WO2020188623A1 - Physical condition detection system - Google Patents

Physical condition detection system Download PDF

Info

Publication number
WO2020188623A1
WO2020188623A1 PCT/JP2019/010798 JP2019010798W WO2020188623A1 WO 2020188623 A1 WO2020188623 A1 WO 2020188623A1 JP 2019010798 W JP2019010798 W JP 2019010798W WO 2020188623 A1 WO2020188623 A1 WO 2020188623A1
Authority
WO
WIPO (PCT)
Prior art keywords
driver
answer
question
physical condition
voice
Prior art date
Application number
PCT/JP2019/010798
Other languages
French (fr)
Japanese (ja)
Inventor
山村　眞哉
Original Assignee
株式会社島津製作所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社島津製作所 filed Critical 株式会社島津製作所
Priority to JP2021506791A priority Critical patent/JP7359201B2/en
Priority to PCT/JP2019/010798 priority patent/WO2020188623A1/en
Publication of WO2020188623A1 publication Critical patent/WO2020188623A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
    • B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
    • B60K28/02—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver
    • B60K28/06—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver responsive to incapacity of driver
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition

Definitions

  • the present invention relates to a physical condition detection system.
  • the driver of a commercial vehicle is managed by roll call before driving.
  • the roll call management system disclosed in Patent Document 1 below acquires vital data such as alcohol in exhaled breath, and the vital data is managed on the network.
  • Patent Document 1 can determine whether or not driving is possible by detecting alcohol in exhaled breath, it cannot recognize symptoms such as cerebral hemorrhage, cerebral infarction, or myocardial infarction during driving. It is not effective for the driver to wear a device such as a sphygmomanometer to detect symptoms such as cerebral hemorrhage, cerebral infarction or myocardial infarction because it may interfere with driving.
  • the driver's physical condition may change during driving. Even if you are not ill, the driver may become drowsy due to tiredness while driving. Even in such a case, it is necessary to detect the change in the driver's physical condition at an early stage, stop the crew / operation, and change or stop the driving business if necessary.
  • An object of the present invention is to provide a physical condition detection system capable of responding to changes in physical condition during driving.
  • the physical condition detection system according to the present invention has the following configuration.
  • the voice analysis server stores a question storage unit that stores a question to the driver, a model answer storage unit that stores a model answer by the driver's voice to the question, and a driver terminal that stores the question stored in the question storage unit. It functions as a voice analysis unit that compares the question transmission unit to be transmitted to the driver with the model answer and the driver's actual answer, and analyzes the driver's physical condition from the difference between the model answer and the actual answer.
  • the driver terminal functions as a speaker for asking the question and a microphone for acquiring a real answer by the voice of the driver.
  • the question is asked once or a plurality of times at a fixed time, and the administrator terminal acquires the analysis result of the driver's physical condition from the voice analysis server.
  • the driver can ask and answer questions and answers by voice while driving, and can recognize changes in physical condition that can be judged by voice.
  • Accidents can be prevented by detecting changes in physical condition caused by illness and drowsiness at an early stage and stopping driving.
  • the physical condition detection system according to the embodiment of the present invention will be described with reference to the drawings.
  • the physical condition detection system functions as described by the hardware and software.
  • the same means may be designated by the same reference numerals and the description thereof may be omitted even in different embodiments.
  • the physical condition detection system 10 of the present application shown in FIG. 1 includes a voice analysis server 12, a driver terminal 14, and an administrator terminal 16.
  • the voice analysis server 12, the driver terminal 14, and the administrator terminal 16 are communicably connected by the network 18.
  • the voice analysis server 12, the driver terminal 14, and the administrator terminal 16 are provided with means for communicating with each other, and the description thereof may be omitted.
  • the voice analysis server 12 includes a question storage unit 20 that stores questions, a model answer storage unit 22 that stores model answers, a question transmission unit 24 that asks the driver a question, and a voice analysis unit 26 that analyzes the physical condition of the driver.
  • the question to the driver is stored in the question storage unit 20.
  • the question is voice data.
  • the content of the question is arbitrary, and it is preferable that the question is always answered by the driver.
  • the driver's name or date of birth may be a question. There may be one question or multiple questions.
  • the model answer storage unit 22 asks the driver a question in advance and stores the model answer obtained from the driver.
  • the model answer is voice data uttered by the driver.
  • the model answer 28 is a vibration waveform of air by voice (FIG. 2), and specifically, the model answer 28 is converted into a digital format and stored.
  • the amplitude differs depending on the volume of the voice, the time differs depending on the length of the voice, and the waveform differs depending on the content of the voice.
  • the amplitude in FIG. 2 is stored as voltage data.
  • the time t1 from the question to the answer and the time t2 from the start to the end of the answer are included in the data of the model answer 28.
  • the time t1 may be the time from the start of the question to the start of the answer, or the time from the end of the question to the start of the answer.
  • Model answer 28 is decomposed as phonemes 30a to 30f for each waveform having the same characteristics.
  • the amplitude B1 for each phoneme 30a to 30f and the waveform of each phoneme 30a to 30f are included in the data of the model answer.
  • the amplitude B1 for each of the phonemes 30a to 30f indicates the loudness of the sound and becomes the data of intonation (including intonation and accent). Although only the amplitude B1 with respect to the phoneme 30f is shown in FIG. 2, the data of the amplitude B1 is individually stored for all the phonemes 30a to 30f.
  • the waveforms of the phonemes 30a to 30f are data indicating what kind of sound it is.
  • a sound may be specified from the waveforms of the phonemes 30a to 30f, and each phoneme 30a to 30f may be stored as character data.
  • the data in model answer 28, t1, t2, and B1 should include a certain allowable range. This is because it is difficult for the driver to utter exactly the same as model answer 28 at any time.
  • the question transmission unit 24 transmits the question stored in the question storage unit 20 to the driver terminal 14. Questions are sent multiple times in a given period of time. The fixed time can be set to one day, half a day, eight hours, or the like. Questions may be sent at fixed time intervals, or questions may be sent at multiple fixed times. For example, the question transmission unit 24 transmits a question once an hour. The driver will answer questions multiple times during the driving process. If the driver's driving work is shortened, the number of times the question is sent may be one. If there are multiple questions, one question may be sent at a time, or multiple questions may be sent.
  • the voice analysis unit 26 compares the actual answer answered by the driver during the driving work with the model answer 28 stored in the model answer storage unit 22, and analyzes the physical condition of the driver from the difference.
  • the voice analysis unit 26 determines the time from the question to the start of the answer, the time from the start to the end of the answer, the intonation of the driver's voice to answer, and the content of the answer.
  • the judgment method by the voice analysis unit 26 is the following (A) to (D).
  • (A) The voice analysis unit 26 obtains the time from the question in the actual answer to the start of the answer, and compares the time with the time t1 of the model answer 28. If the actual response time is within the above allowable range of the model response 28, it is determined that the driver's physical condition is normal. For example, as shown in FIG. 3, if the time t1x from the question to the start of the answer in the actual answer 32a is longer than the time t1 of the model answer 28 and is not within the above allowable range of the model answer 28, the driver's physical condition is not good. Judge as abnormal.
  • the voice analysis unit 26 determines that the driver's physical condition is abnormal if the answer is not answered by the predetermined time.
  • the predetermined time is longer than the above allowable range.
