB 112, and display the read detection value together with the motion graph 331 on the notification screen 330. By displaying, for example, the detection value acquired from the image data in association with the operation information in addition to the operation information in the abnormal state, the actual operation state of the target person can be recognized in more detail.
- the target person can recognize the occurrence of an abnormal state on the notification screen 330 displayed on the display unit 33. As a result, it is possible to notify the possibility of cerebral infarction even when the subject is not aware of it, so that it is possible to encourage early examination and the like and assist in the detection of cerebral infarction.
- the control unit 30 of the terminal device 3 receives the operation of pressing the confirmation button 334, the control unit 30 transmits the operation information to the information processing device 1.
- the control unit 10 of the information processing device 1 acquires operation information. If the operation information is not acquired for a predetermined period, the control unit 30 may output the notification information to the terminal device 3 again. As a result, the information can be reliably notified to the target person.
- the difference value is determined for each of the left half body and the right half body, but the present embodiment is not limited to this.
- the control unit 10 may determine whether or not it is in an abnormal state based on the difference value between the left operation information and the right operation information.
- the control unit 10 calculates the difference value between the two at each time from the left operation information and the right operation information in a predetermined period, averages the difference values over the period, and serves as the reference operation information on the left.
- the difference value between the operation information and the right operation information is derived.
- the control unit 10 acquires the operation information from the detection device 2, the control unit 10 calculates the difference value between the left operation information and the right operation information.
- the control unit 10 compares the calculated difference value with the difference value indicated by the reference operation information, and calculates the difference value between the two (referred to as “second difference value” for convenience).
- the control unit 10 compares the calculated second difference value with the threshold value, and if the second difference value is equal to or greater than the threshold value, determines that the state is abnormal. In this way, the control unit 10 compares the left-right difference of the operation information in the reference state (difference value which is the reference operation information) with the left-right difference of the current operation information, and determines whether or not the state is abnormal. You may.
- step S23 includes the process of step S24, and the control unit 10 may determine whether or not it is in an abnormal state by the process of determining whether or not it is in a false abnormal state.
- the control unit 10 may determine that the subject is unlikely to have a cerebral infarction, that is, is not in an abnormal state, by determining that the subject is in a pseudo-abnormal state based on the motion information.
- the determination accuracy can be further improved by determining whether or not each of the operation information derived from the image data obtained by the camera and the operation information derived from the line-of-sight data obtained by the line-of-sight sensor is in an abnormal state.
- a different threshold value may be defined depending on the detection location of the operation information, or the threshold value may be corrected according to the detection location. For example, even if the operation pattern is the same, the intensity of the operation, the movable range, etc. may change depending on the place where the operation is performed. Therefore, the reference operation is performed by using the threshold value according to the detection place of the operation information. It is preferred that a comparison be made with the information. Further, when the room temperature around the target person is detected by, for example, a temperature sensor provided in the motion detection sensor 2a, the threshold value may be corrected based on the change value of the room temperature in the movement path of the target person.
- the control unit 10 acquires a temperature change, compares it with the reference operation information using a threshold value derived by using a different correction value according to the acquired temperature change, and determines whether or not there is an abnormal state.
- FIG. 10 is a flowchart showing an example of a processing procedure related to warning information.
- the process of FIG. 10 is executed by the control unit 10 of the information processing device 1 and the control unit 30 of the terminal device 3.
- the following processing is executed in parallel with the processing of FIG.
- the control unit 10 determines whether or not the abnormal state continues for a predetermined time (step S31).
- the control unit 10 refers to the detection value DB 112 and specifies the time when the first operation information related to the abnormal state is detected.
- the control unit 10 determines the magnitude relationship between the elapsed time from the time when the first operation information is detected and a preset threshold value (for example, 20 minutes), and determines whether or not the elapsed time is equal to or greater than the threshold value. judge.
- control unit 10 When it is determined that the abnormal state does not continue for a predetermined time because the elapsed time is less than the threshold value (step S31: NO), the control unit 10 ends the process. In this case, the control unit 10 may output the information notifying the end of the abnormal state to the terminal device 3 by the communication unit 12.