  • the voice analysis unit 26 obtains the time from the start to the end of the answer of the actual answer, and compares the time with the time t2 of the model answer 28. If the actual answer time is within the above shared range of model answer 28, it is judged that the driver's physical condition is normal. For example, as shown in FIG. 4, the reality answer 32b has a soundless time between the phonemes 30c and 30d and the phonemes 30d and 30e. Therefore, the time t2x from the start to the end of the answer in the actual answer 32b becomes long, and if it is not within the above allowable range of the model answer 28, it is judged that the driver's physical condition is abnormal.
  • (C) Divide the actual answer into phonemes and obtain the amplitude of the waveform for each phoneme. If the obtained amplitude of each phoneme is within the above allowable range of the amplitude B1 of the model answer 28, it is determined that the driver's physical condition is normal. For example, in the reality answer 32c of FIG. 5, the amplitude B1x of the phoneme 30d'between the phonemes 30c and 30e is larger than the amplitude B1 of the phoneme 30d of the model answer 28. If the amplitude B1x of the phoneme 30d'in the actual answer 32c is not within the above allowable range of the model answer 28, it is judged that the driver's physical condition is abnormal.
  • (D) Compare the waveforms of each phoneme in the model answer 28 and the actual answer. As a result of comparison, if each waveform is the same, it is judged that the driver's physical condition is normal. Instead of comparing the waveforms themselves, the sound obtained from the waveform may be converted into character data, and the waveforms may be compared depending on whether or not the character data match. For example, the phoneme 30d of the model answer 28 in FIG. 2 is the phoneme 30g in the actual answer 32d of FIG. Since the actual response 32d in FIG. 6 has a waveform different from that in the model response 28 in FIG. 2 and the sound is different, it is determined that the driver's physical condition is abnormal.
  • driver's physical condition is normal in all of the above (A) to (D), it is finally judged that the driver's physical condition is normal. If at least one driver's physical condition is abnormal, it is determined that the driver's physical condition is abnormal.
  • the analysis result is transmitted to the administrator terminal 16 via the network 18.
  • the analysis result may be character data to be displayed on the display of the administrator terminal 16 or voice data emitted from the speaker.
  • the analysis result may be transmitted to the driver terminal 14 in addition to being transmitted to the administrator terminal 16.
  • the driver terminal 14 is a portable terminal or a device provided in the vehicle 34. Examples of portable terminals include smartphones, mobile phones, and tablet computers. A portable terminal may be detachably attached to the vehicle 34. As the device installed in the vehicle 34, a device of a car navigation system (automotive navigation system) may be used, or a car navigation system and a smartphone may be linked.
  • the driver terminal 14 functions as a speaker 36 for asking a question and a microphone 38 for acquiring voice.
  • the driver terminal 14 reproduces the question sent from the voice analysis server 12 on the speaker 36.
  • the driver listens to and answers the question posed by the speaker 36.
  • the answer is collected by the microphone 38 and transmitted to the voice analysis server 12.
  • the driver only listens to the question and answers. The driver is still holding the steering wheel and there is no problem in driving. When the driver develops illness or becomes drowsy, the actual answer does not fall within the permissible range of model answer 28 or gives an inaccurate answer.
  • each driver When there are a plurality of drivers, each driver carries a driver terminal 14. A question is stored in the question storage unit 20 for each driver terminal 14, and the model answer 28 is stored in the model answer storage unit 22. That is, the question and the model answer 28 are associated with each driver terminal 14.
  • the question transmitting unit 24 may transmit a question at a different time for each driver terminal 14.
  • the administrator terminal 16 includes a portable terminal or a stationary computer.
  • the administrator terminal 16 includes a smartphone, a mobile phone, a tablet computer, a laptop computer, and a desktop computer.
  • the administrator terminal 16 receives the analysis result from the voice analysis server 12, and displays the analysis result on the display provided in the administrator terminal 16.
  • the analysis result may be output by the speaker.
  • the administrator terminal 16 may emit an alarm sound through the speaker. From these things, the manager can recognize the change in the physical condition of the driver.
  • the administrator looks at the analysis result displayed on the display of the administrator terminal 16, and if the driver's physical condition is abnormal, the administrator instructs the driver to stop the flight / operation. If the administrator terminal 16 and the driver terminal 14 are smartphones or mobile phones, they may be instructed to stop the crew / operation by their call functions. Further, the manager terminal 16 may be provided with a stop instruction unit 40 for transmitting a crew / operation stop command, and the stop instruction unit 40 may transmit a crew / operation stop command to the driver terminal 14. A stop instruction is issued from the speaker 36 of the driver terminal 14, or a stop instruction is displayed on the display.
  • a question to the driver is stored in the question storage unit 20 in advance. Further, a question is asked to the driver in advance, and the driver's answer is stored in the model answer storage unit 22 as the model answer 28.
  • the model answer 28 may be acquired by the voice analysis server 12 by sending question data from the voice analysis server 12 to the driver terminal 14 and having the driver terminal 14 answer the question data.
  • the question transmitting unit 24 transmits a question to the driver terminal 14 during the driving time of the driver.
  • the question transmission unit 24 starts transmitting the question with the signal that the driver terminal 14 is activated and communicates with the voice analysis server 12. Transmission is performed multiple times in a fixed time. When the power of the driver terminal 14 is turned off and the communication with the voice analysis server 12 is cut off, the question transmission unit 24 stops the question transmission.
  • the driver terminal 14 When the driver terminal 14 receives a question, the speaker 36 emits a sound, and the microphone 38 collects the driver's answer. The driver listens to the question and answers it aloud.
  • the voice analysis unit 26 analyzes the real answer. As described above, it is determined whether or not the actual answer is within the permissible range of the model answer 28 and whether or not the content of the actual answer is correct. If the actual answer is not within the permissible range of the model answer 28, or if the content of the actual answer is inaccurate, the analysis result is regarded as abnormal. If the actual answer falls within the permissible range of the model answer 28 and the content of the actual answer is correct, the analysis result is regarded as normal.
  • the analysis result is transmitted from the voice analysis server 12 to the administrator terminal 16.
  • the analysis result is displayed on the display provided in the administrator terminal 16.
  • the manager recognizes the change in the driver's physical condition by looking at the analysis result displayed on the display. If the analysis result is abnormal, the manager will contact the driver. If the driver has a disease such as cerebral hemorrhage, cerebral infarction or myocardial infarction, he / she is instructed to stop the flight / operation, and if the driver is drowsy, he / she is instructed to take a break.
  • the operation stop instruction may be given by both terminals 14 and 16, or may be given by using another mobile phone or the like.
  • the present application can detect an abnormality in the physical condition of the driver while driving and instruct the driver to stop the operation / crew. It is possible to recognize changes in the driver's physical condition such as the onset of illness or drowsiness of the driver, making it easier to prevent vehicle accidents. Since questions and answers are given by voice, there is no problem in driving.
  • the automatic stop device 44 of the vehicle 34 may be used in the physical condition detection system 42.
  • a stop signal to the automatic stop device 44 is generated by the stop signal generation unit 46 of the administrator terminal 16.
  • the administrator operates the administrator terminal 16 to generate a stop signal, and the administrator terminal 16 generates a stop signal to the automatic stop device 44 of the vehicle 34.
  • the vehicle 34 is automatically stopped by the stop signal.
  • the administrator may transmit a stop instruction to the driver terminal 14 by the stop instruction unit 40 before transmitting the stop signal.
  • the manager and the driver may communicate with each other using other communication means to check for any abnormalities. Sends a stop signal when the driver really has something wrong.
  • the driver terminal 14 may include a canceling unit 48 that generates a signal for canceling the actual answer.
  • the signal generated by the canceling unit 48 is transmitted to the voice analysis server 12.
  • the canceling unit 48 may be one in which the driver emits a specific voice toward the microphone 38 to analyze the voice and generate a cancel signal.
  • the voice analysis unit 26 cancels the analysis result. Even if the analysis result is abnormal, the analysis result is cancelled.
  • the canceled information is also transmitted to the administrator terminal 16. It is also possible to stop the operation before the administrator instructs the driver to stop the operation.
  • the question and model answer 28 may be changed on a regular basis. For example, the question and the model answer 28 are changed every month, and they are stored in the question storage unit 20 and the model answer storage unit 22. Even if the questions are the same, only the model answer 28 may be rewritten. This is because the sound produced by the driver may change with time, and the model answer 28 may change.
  • the voice analysis server 12 may accumulate the actual answers, learn the accumulated real answers, and rewrite the model answer 28 of the model answer storage unit 22.
  • the voice analysis server 12 includes a reality answer storage unit 52 that stores real answers and an answer learning unit 54 that learns real answers.
  • the voice analysis server 12 stores the real answer in the real answer storage unit 52 each time the real answer is received.
  • the answer learning unit 54 creates the driver's model answer 28 and the allowable range from a large number of actual answers by AI (Artificial Intelligence), and rewrites the model answer 28 and the allowable range of the model answer storage unit 22. It is impossible for the driver to always give a fixed answer, and each answer is slightly different, but the answer learning unit 54 learns a large number of actual answers uttered by one driver at normal times with AI. It is possible to improve the accuracy of the driver's judgment as to whether it is normal or abnormal.
  • AI Artificial Intelligence
  • the voice analysis server, the driver terminal, and the administrator terminal are connected by a network so as to be able to communicate with each other.
  • the voice analysis server stores a question storage unit that stores a question to the driver, a model answer storage unit that stores a model answer by the driver's voice to the question, and a driver terminal that stores the question stored in the question storage unit. It functions as a voice analysis unit that compares the model answer and the driver's actual answer and analyzes the driver's physical condition from the difference between the model answer and the actual answer.
  • the driver terminal functions as a speaker for asking the question and a microphone for acquiring a real answer by the voice of the driver.
  • the question is asked once or a plurality of times at a fixed time, and the administrator terminal acquires the analysis result of the driver's physical condition from the voice analysis server.
  • the driver only asks and answers by voice while driving, and does not interfere with driving. Since the driver's physical condition change is detected at an early stage during driving and the result is displayed on the administrator terminal, the administrator can contact the driver and stop the operation. It is also possible to stop the operation before the driver has an accident.
  • the vehicle driven by the driver is provided with an automatic stop device, and the administrator terminal is provided with a stop signal generation unit for transmitting a stop signal to the automatic stop device.
  • the vehicle can be stopped at the discretion of the manager without the driver stopping the vehicle.
  • the driver terminal includes a canceling unit that generates a signal for canceling the actual answer and the voice analysis server receives a signal for canceling the actual answer within a predetermined time after receiving the actual answer, the voice analysis unit receives the signal. Cancel the analysis result.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biophysics (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Developmental Disabilities (AREA)
  • Educational Technology (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychiatry (AREA)
  • Psychology (AREA)
  • Social Psychology (AREA)
  • Child & Adolescent Psychology (AREA)
  • Combustion & Propulsion (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Epidemiology (AREA)
  • Chemical & Material Sciences (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

[Problem] To provide a physical condition detection system capable of responding to a change in physical condition during driving. [Solution] A physical condition detection system 10 is configured such that a voice analysis server 12, a driver's terminal 14, and a controller's terminal 16 are connected to be able to communicate via a network 18. The voice analysis server 12 functions as a question storage unit 20 that stores questions to be directed to a driver; a model response storage unit 22 that stores a driver's vocal model response 28 to the questions; a question transmitter 24 that transmits the questions stored in the question storage unit 20 to the driver's terminal 14; and a voice analysis unit 26 that compares the model response 28 with the actual response from the driver to analyze the physical condition of the driver from the difference between the model response 28 and the actual response. The driver's terminal 14 functions as a speaker 36 for posing a question and a microphone 38 for acquiring the driver's actual vocal response.

Description

体調検知システムPhysical condition detection system
　本発明は、体調検知システムに関するものである。 The present invention relates to a physical condition detection system.
　従来、事業用車両の運転者は運転前の点呼で健康管理されている。たとえば、下記特許文献１に開示される点呼管理システムは、呼気中アルコールなどのバイタルデータを取得し、そのバイタルデータはネットワーク上で管理されている。 Conventionally, the driver of a commercial vehicle is managed by roll call before driving. For example, the roll call management system disclosed in Patent Document 1 below acquires vital data such as alcohol in exhaled breath, and the vital data is managed on the network.
特開２０１２－１５９９５９号公報Japanese Unexamined Patent Publication No. 2012-159959
　血中アルコールに起因した運転ミスによる事故以外に、運転者が運転中に脳出血、脳梗塞または心筋梗塞などを発症して事故に至るケースがある。そのため、運転中に脳出血、脳梗塞または心筋梗塞などの症状を早期発見し、そのような症状がある場合に乗務・運行を停止させる必要がある。しかし、特許文献１は呼気中アルコールを検出することで運転の可否を判断できるが、運転中の脳出血、脳梗塞または心筋梗塞などの症状を認知できない。脳出血、脳梗塞または心筋梗塞などの症状を発見するために、血圧計などの器具を運転者が装着することは、運転に支障をきたす可能性があるため、有効ではない。 In addition to accidents caused by driving mistakes caused by blood alcohol, there are cases where the driver develops cerebral hemorrhage, cerebral infarction or myocardial infarction while driving, leading to an accident. Therefore, it is necessary to detect symptoms such as cerebral hemorrhage, cerebral infarction or myocardial infarction at an early stage while driving, and to stop the flight / operation when such symptoms are present. However, although Patent Document 1 can determine whether or not driving is possible by detecting alcohol in exhaled breath, it cannot recognize symptoms such as cerebral hemorrhage, cerebral infarction, or myocardial infarction during driving. It is not effective for the driver to wear a device such as a sphygmomanometer to detect symptoms such as cerebral hemorrhage, cerebral infarction or myocardial infarction because it may interfere with driving.
　脳出血、脳梗塞または心筋梗塞に限らず、運転中に運転者の体調が変わる場合もある。病気ではなくても、運転者が運転中に疲れから眠気を催す場合もある。そのような場合も、早期に運転者の体調変化を検知し、乗務・運行を停止させ、必要であれば運転業務を変更または中止する必要がある。 Not limited to cerebral hemorrhage, cerebral infarction or myocardial infarction, the driver's physical condition may change during driving. Even if you are not ill, the driver may become drowsy due to tiredness while driving. Even in such a case, it is necessary to detect the change in the driver's physical condition at an early stage, stop the crew / operation, and change or stop the driving business if necessary.
　本発明の目的は、運転中の体調変化に対応できる体調検知システムを提供することにある。 An object of the present invention is to provide a physical condition detection system capable of responding to changes in physical condition during driving.
　以上の課題を解決すべく、本発明に係る体調検知システムは、以下に述べるような構成を有する。 In order to solve the above problems, the physical condition detection system according to the present invention has the following configuration.