- step S31: YES When it is determined that the abnormal state continues for a predetermined time because the elapsed time is equal to or greater than the threshold value (step S31: YES), the control unit 10 notifies the communication unit 12 of the continuation of the abnormal state. Is output to the terminal device 3 (step S32).
- the output destination of the warning information is the terminal device 3 of the target person as well as the output destination of the notification information.
- the control unit 30 of the terminal device 3 acquires warning information by the communication unit 32 (step S33). Based on the acquired warning information, the control unit 30 displays the warning information and the warning screen 340 for receiving the emergency call operation for the warning information on the display unit 33 (step S34).
- FIG. 11 is a diagram showing an example of a warning screen 340 displayed on the display unit 33.
- the control unit 30 displays the warning screen information based on the warning information acquired from the information treatment device 1 on the display unit 33.
- the warning screen 340 includes warning information indicating the occurrence and content of the warning state, and further selects a notification unnecessary button 341 that accepts the selection that an emergency call is not required for the warning information and the selection that an emergency call is required. Includes a call request button 342 to accept.
- An emergency call is to notify a person other than the subject that there is a high possibility of cerebral infarction when the abnormal condition of the subject continues.
- An emergency call assists a request for assistance to a subject in an emergency by, for example, reporting to the subject's family, fire department, medical institution, or the like.
- the target person performs a button operation for selecting whether or not to make an emergency call on the warning screen 340 displayed on the display unit 33.
- the control unit 30 accepts a button operation and executes a process according to the received operation content.
- the control unit 30 determines whether or not an emergency call is required (step S35). When the control unit 30 determines that an emergency call is not necessary by accepting the selection operation of the notification unnecessary button 341 via the operation unit 34 (step S35: NO), the control unit 30 ends the process. On the other hand, when it is determined that an emergency call is necessary by accepting the selection operation of the report need button 342 via the operation unit 34 (step S35: YES), the control unit 30 needs an emergency call by the communication unit 32. The emergency call information indicating that there is is output to the information processing device 1 (step S36). The control unit 30 may determine that an emergency call is necessary because the selection operation of both the report unnecessary button 341 and the report required button 342 is not accepted and the predetermined time has elapsed.
- the control unit 10 of the information processing device 1 determines whether or not an emergency call for the warning information is required (step S37). When it is determined that an emergency call is necessary by acquiring the emergency call information from the terminal device 3 (step S37: YES), the control unit 10 externally transmits the emergency information for notifying the abnormal state of the target person by the communication unit 32. Output to (step S38).
- the control unit 10 may specify an emergency notification destination in an emergency with reference to the target person information DB 111, and may make a report to the emergency notification destination using, for example, a call function.
- the control unit 10 skips the emergency call process in step S38 and ends a series of processes. ..
- the information processing device 1 changes the acquisition interval of the operation information according to the state of the target person. For example, in step S24 of FIG. 7, when it is determined that the state is abnormal, the control unit 10 outputs a detection interval change instruction to the detection device 2. For example, by changing the operation information acquisition interval, which is normally set every minute, every 10 seconds after the occurrence of an abnormal state, it is possible to identify the target person's state in more detail. ..
- a part or all of the processes executed by the control unit 10 of the information processing device 1 are partly or all of the processes executed by the control unit 30 of the terminal device 3. It may be executed by the control unit 20 of the detection device 2.
- the terminal device 3 may substantially include the information processing device 1 and directly communicate with the detection device 2.
- the terminal device 3 may be configured to substantially include the information processing device 1 and the detection device 2, and each of the above-mentioned processes may be executed by one terminal device 3 having these functions.
- the possibility of cerebral infarction can be determined based on the movement information of the subject's daily movements, particularly the movements that are repeatedly performed on a daily basis.
- the subject can be promptly notified to assist in early detection of cerebral infarction.
- Whether or not there is an abnormal state can be accurately determined by using the reference operation information and the false abnormal state information according to each target person.