　本発明の体調検知システムは、音声分析サーバー、運転者端末および管理者端末がネットワークによって通信可能に接続されている。前記音声分析サーバーが、運転者に対する質問を記憶した質問記憶部と、前記質問に対する運転者の音声によるモデル回答を記憶したモデル回答記憶部と、前記質問記憶部に記憶された質問を運転者端末に送信する質問送信部と、前記モデル回答と運転者の現実回答とを比較し、モデル回答と現実回答との差から運転者の体調を分析する音声分析部として機能する。前記運転者端末が、前記質問を発するスピーカーと、前記運転者の音声による現実回答を取得するマイクとして機能する。前記質問が一定時間に１または複数回おこなわれ、前記管理者端末が音声分析サーバーから運転者の体調の分析結果を取得する。 In the physical condition detection system of the present invention, the voice analysis server, the driver terminal and the administrator terminal are connected by a network so as to be able to communicate with each other. The voice analysis server stores a question storage unit that stores a question to the driver, a model answer storage unit that stores a model answer by the driver's voice to the question, and a driver terminal that stores the question stored in the question storage unit. It functions as a voice analysis unit that compares the question transmission unit to be transmitted to the driver with the model answer and the driver's actual answer, and analyzes the driver's physical condition from the difference between the model answer and the actual answer. The driver terminal functions as a speaker for asking the question and a microphone for acquiring a real answer by the voice of the driver. The question is asked once or a plurality of times at a fixed time, and the administrator terminal acquires the analysis result of the driver's physical condition from the voice analysis server.
　本発明によれば、運転者が運転中に音声によって質問および回答され、音声によって判断できる体調の変化を認知できる。病気および眠気などによって引き起こされる体調変化を早期に発見して運転を中止することで、事故を未然に防ぐことができる。 According to the present invention, the driver can ask and answer questions and answers by voice while driving, and can recognize changes in physical condition that can be judged by voice. Accidents can be prevented by detecting changes in physical condition caused by illness and drowsiness at an early stage and stopping driving.
本願の体調検知システムの構成を示す図である。It is a figure which shows the structure of the physical condition detection system of this application. モデル回答の一例を示す音声波形の図である。It is a figure of the voice waveform which shows an example of a model answer. 質問から回答までの時間が長くなった現実回答の例を示す音声波形の図である。It is a figure of the voice waveform which shows the example of the actual answer which the time from the question to the answer became long. 回答の開始から終了までの時間が長くなった現実回答の例を示す音声波形の図である。It is a figure of the voice waveform which shows the example of the real answer which the time from the start to the end of the answer became long. 回答の振幅が大きくなった現実回答の例を示す音声波形の図である。It is a figure of the voice waveform which shows the example of the real answer which the amplitude of the answer became large. 現実回答の音がモデル回答の音と異なった例を示す音声波形の図である。It is a figure of the voice waveform which shows the example that the sound of a real answer is different from the sound of a model answer. 車両の自動停止装置と連携された本願の体調検知システムの構成を示す図である。It is a figure which shows the structure of the physical condition detection system of this application linked with the automatic stop device of a vehicle. 学習機能を備えた本願の体調検知システムの構成を示す図である。It is a figure which shows the structure of the physical condition detection system of this application provided with a learning function.
　本発明の実施形態に係るその体調検知システムについて図面を参照して説明する。体調検知システムは、ハードウェアおよびソフトウェアが説明するように機能するものである。複数の実施形態を説明するが、異なる実施形態であっても同じ手段には同一の符号を付して説明を省略する場合がある。 The physical condition detection system according to the embodiment of the present invention will be described with reference to the drawings. The physical condition detection system functions as described by the hardware and software. Although a plurality of embodiments will be described, the same means may be designated by the same reference numerals and the description thereof may be omitted even in different embodiments.
　[実施形態１]
　図１に示す本願の体調検知システム１０は、音声分析サーバー１２、運転者端末１４および管理者端末１６を備える。音声分析サーバー１２、運転者端末１４および管理者端末１６はネットワーク１８によって通信可能に接続されている。音声分析サーバー１２、運転者端末１４および管理者端末１６は互いに通信するための手段を備えており、その説明を省略する場合がある。 [Embodiment 1]
The physical condition detection system 10 of the present application shown in FIG. 1 includes a voice analysis server 12, a driver terminal 14, and an administrator terminal 16. The voice analysis server 12, the driver terminal 14, and the administrator terminal 16 are communicably connected by the network 18. The voice analysis server 12, the driver terminal 14, and the administrator terminal 16 are provided with means for communicating with each other, and the description thereof may be omitted.
　[音声分析サーバー]
　音声分析サーバー１２は質問を記憶した質問記憶部２０、モデル回答を記憶したモデル回答記憶部２２、運転者に質問する質問送信部２４、および運転者の体調を分析する音声分析部２６を備える。 [Voice analysis server]
The voice analysis server 12 includes a question storage unit 20 that stores questions, a model answer storage unit 22 that stores model answers, a question transmission unit 24 that asks the driver a question, and a voice analysis unit 26 that analyzes the physical condition of the driver.
　運転者に対する質問が質問記憶部２０に記憶される。質問は音声データである。質問の内容は任意であり、運転者から必ず回答される質問が好ましい。たとえば、運転者の名前または生年月日などが質問として挙げられる。質問は１つであってもよいし、複数であってもよい。 The question to the driver is stored in the question storage unit 20. The question is voice data. The content of the question is arbitrary, and it is preferable that the question is always answered by the driver. For example, the driver's name or date of birth may be a question. There may be one question or multiple questions.
　モデル回答記憶部２２は予め運転者に対して質問しておき、運転者から得られたモデル回答を記憶しておく。モデル回答は運転者の発声した音声データである。たとえば、モデル回答２８は音声による空気の振動波形であり（図２）、具体的にはモデル回答２８がディジタル形式に変換されて記憶される。振幅は音声の大小によって異なり、音声の長さによって時間が異なり、波形が音声内容によって異なる。図２における振幅は電圧のデータとして記憶される。 The model answer storage unit 22 asks the driver a question in advance and stores the model answer obtained from the driver. The model answer is voice data uttered by the driver. For example, the model answer 28 is a vibration waveform of air by voice (FIG. 2), and specifically, the model answer 28 is converted into a digital format and stored. The amplitude differs depending on the volume of the voice, the time differs depending on the length of the voice, and the waveform differs depending on the content of the voice. The amplitude in FIG. 2 is stored as voltage data.
　質問から回答までの時間ｔ１、回答を開始してから終了するまでの時間ｔ２がモデル回答２８のデータに含まれる。時間ｔ１は質問開始から回答開始までの時間であってもよいし、質問終了から回答開始までの時間であってもよい。 The time t1 from the question to the answer and the time t2 from the start to the end of the answer are included in the data of the model answer 28. The time t1 may be the time from the start of the question to the start of the answer, or the time from the end of the question to the start of the answer.
　モデル回答２８は同一特徴の波形ごとに音素３０ａ～３０ｆとして分解する。音素３０ａ～３０ｆごとの振幅Ｂ１、各音素３０ａ～３０ｆの波形がモデル回答のデータに含まれる。音素３０ａ～３０ｆごとの振幅Ｂ１は音の大小を示し、抑揚（イントネーションおよびアクセントを含む）のデータとなる。なお、図２では音素３０ｆに対する振幅Ｂ１のみを示しているが、すべての音素３０ａ～３０ｆについて個別に振幅Ｂ１のデータを記憶する。 Model answer 28 is decomposed as phonemes 30a to 30f for each waveform having the same characteristics. The amplitude B1 for each phoneme 30a to 30f and the waveform of each phoneme 30a to 30f are included in the data of the model answer. The amplitude B1 for each of the phonemes 30a to 30f indicates the loudness of the sound and becomes the data of intonation (including intonation and accent). Although only the amplitude B1 with respect to the phoneme 30f is shown in FIG. 2, the data of the amplitude B1 is individually stored for all the phonemes 30a to 30f.
　各音素３０ａ～３０ｆの波形は音によって異なるため、各音素３０ａ～３０ｆの波形は何の音であるかを示すデータとなる。音素３０ａ～３０ｆの波形から音を特定し、各音素３０ａ～３０ｆが文字データとして記憶されてもよい。 Since the waveforms of the phonemes 30a to 30f differ depending on the sound, the waveforms of the phonemes 30a to 30f are data indicating what kind of sound it is. A sound may be specified from the waveforms of the phonemes 30a to 30f, and each phoneme 30a to 30f may be stored as character data.
　モデル回答２８の中のデータであるｔ１、ｔ２、Ｂ１は一定の許容範囲を含めるようにする。運転者がいつでもモデル回答２８と全く同一に発声することは難しいためである。 The data in model answer 28, t1, t2, and B1, should include a certain allowable range. This is because it is difficult for the driver to utter exactly the same as model answer 28 at any time.
　質問送信部２４は質問記憶部２０に記憶された質問を運転者端末１４に送信する。質問は一定時間に複数回送信される。一定時間は１日、半日、８時間など設定可能である。決められた時間間隔で質問が送信されてもよいし、定められた複数の時間に質問が送信されてもよい。たとえば質問送信部２４は１時間に１回質問を送信する。運転者が運転業務中に複数回質問に回答することになる。なお、運転者の運転業務が短時間になった場合は質問を送信する回数が１回になる場合もある。複数の質問がある場合、１回に１つの質問を送信してもよいし、複数の質問を送信してもよい。 The question transmission unit 24 transmits the question stored in the question storage unit 20 to the driver terminal 14. Questions are sent multiple times in a given period of time. The fixed time can be set to one day, half a day, eight hours, or the like. Questions may be sent at fixed time intervals, or questions may be sent at multiple fixed times. For example, the question transmission unit 24 transmits a question once an hour. The driver will answer questions multiple times during the driving process. If the driver's driving work is shortened, the number of times the question is sent may be one. If there are multiple questions, one question may be sent at a time, or multiple questions may be sent.
　音声分析部２６は運転者が運転業務中に回答した現実回答とモデル回答記憶部２２に記憶されたモデル回答２８とを比較し、その差から運転者の体調を分析する。質問から回答開始までの時間、回答を開始してから終了するまでの時間、回答する運転者の音声の抑揚、回答の内容が音声分析部２６で判断される。 The voice analysis unit 26 compares the actual answer answered by the driver during the driving work with the model answer 28 stored in the model answer storage unit 22, and analyzes the physical condition of the driver from the difference. The voice analysis unit 26 determines the time from the question to the start of the answer, the time from the start to the end of the answer, the intonation of the driver's voice to answer, and the content of the answer.
　音声分析部２６による判断手法は下記の（Ａ）～（Ｄ）である。（Ａ）音声分析部２６は、現実回答における質問から回答開始までの時間を求め、その時間をモデル回答２８の時間ｔ１と比較する。現実回答の時間がモデル回答２８の上記許容範囲内であれば、運転者の体調が正常と判断する。たとえば、図３に示すように、現実回答３２ａにおける質問から回答開始までの時間ｔ１ｘがモデル回答２８の時間ｔ１よりも長く、モデル回答２８の上記許容範囲内に入っていなければ運転者の体調が異常と判断する。 The judgment method by the voice analysis unit 26 is the following (A) to (D). (A) The voice analysis unit 26 obtains the time from the question in the actual answer to the start of the answer, and compares the time with the time t1 of the model answer 28. If the actual response time is within the above allowable range of the model response 28, it is determined that the driver's physical condition is normal. For example, as shown in FIG. 3, if the time t1x from the question to the start of the answer in the actual answer 32a is longer than the time t1 of the model answer 28 and is not within the above allowable range of the model answer 28, the driver's physical condition is not good. Judge as abnormal.
　質問開始から一定時間たっても回答が無い場合、現実回答３２ａの時間ｔ１ｘが決定できない。そのため、音声分析部２６は所定時間までに回答されなかった場合に運転者の体調が異常と判断する。その所定時間は上記許容範囲よりも長い時間とする。 If there is no answer within a certain period of time from the start of the question, the time t1x of the actual answer 32a cannot be determined. Therefore, the voice analysis unit 26 determines that the driver's physical condition is abnormal if the answer is not answered by the predetermined time. The predetermined time is longer than the above allowable range.
　（Ｂ）音声分析部２６は現実回答の回答開始から終了までの時間を求め、その時間をモデル回答２８の時間ｔ２と比較する。現実回答の時間がモデル回答２８の上記共用範囲内に入っていれば運転者の体調が正常と判断する。たとえば、図４に示すように、現実回答３２ｂは音素３０ｃと３０ｄ、音素３０ｄと３０ｅの間に音の無い時間がある。そのため、現実回答３２ｂにおける回答を開始してから終了するまでの時間ｔ２ｘが長くなり、モデル回答２８の上記許容範囲内に入っていなければ運転者の体調が異常と判断する。 (B) The voice analysis unit 26 obtains the time from the start to the end of the answer of the actual answer, and compares the time with the time t2 of the model answer 28. If the actual answer time is within the above shared range of model answer 28, it is judged that the driver's physical condition is normal. For example, as shown in FIG. 4, the reality answer 32b has a soundless time between the phonemes 30c and 30d and the phonemes 30d and 30e. Therefore, the time t2x from the start to the end of the answer in the actual answer 32b becomes long, and if it is not within the above allowable range of the model answer 28, it is judged that the driver's physical condition is abnormal.
　（Ｃ）現実回答を音素に分割し、音素ごとの波形の振幅を求める。その求めた各音素の振幅がモデル回答２８の振幅Ｂ１の上記許容範囲内に入っていれば、運転者の体調が正常と判断する。たとえば、図５の現実回答３２ｃは音素３０ｃと３０ｅの間にある音素３０ｄ'の振幅Ｂ１ｘがモデル回答２８の音素３０ｄの振幅Ｂ１よりも大きくなっている。現実回答３２ｃにおける音素３０ｄ'の振幅Ｂ１ｘがモデル回答２８の上記許容範囲内に入っていなければ運転者の体調が異常と判断する。 (C) Divide the actual answer into phonemes and obtain the amplitude of the waveform for each phoneme. If the obtained amplitude of each phoneme is within the above allowable range of the amplitude B1 of the model answer 28, it is determined that the driver's physical condition is normal. For example, in the reality answer 32c of FIG. 5, the amplitude B1x of the phoneme 30d'between the phonemes 30c and 30e is larger than the amplitude B1 of the phoneme 30d of the model answer 28. If the amplitude B1x of the phoneme 30d'in the actual answer 32c is not within the above allowable range of the model answer 28, it is judged that the driver's physical condition is abnormal.