- the biological information of the subject is acquired, and the presence or absence of the possibility of cerebral infarction of the subject is determined based on the motion information and the biological information.
- the differences between the second embodiment and the first embodiment will be described. Since the other configurations other than the configurations described later are the same as those of the information processing system 100 of the first embodiment, the common configurations are designated by the same reference numerals and detailed description thereof will be omitted.
- the detection device 2 of the second embodiment includes a motion detection sensor 2a and a biological information detection sensor 2b as shown in FIG.
- the biological information detection sensor 2b is a detection device that detects the biological information of the subject.
- the detection device 2 transmits the motion information detected by the motion detection sensor 2a and the biometric information detected by the biometric information detection sensor 2b to the information processing device 1.
- the biological information detection sensor 2b is, for example, an infrared camera that detects the blood flow and surface temperature of the subject.
- the biological information detection sensor 2b may detect the body pressure of the subject by using a surface pressure sensor provided on a mat such as a bedding or a seat used by the subject.
- the biological information detection sensor 2b may detect the pulse wave, body temperature, etc. of the subject by using a pulse wave sensor, a temperature sensor, or the like.
- the detection device 2 may be composed of a combination of a plurality of types of motion detection sensors 2a and a biological information detection sensor 2b.
- FIG. 12 is a block diagram showing the configuration of the detection device 2 according to the second embodiment.
- the detection device 2 includes a biological information detection unit 24 in addition to a control unit 20, a storage unit 21, a communication unit 22, and an operation information detection unit 23.
- the biological information detection unit 24 acquires a detection signal using the biological information detection sensor 2b.
- the biological information detection unit 24 may include an A / D conversion function and output the measured value obtained from the biological information detection sensor 2b to the control unit 20.
- the control unit 10 of the information processing device 1 stores the detection value including the operation information and the biological information acquired from the detection device 2 in the detection value DB 112.
- the information processing device 1 determines the possibility of cerebral infarction of the subject based on the motion information and the biological information.
- FIG. 13 is a flowchart showing an example of the abnormality state determination processing procedure in the second embodiment. The same step numbers are assigned to the processes common to those in FIG. 7 of the first embodiment, and detailed description thereof will be omitted.
- the control unit 10 of the information processing device 1 refers to the detection value DB 112 and acquires new operation information and biometric information acquired and stored from the detection device 2 in real time (step S41).
- the operation information is associated with a target person ID, an operation pattern, and the like.
- the control unit 10 acquires reference operation information for comparison with the acquired operation information (step S22).
- the control unit 10 refers to the reference operation information DB 113 and acquires the reference operation information including the same target person ID and operation pattern as the acquired operation information.
- the control unit 10 compares the acquired motion information with the reference motion information, and determines whether or not the subject has a possibility of cerebral infarction, that is, whether or not the subject's motion information is in an abnormal state (step S23). ). When it is determined that there is no abnormal state (step S23: NO), the control unit 10 returns the process to step S41 and continues to acquire the operation information and the biological information. When it is determined that the abnormal state is (step S23: YES), the control unit 10 determines whether or not the abnormal state is a false abnormal state (step S44).
- the control unit 10 compares the false abnormal state information regarding the false abnormal state stored in advance with the operation information of the target person, and determines whether or not the abnormal state of the target person is a false abnormal state.
- the control unit 10 of the second embodiment determines whether or not it is in a pseudo-abnormal state based on the operation information and the biological information. That is, the false abnormal state information is defined including the operation information and the biological information. For example, when the change value of the blood flow rate, the body temperature, the change value of the shape of the left and right half of the body, etc. of the subject are predetermined values, it corresponds to the false abnormal state information.
- step S44: YES When it is determined that the abnormal state is a false abnormal state because the operation information of the target person corresponds to the false abnormal state information (step S44: YES), the control unit 10 returns the process to step S41 and acquires the operation information. To continue.
- step S44: NO When it is determined that the abnormal state is not a false abnormal state because the operation information of the target person does not correspond to the false abnormal state information (step S44: NO), the control unit 10 indicates the abnormal state to the terminal device 3 by the communication unit 12. The notification information for notifying the occurrence is output (step S25).
- the control unit 30 of the terminal device 3 acquires notification information for notifying the occurrence of an abnormal state by the communication unit 32 (step S26). Based on the acquired notification information, the control unit 30 displays a notification screen including information indicating the occurrence of an abnormal state on the display unit 33 (step S27), and ends a series of processes.
- the control unit 10 may perform a loop process of performing step S21 after the process of step S25.
- an appropriate determination is made by determining the possibility of cerebral infarction including motion information and biological information. Results can be provided.
- the detection device 2 of the third embodiment includes a sound sensor that detects the spoken voice of the target person as the motion detection sensor 2a.
- the motion detection sensor 2a may further include a camera or the like that detects the motion of the subject's face.
- the information processing device 1 determines the possibility of cerebral infarction based on the operation information which is the voice data acquired from the detection device 2.
- the reference operation information of the reference operation information DB 113 stores voice data related to a plurality of reference patterns of words.
- the information processing device 1 determines the possibility of cerebral infarction by comparing the voice data of the subject in the normal state with the voice data detected in real time.
- the control unit 10 analyzes the voice data detected by the sound sensor and extracts a preset word pattern from the spoken voice.
- the control unit 10 determines the magnitude relationship between the difference value between the voice data corresponding to the extracted word pattern, the voice data which is the reference operation information, and the preset threshold value, and the difference value is equal to or larger than the threshold value. By determining whether or not it is, it is determined whether or not it is an abnormal state that may cause cerebral infarction.
- the control unit 10 may further acquire image data showing the speech operation of the subject's face captured by the camera. For example, using a pattern matching method or other known technique, the control unit 10 performs image analysis of motion information, which is acquired image data, and determines whether or not it matches a preset utterance pattern. When it is determined that the utterance pattern matches, the control unit 10 executes the above-mentioned voice data analysis process and determines whether or not it is in an abnormal state.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Physiology (AREA)
- Neurology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Psychology (AREA)
- Neurosurgery (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