　（Ｄ）モデル回答２８と現実回答の各音素の波形を比較する。比較の結果、各波形が同じであれば運転者の体調が正常と判断する。波形そのものを比較するのではなく、波形から求められる音を文字データに変換し、文字データが一致するか否かで波形を比較してもよい。たとえば図２のモデル回答２８の音素３０ｄが図６の現実回答３２ｄでは音素３０ｇになっている。図６の現実回答３２ｄは図２のモデル回答２８と異なる波形になっており、音が異なるため、運転者の体調が異常と判断する。 (D) Compare the waveforms of each phoneme in the model answer 28 and the actual answer. As a result of comparison, if each waveform is the same, it is judged that the driver's physical condition is normal. Instead of comparing the waveforms themselves, the sound obtained from the waveform may be converted into character data, and the waveforms may be compared depending on whether or not the character data match. For example, the phoneme 30d of the model answer 28 in FIG. 2 is the phoneme 30g in the actual answer 32d of FIG. Since the actual response 32d in FIG. 6 has a waveform different from that in the model response 28 in FIG. 2 and the sound is different, it is determined that the driver's physical condition is abnormal.
　上記（Ａ）～（Ｄ）の全てで運転者の体調が正常であれば最終的に運転者の体調が正常と判断する。少なくとも１つ運転者の体調が異常であれば運転者の体調が異常と判断する。 If the driver's physical condition is normal in all of the above (A) to (D), it is finally judged that the driver's physical condition is normal. If at least one driver's physical condition is abnormal, it is determined that the driver's physical condition is abnormal.
　分析結果はネットワーク１８を介して管理者端末１６に送信される。分析結果は管理者端末１６のディスプレイに表示させる文字データであってもよいし、スピーカーから発せられる音声データであってもよい。分析結果は管理者端末１６に送信する以外に運転者端末１４に送信してもよい。 The analysis result is transmitted to the administrator terminal 16 via the network 18. The analysis result may be character data to be displayed on the display of the administrator terminal 16 or voice data emitted from the speaker. The analysis result may be transmitted to the driver terminal 14 in addition to being transmitted to the administrator terminal 16.
　[運転者端末]
　運転者端末１４は携行可能な端末または車両３４に備え付けられた装置である。携行可能な端末として、スマートフォン、携帯電話、タブレット型コンピュータが挙げられる。携行可能な端末を車両３４に取り外し可能に取り付けてもよい。車両３４に据え付けられた装置としては、カーナビゲーションシステム（automotive navigation system）の装置を利用してもよく、さらにカーナビゲーションシステムとスマートフォンを連携させてもよい。運転者端末１４は質問を発するスピーカー３６および音声を取得するマイク３８として機能する。 [Driver terminal]
The driver terminal 14 is a portable terminal or a device provided in the vehicle 34. Examples of portable terminals include smartphones, mobile phones, and tablet computers. A portable terminal may be detachably attached to the vehicle 34. As the device installed in the vehicle 34, a device of a car navigation system (automotive navigation system) may be used, or a car navigation system and a smartphone may be linked. The driver terminal 14 functions as a speaker 36 for asking a question and a microphone 38 for acquiring voice.
　運転者端末１４は音声分析サーバー１２から送られてくる質問をスピーカー３６で再生する。運転者はスピーカー３６から発せられる質問を聞いて回答する。回答はマイク３８で集音され、音声分析サーバー１２に送信される。 The driver terminal 14 reproduces the question sent from the voice analysis server 12 on the speaker 36. The driver listens to and answers the question posed by the speaker 36. The answer is collected by the microphone 38 and transmitted to the voice analysis server 12.
　運転者は質問を聞いて回答するだけである。運転者はハンドルを握ったままであり、運転に支障はない。運転者が病気を発症したり眠気を催したりすると、現実回答がモデル回答２８の許容範囲に入らなかったり、不正確な回答をする。 The driver only listens to the question and answers. The driver is still holding the steering wheel and there is no problem in driving. When the driver develops illness or becomes drowsy, the actual answer does not fall within the permissible range of model answer 28 or gives an inaccurate answer.
　運転者が複数いる場合、運転者それぞれが運転者端末１４を携行する。運転者端末１４ごとに質問が質問記憶部２０に記憶され、モデル回答２８がモデル回答記憶部２２に記憶される。すなわち運転者端末１４ごとに質問とモデル回答２８が紐づけされる。質問送信部２４は運転者端末１４ごとに異なる時間に質問を送信してもよい。 When there are a plurality of drivers, each driver carries a driver terminal 14. A question is stored in the question storage unit 20 for each driver terminal 14, and the model answer 28 is stored in the model answer storage unit 22. That is, the question and the model answer 28 are associated with each driver terminal 14. The question transmitting unit 24 may transmit a question at a different time for each driver terminal 14.
　[管理者端末]
　管理者端末１６は携行可能な端末または据え付け型のコンピュータを含む。スマートフォン、携帯電話、タブレット型コンピュータ、ラップトップ型コンピュータ、ディスクトップ型コンピュータが管理者端末１６として挙げられる。管理者端末１６は音声分析サーバー１２から分析結果を受信し、管理者端末１６に備えられたディスプレイに分析結果を表示する。スピーカーで分析結果を発してもよい。運転者の体調が異常であった場合に管理者端末１６がスピーカーで警報音を発してもよい。これらのことから、管理者は運転者の体調の変化を認知することができる。 [Administrator terminal]
The administrator terminal 16 includes a portable terminal or a stationary computer. The administrator terminal 16 includes a smartphone, a mobile phone, a tablet computer, a laptop computer, and a desktop computer. The administrator terminal 16 receives the analysis result from the voice analysis server 12, and displays the analysis result on the display provided in the administrator terminal 16. The analysis result may be output by the speaker. When the driver's physical condition is abnormal, the administrator terminal 16 may emit an alarm sound through the speaker. From these things, the manager can recognize the change in the physical condition of the driver.
　管理者は管理者端末１６のディスプレイに表示される分析結果を見て、運転者の体調が異常であれば、運転者に乗務・運行の停止を指示する。管理者端末１６と運転者端末１４がスマートフォンまたは携帯電話であれば、それらの通話機能で乗務・運行の停止を指示してもよい。また、管理者端末１６に乗務・運行の停止指令を送信するための停止指示部４０を備え、その停止指示部４０から運転者端末１４に乗務・運行の停止指令を送信してもよい。運転者端末１４のスピーカー３６から停止指示を発したり、ディスプレイに停止指示を表示させたりする。 The administrator looks at the analysis result displayed on the display of the administrator terminal 16, and if the driver's physical condition is abnormal, the administrator instructs the driver to stop the flight / operation. If the administrator terminal 16 and the driver terminal 14 are smartphones or mobile phones, they may be instructed to stop the crew / operation by their call functions. Further, the manager terminal 16 may be provided with a stop instruction unit 40 for transmitting a crew / operation stop command, and the stop instruction unit 40 may transmit a crew / operation stop command to the driver terminal 14. A stop instruction is issued from the speaker 36 of the driver terminal 14, or a stop instruction is displayed on the display.