図1は、第1実施形態における情報処理システム100の概要図である。本実施形態の情報処理システム100は、対象者の動作情報から脳梗塞の可能性を判定するシステムである。情報処理システム100は、情報処理装置1と、検出装置2に備えられる動作検出センサ2aとを含む。情報処理装置1と検出装置2とは、インターネット等のネットワークNを介して情報の送受信が可能である。情報処理装置1はさらに、ネットワークNを介して端末装置3と通信接続される。
第2実施形態では、対象者の生体情報を取得し、動作情報及び生体情報に基づき対象者の脳梗塞の可能性の有無を判定する。以下では、第2実施形態について、第1実施形態と異なる点を説明する。後述する構成を除く他の構成については第1実施形態の情報処理システム100と同様であるので、共通する構成については同一の符号を付してその詳細な説明を省略する。
第3実施形態では、情報処理を音声データである動作情報に特化して実現する。以下では、第3実施形態について、第1実施形態と異なる点を説明する。後述する構成を除く他の構成については第1実施形態の情報処理システム100と同様であるので、共通する構成については同一の符号を付してその詳細な説明を省略する。
2 検出装置
2a 動作検出センサ
2b 生体情報検出センサ
3 端末装置
10,20,30 制御部
11,21,31 記憶部
111 対象者DB
112 検査値DB
113 基準動作情報DB
1P プログラム
Claims (12)
- 対象者の動作を検出する動作検出装置が検出した動作情報を取得し、
取得した前記動作情報を記憶部に記憶し、
記憶した所定期間における前記動作情報に基づき、前記対象者の左半身及び右半身の基準動作情報を導出し、
導出した前記基準動作情報と、前記所定期間より後の検出時点における前記対象者の左半身及び右半身の動作情報とに基づき、前記対象者に脳梗塞の可能性がある異常状態であるか否かを判定する
処理をコンピュータに実行させる情報処理方法。 - 前記異常状態であると判定した場合、通知を出力する
処理をコンピュータに実行させる請求項1に記載の情報処理方法。 - 前記異常状態が所定時間に亘って継続しているか否かを判定する
処理をコンピュータに実行させる請求項1又は請求項2に記載の情報処理方法。 - 前記異常状態であると判定した場合、前記動作情報に基づき、脳梗塞以外の要因で前記対象者の左半身又は右半身に所定の変化が生じている偽異常状態であるか否かを判定する
処理をコンピュータに実行させる請求項1から請求項3のいずれか1項に記載の情報処理方法。 - 前記対象者の生体情報を検出する生体情報検出装置が検出した生体情報を取得し、
前記異常状態であると判定した場合、前記生体情報に基づき、脳梗塞以外の要因で前記対象者の左半身又は右半身に所定の変化が生じている偽異常状態であるか否かを判定する
処理をコンピュータに実行させる請求項1から請求項3のいずれか1項に記載の情報処理方法。 - 前記動作情報は、前記対象者の左半身の動作を検出した第1動作情報及び前記対象者の右半身の動作を検出した第2動作情報を含み、
前記基準動作情報の第1動作情報及び第2動作情報の差分値と、前記検出時点の第1動作情報及び第2動作情報の差分値とを比較して、前記異常状態であるか否かを判定する
処理をコンピュータに実行させる請求項1から請求項5のいずれか1項に記載の情報処理方法。 - 前記動作情報は、前記対象者の左半身の動作を検出した第1動作情報及び前記対象者の右半身の動作を検出した第2動作情報を含み、
前記基準動作情報の第1動作情報及び前記検出時点の第1動作情報と、前記基準動作情報の第2動作情報及び前記検出時点の第2動作情報とをそれぞれ比較して、前記異常状態であるか否かを判定する
処理をコンピュータに実行させる請求項1から請求項6のいずれか1項に記載の情報処理方法。 - 前記動作情報の検出場所に応じて、異なる閾値を用いて前記基準動作情報と前記検出時点の動作情報とを比較する
処理をコンピュータに実行させる請求項1から請求項7のいずれか1項に記載の情報処理方法。 - 前記動作検出装置は複数種類の検出装置を含み、前記対象者における複数の動作情報を取得する
請求項1から請求項8のいずれか1項に記載の情報処理方法。 - 対象者の動作を検出する動作検出装置が検出した動作情報を取得し、
取得した前記動作情報を記憶部に記憶し、
記憶した所定期間における前記動作情報に基づき、前記対象者の左半身及び右半身の基準動作情報を導出し、
導出した前記基準動作情報と、前記所定期間より後の検出時点における前記対象者の左半身及び右半身の動作情報とに基づき、前記対象者に脳梗塞の可能性がある異常状態であるか否かを判定する
処理をコンピュータに実行させるコンピュータプログラム。 - 対象者の動作を検出する動作検出装置が検出した動作情報を取得する動作情報取得部と、
前記動作情報取得部が取得した動作情報を記憶する記憶部と、
前記記憶部が記憶した所定期間における動作情報に基づき、前記対象者の左半身及び右半身の基準動作情報を導出する導出部と、
前記導出部が導出した前記基準動作情報と、前記所定期間より後の検出時点における前記対象者の左半身及び右半身の動作情報とに基づき、前記対象者に脳梗塞の可能性がある異常状態であるか否かを判定する判定部と
を備える情報処理装置。 - 対象者の動作を検出する動作検出装置と、該動作検出装置から動作情報を取得する情報処理装置とを含み、
前記情報処理装置は、
前記動作検出装置が検出した動作情報を取得する動作情報取得部と、
前記動作情報取得部が取得した動作情報を記憶する記憶部と、
前記記憶部が記憶した所定期間における動作情報に基づき、前記対象者の左半身及び右半身の基準動作情報を導出する導出部と、
前記導出部が導出した前記基準動作情報と、前記所定期間より後の検出時点における前記対象者の左半身及び右半身の動作情報とに基づき、前記対象者に脳梗塞の可能性がある異常状態であるか否かを判定する判定部と
を備える情報処理システム。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP21767819.2A EP4111984A4 (en) | 2020-03-10 | 2021-03-09 | INFORMATION PROCESSING METHOD, COMPUTER PROGRAM, INFORMATION PROCESSING DEVICE AND INFORMATION PROCESSING SYSTEM |
CN202180010135.4A CN114980814A (zh) | 2020-03-10 | 2021-03-09 | 信息处理方法、计算机程序、信息处理装置及信息处理*** |
JP2022507209A JPWO2021182455A1 (ja) | 2020-03-10 | 2021-03-09 | |
US17/823,710 US20220409120A1 (en) | 2020-03-10 | 2022-08-31 | Information Processing Method, Computer Program, Information Processing Device, and Information Processing System |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020041076 | 2020-03-10 | ||
JP2020-041076 | 2020-03-10 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/823,710 Continuation US20220409120A1 (en) | 2020-03-10 | 2022-08-31 | Information Processing Method, Computer Program, Information Processing Device, and Information Processing System |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021182455A1 true WO2021182455A1 (ja) | 2021-09-16 |
Family
ID=77671699
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/009229 WO2021182455A1 (ja) | 2020-03-10 | 2021-03-09 | 情報処理方法、コンピュータプログラム、情報処理装置及び情報処理システム |
Country Status (5)
Country | Link |
---|---|
US (1) | US20220409120A1 (ja) |
EP (1) | EP4111984A4 (ja) |
JP (1) | JPWO2021182455A1 (ja) |
CN (1) | CN114980814A (ja) |
WO (1) | WO2021182455A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023048287A1 (ja) * | 2021-09-27 | 2023-03-30 | テルモ株式会社 | 情報処理システム、プログラム及び情報処理方法 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005348893A (ja) * | 2004-06-09 | 2005-12-22 | Taiji Nishimura | 脳梗塞の予知方法 |
KR20150032956A (ko) * | 2013-09-23 | 2015-04-01 | 이양수 | 뇌졸중 감지 장치 및 방법 |
JP2018171443A (ja) * | 2017-03-31 | 2018-11-08 | コリア リサーチ インスティトゥート オブ スタンダーズ アンド サイエンス | 脳卒中モニタリングシステム |
JP2019535069A (ja) * | 2016-09-19 | 2019-12-05 | エヌ・ティ・ティ イノベーション インスティチュート インクNTT Innovation Institute, Inc. | 脳卒中検出及び予防システム及び方法 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE4441907A1 (de) * | 1993-12-16 | 1995-06-22 | Hewlett Packard Co | Patienten-Notfallreaktionssystem |
US20150164377A1 (en) * | 2013-03-13 | 2015-06-18 | Vaidhi Nathan | System and method of body motion analytics recognition and alerting |
US20150018723A1 (en) * | 2013-07-09 | 2015-01-15 | Industry-Academic Cooperation Foundation, Kyungpook National University | Apparatus for early detection of paralysis based on motion sensing |
ES2947033T3 (es) * | 2016-01-12 | 2023-07-31 | Univ Yale | Sistema para diagnóstico y notificación acerca de la aparición de un accidente cardiovascular o ACV |
AU2017305321B2 (en) * | 2016-08-02 | 2022-12-22 | New York University | Methods and kits for assessing neurological function and localizing neurological lesions |
US11389109B2 (en) * | 2018-04-14 | 2022-07-19 | Y. Michael Lee | System and method for monitoring and treating head, spine and body health and wellness |
-
2021
- 2021-03-09 JP JP2022507209A patent/JPWO2021182455A1/ja active Pending
- 2021-03-09 EP EP21767819.2A patent/EP4111984A4/en active Pending
- 2021-03-09 CN CN202180010135.4A patent/CN114980814A/zh active Pending
- 2021-03-09 WO PCT/JP2021/009229 patent/WO2021182455A1/ja active Application Filing
-
2022
- 2022-08-31 US US17/823,710 patent/US20220409120A1/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005348893A (ja) * | 2004-06-09 | 2005-12-22 | Taiji Nishimura | 脳梗塞の予知方法 |