　[体調検知方法]
　次に本願の体調検知システム１０を使用した体調検知方法について説明する。（１）運転者への質問を予め質問記憶部２０に記憶しておく。さらに、運転者に予め質問し、運転者の回答をモデル回答２８としてモデル回答記憶部２２に記憶しておく。音声分析サーバー１２から運転者端末１４に質問データを送り、運転者端末１４で回答してもらうことでモデル回答２８を音声分析サーバー１２で取得してもよい。 [Physical condition detection method]
Next, a physical condition detection method using the physical condition detection system 10 of the present application will be described. (1) A question to the driver is stored in the question storage unit 20 in advance. Further, a question is asked to the driver in advance, and the driver's answer is stored in the model answer storage unit 22 as the model answer 28. The model answer 28 may be acquired by the voice analysis server 12 by sending question data from the voice analysis server 12 to the driver terminal 14 and having the driver terminal 14 answer the question data.
　（２）運転者が運転時間中に質問送信部２４が質問を運転者端末１４に送信する。運転者端末１４が起動して音声分析サーバー１２と通信されたことを合図として、質問送信部２４は質問の送信を開始する。送信は一定時間に複数回おこなわれる。運転者端末１４の電源がオフになって音声分析サーバー１２との通信が切断されると、質問送信部２４は質問送信を停止する。 (2) The question transmitting unit 24 transmits a question to the driver terminal 14 during the driving time of the driver. The question transmission unit 24 starts transmitting the question with the signal that the driver terminal 14 is activated and communicates with the voice analysis server 12. Transmission is performed multiple times in a fixed time. When the power of the driver terminal 14 is turned off and the communication with the voice analysis server 12 is cut off, the question transmission unit 24 stops the question transmission.
　（３）運転者端末１４は質問を受信するとスピーカー３６で発し、マイク３８で運転者の回答を集音する。運転者は質問を聞いて声で回答する。 (3) When the driver terminal 14 receives a question, the speaker 36 emits a sound, and the microphone 38 collects the driver's answer. The driver listens to the question and answers it aloud.
　（４）音声分析サーバー１２が現実回答を受信すると、音声分析部２６が現実回答を分析する。上記のように現実回答がモデル回答２８の許容範囲の中に入っているか否か、現実回答の内容が正しいか否かでおこなう。現実回答がモデル回答２８の許容範囲に入っていない、または現実回答の内容が不正確であれば分析結果を体調異常とする。現実回答がモデル回答２８の許容範囲に入り、かつ現実回答の内容が正しければ分析結果を体調正常とする。 (4) When the voice analysis server 12 receives the real answer, the voice analysis unit 26 analyzes the real answer. As described above, it is determined whether or not the actual answer is within the permissible range of the model answer 28 and whether or not the content of the actual answer is correct. If the actual answer is not within the permissible range of the model answer 28, or if the content of the actual answer is inaccurate, the analysis result is regarded as abnormal. If the actual answer falls within the permissible range of the model answer 28 and the content of the actual answer is correct, the analysis result is regarded as normal.
　（５）分析結果は音声分析サーバー１２から管理者端末１６に送信される。管理者端末１６に備えられるディスプレイで分析結果が表示される。管理者はディスプレイに表示される分析結果を見て、運転者の体調の変化を認知する。その分析結果が体調異常の場合に管理者から運転者に連絡をする。運転者が脳出血、脳梗塞または心筋梗塞などの病気を発症していれば乗務・運行の停止を指示し、運転者が眠気を催していれば休憩を取るように指示する。運転停止指示は両端末１４、１６によって行ってもよいし、他の携帯電話などを使用して行ってもよい。 (5) The analysis result is transmitted from the voice analysis server 12 to the administrator terminal 16. The analysis result is displayed on the display provided in the administrator terminal 16. The manager recognizes the change in the driver's physical condition by looking at the analysis result displayed on the display. If the analysis result is abnormal, the manager will contact the driver. If the driver has a disease such as cerebral hemorrhage, cerebral infarction or myocardial infarction, he / she is instructed to stop the flight / operation, and if the driver is drowsy, he / she is instructed to take a break. The operation stop instruction may be given by both terminals 14 and 16, or may be given by using another mobile phone or the like.
　以上のように、本願は運転中の運転者の体調異常を検知して、運転者に運行・乗務の停止を指示できる。運転者の病気の発症または眠気などの運転者の体調変化を認知でき、車両事故を防止しやすくなっている。音声による質問と回答を行うため、運転に支障が無い。 As described above, the present application can detect an abnormality in the physical condition of the driver while driving and instruct the driver to stop the operation / crew. It is possible to recognize changes in the driver's physical condition such as the onset of illness or drowsiness of the driver, making it easier to prevent vehicle accidents. Since questions and answers are given by voice, there is no problem in driving.
　[実施形態２]
　図７に示すように、体調検知システム４２の中で車両３４の自動停止装置４４が利用されてもよい。自動停止装置４４への停止信号が管理者端末１６の停止信号生成部４６で生成される。分析結果が体調異常であった場合に、管理者が管理者端末１６を操作することで停止信号生成部４６が停止信号を生成し、管理者端末１６から車両３４の自動停止装置４４に停止信号を送信する。停止信号によって車両３４が自動的に停止する。管理者は、停止信号を送信する前に、停止指示部４０によって運転者端末１４に停止指示を送信してもよい。管理者と運転者が他の通信手段を用いて連絡を取り合って、異常がないか確認してもよい。運転者に本当に異常があった場合に停止信号を送信する。 [Embodiment 2]
As shown in FIG. 7, the automatic stop device 44 of the vehicle 34 may be used in the physical condition detection system 42. A stop signal to the automatic stop device 44 is generated by the stop signal generation unit 46 of the administrator terminal 16. When the analysis result is abnormal, the administrator operates the administrator terminal 16 to generate a stop signal, and the administrator terminal 16 generates a stop signal to the automatic stop device 44 of the vehicle 34. To send. The vehicle 34 is automatically stopped by the stop signal. The administrator may transmit a stop instruction to the driver terminal 14 by the stop instruction unit 40 before transmitting the stop signal. The manager and the driver may communicate with each other using other communication means to check for any abnormalities. Sends a stop signal when the driver really has something wrong.
　運転状況によってはすぐに回答できなかったり、声の抑揚が変化したりする場合がある。その場合に、運転者の体調が正常であるのにかかわらず、音声分析部２６の分析結果が体調異常になる場合がある。そのため、運転者端末１４は現実回答をキャンセルする信号を生成するキャンセル部４８を備えてもよい。キャンセル部４８で生成された信号は音声分析サーバー１２に送信される。キャンセル部４８は運転者が特定の音声をマイク３８に向けて発することで、音声を分析してキャンセル信号を生成するものであってもよい。 Depending on the driving situation, it may not be possible to answer immediately or the intonation of the voice may change. In that case, the analysis result of the voice analysis unit 26 may become abnormal even though the driver's physical condition is normal. Therefore, the driver terminal 14 may include a canceling unit 48 that generates a signal for canceling the actual answer. The signal generated by the canceling unit 48 is transmitted to the voice analysis server 12. The canceling unit 48 may be one in which the driver emits a specific voice toward the microphone 38 to analyze the voice and generate a cancel signal.
　音声分析サーバー２６が現実回答を受信後の所定時間内にキャンセル信号を受信すると、音声分析部２６は分析結果をキャンセルする。分析結果が体調異常であっても、その分析結果がキャンセルされる。管理者端末１６にもキャンセルされた情報を送信する。管理者が運転者に運転停止を指示する前に止めることもできる。 When the voice analysis server 26 receives the cancel signal within a predetermined time after receiving the actual answer, the voice analysis unit 26 cancels the analysis result. Even if the analysis result is abnormal, the analysis result is cancelled. The canceled information is also transmitted to the administrator terminal 16. It is also possible to stop the operation before the administrator instructs the driver to stop the operation.
　[実施形態３]
　質問およびモデル回答２８は定期的に変更されてもよい。たとえば、１ヶ月毎に質問およびモデル回答２８を変更し、それらを質問記憶部２０とモデル回答記憶部２２に記憶する。質問は同じであってもモデル回答２８のみを書き換えてもよい。時間とともに運転者の発音する音が変化し、モデル回答２８が変化する場合があるためである。 [Embodiment 3]
The question and model answer 28 may be changed on a regular basis. For example, the question and the model answer 28 are changed every month, and they are stored in the question storage unit 20 and the model answer storage unit 22. Even if the questions are the same, only the model answer 28 may be rewritten. This is because the sound produced by the driver may change with time, and the model answer 28 may change.
　[実施形態４]
　図８の体調検知システム５０のように、音声分析サーバー１２が現実回答を蓄積し、蓄積された現実回答を学習し、モデル回答記憶部２２のモデル回答２８を書き換えてもよい。音声分析サーバー１２は現実回答を蓄積する現実回答記憶部５２、現実回答を学習する回答学習部５４を備える。音声分析サーバー１２は現実回答を受信するたびに現実回答記憶部５２に現実回答を記憶する。 [Embodiment 4]
As in the physical condition detection system 50 of FIG. 8, the voice analysis server 12 may accumulate the actual answers, learn the accumulated real answers, and rewrite the model answer 28 of the model answer storage unit 22. The voice analysis server 12 includes a reality answer storage unit 52 that stores real answers and an answer learning unit 54 that learns real answers. The voice analysis server 12 stores the real answer in the real answer storage unit 52 each time the real answer is received.
　回答学習部５４はＡＩ（Artificial Intelligence）によって多数の現実回答から運転者のモデル回答２８および許容範囲を作成し、モデル回答記憶部２２のモデル回答２８および許容範囲を書き換える。運転者がいつも一定の回答をすることは不可能であり、各回答が微妙に異なるが、一の運転者が正常時に発声した多数の現実回答を回答学習部５４がＡＩで学習することで、運転者の正常か異常かの判断の正確性を高めることができる。 The answer learning unit 54 creates the driver's model answer 28 and the allowable range from a large number of actual answers by AI (Artificial Intelligence), and rewrites the model answer 28 and the allowable range of the model answer storage unit 22. It is impossible for the driver to always give a fixed answer, and each answer is slightly different, but the answer learning unit 54 learns a large number of actual answers uttered by one driver at normal times with AI. It is possible to improve the accuracy of the driver's judgment as to whether it is normal or abnormal.
　（第１項）一態様に係る体調検知システムは、音声分析サーバー、運転者端末および管理者端末がネットワークによって通信可能に接続されている。前記音声分析サーバーは、運転者に対する質問を記憶した質問記憶部と、前記質問に対する運転者の音声によるモデル回答を記憶したモデル回答記憶部と、前記質問記憶部に記憶された質問を運転者端末に送信する質問送信部と、前記モデル回答と運転者の現実回答とを比較し、モデル回答と現実回答との差から運転者の体調を分析する音声分析部として機能する。前記運転者端末は、前記質問を発するスピーカーと、前記運転者の音声による現実回答を取得するマイクとして機能する。前記質問が一定時間に１または複数回おこなわれ、前記管理者端末が音声分析サーバーから運転者の体調の分析結果を取得する。 (Paragraph 1) In the physical condition detection system according to one aspect, the voice analysis server, the driver terminal, and the administrator terminal are connected by a network so as to be able to communicate with each other. The voice analysis server stores a question storage unit that stores a question to the driver, a model answer storage unit that stores a model answer by the driver's voice to the question, and a driver terminal that stores the question stored in the question storage unit. It functions as a voice analysis unit that compares the model answer and the driver's actual answer and analyzes the driver's physical condition from the difference between the model answer and the actual answer. The driver terminal functions as a speaker for asking the question and a microphone for acquiring a real answer by the voice of the driver. The question is asked once or a plurality of times at a fixed time, and the administrator terminal acquires the analysis result of the driver's physical condition from the voice analysis server.
　第１項に記載の体調検知システムによれば、運転者が運転中に音声で質問され回答するだけであり、運転の妨げにならない。運転中に運転者の体調変化を早期に発見し、管理者端末で結果が表示されるため、管理者から運転者に連絡して運転を停止させることができる。運転者が事故する前に運転停止させることも可能である。 According to the physical condition detection system described in the first paragraph, the driver only asks and answers by voice while driving, and does not interfere with driving. Since the driver's physical condition change is detected at an early stage during driving and the result is displayed on the administrator terminal, the administrator can contact the driver and stop the operation. It is also possible to stop the operation before the driver has an accident.
　(第２項）前記モデル回答と運転者の現実回答との比較が、質問から回答開始までの時間、回答を開始してから終了するまでの時間、回答する運転者の音声の抑揚、回答の正確性の少なくとも１つを含む。 (Section 2) The comparison between the model answer and the driver's actual answer is the time from the question to the start of the answer, the time from the start to the end of the answer, the intonation of the driver's voice to answer, and the answer. Includes at least one of accuracy.
　第２項に記載の体調検知システムによれば、運転者の体調変化で発声がおかしくなったことを検知できる。 According to the physical condition detection system described in the second item, it is possible to detect that the utterance has become strange due to a change in the physical condition of the driver.
　（第３項）前記運転者が運転する車両に自動停止装置が備えられており、前記管理者端末が自動停止装置に停止信号を送信する停止信号生成部を備える。 (Section 3) The vehicle driven by the driver is provided with an automatic stop device, and the administrator terminal is provided with a stop signal generation unit for transmitting a stop signal to the automatic stop device.
　第３項に記載の体調検知システムによれば、運転者が車両を停止させなくても、管理者の判断で車両を停止させることができる。 According to the physical condition detection system described in the third paragraph, the vehicle can be stopped at the discretion of the manager without the driver stopping the vehicle.
　(第４項）前記運転者端末が現実回答をキャンセルする信号を生成するキャンセル部を備え、前記音声分析サーバーが現実回答を受信後の所定時間内にキャンセルする信号を受信すると、音声分析部は分析した結果をキャンセルする。 (Item 4) When the driver terminal includes a canceling unit that generates a signal for canceling the actual answer and the voice analysis server receives a signal for canceling the actual answer within a predetermined time after receiving the actual answer, the voice analysis unit receives the signal. Cancel the analysis result.
　第４項に記載の体調検知システムによれば、運転状況などで運転者が正確に回答できなくて体調異常と判断されても、その結果をキャンセルすることで、体調異常と判断されなくできる。 According to the physical condition detection system described in paragraph 4, even if the driver cannot answer accurately due to driving conditions and is judged to be in poor physical condition, the result can be canceled so that the driver is not judged to be in poor physical condition.
　その他、本発明は、その主旨を逸脱しない範囲で当業者の知識に基づき種々の改良、修正、変更を加えた態様で実施できるものである。 In addition, the present invention can be implemented in a mode in which various improvements, modifications, and changes are made based on the knowledge of those skilled in the art without departing from the gist thereof.
１０、４２、５０：体調検知システム
１２：音声分析サーバー
１４：運転者端末
１６：管理者端末
１８：ネットワーク
２０：質問記憶部
２２：モデル回答記憶部
２４：質問送信部
２６：音声分析部
２