KR20150032956A (ko) * | 2013-09-23 | 2015-04-01 | 이양수 | 뇌졸중 감지 장치 및 방법 |
JP2019535069A (ja) * | 2016-09-19 | 2019-12-05 | エヌ・ティ・ティ イノベーション インスティチュート インクNTT Innovation Institute, Inc. | 脳卒中検出及び予防システム及び方法 |
JP2018171443A (ja) * | 2017-03-31 | 2018-11-08 | コリア リサーチ インスティトゥート オブ スタンダーズ アンド サイエンス | 脳卒中モニタリングシステム |
Non-Patent Citations (1)
Title |
---|
See also references of EP4111984A4 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023048287A1 (ja) * | 2021-09-27 | 2023-03-30 | テルモ株式会社 | 情報処理システム、プログラム及び情報処理方法 |
Also Published As
Publication number | Publication date |
---|---|
US20220409120A1 (en) | 2022-12-29 |
EP4111984A1 (en) | 2023-01-04 |
JPWO2021182455A1 (ja) | 2021-09-16 |
EP4111984A4 (en) | 2023-08-09 |
CN114980814A (zh) | 2022-08-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210183516A1 (en) | Systems and methods to identify persons and/or identify and quantify pain, fatigue, mood, and intent with protection of privacy | |
JP6268193B2 (ja) | 脈波測定装置、携帯機器、医療機器システム、及び生体情報コミュニケーションシステム | |
CN109215804B (zh) | 基于虚拟现实技术与生理参数检测的精神类疾病辅助诊断*** | |
Lamonaca et al. | Health parameters monitoring by smartphone for quality of life improvement | |
US20240091623A1 (en) | System and method for client-side physiological condition estimations based on a video of an individual | |
JP6073919B2 (ja) | ユーザの圧受容器反射をモニタリングする方法及び装置 | |
US9747902B2 (en) | Method and system for assisting patients | |
CN111225612A (zh) | 基于机器学习的神经障碍识别和监测*** | |
KR102338297B1 (ko) | 사용자 상태를 판단하기 위한 시스템의 제어 방법, 장치 및 프로그램 | |
EP3160328B1 (en) | Device, system and computer program for detecting a health condition of a subject | |
KR20200056660A (ko) | 얼굴 내 미세움직임 기반 통증 모니터링 방법 및 시스템 | |
WO2021182455A1 (ja) | 情報処理方法、コンピュータプログラム、情報処理装置及び情報処理システム | |
US20240065599A1 (en) | Cognitive function estimation device, cognitive function estimation method, and storage medium | |
US20210202078A1 (en) | Patient-Observer Monitoring | |
WO2023189313A1 (ja) | プログラム、情報処理装置、および情報処理方法 | |
JP7209954B2 (ja) | 眼振解析システム | |
CN118338853A (zh) | 计算机程序、信息处理方法及信息处理装置 | |
CN115067903A (zh) | 血压监控装置、血压监控方法和存储介质 | |
JP5511503B2 (ja) | 生体情報計測処理装置及び生体情報計測処理方法 | |
Siedel et al. | Contactless interactive fall detection and sleep quality estimation for supporting elderly with incipient dementia | |
WO2020161947A1 (ja) | 身体健康状態映像分析装置、方法並びにシステム | |
JP2019180831A (ja) | 眼球運動特徴量算出システム、眼球運動特徴量算出方法及び眼球運動特徴量算出プログラム | |
CN115770013B (zh) | 辅助弱势人群的眼动测试方法、装置、设备及介质 | |
WO2023157596A1 (ja) | 情報処理方法、情報処理装置、プログラム、及び、情報処理システム | |
Kiprijanovska et al. | Smart Glasses for Gait Analysis of Parkinson’s Disease Patients |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21767819 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022507209 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202217050864 Country of ref document: IN |
|
ENP | Entry into the national phase |
Ref document number: 2021767819 Country of ref document: EP Effective date: 20220930 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |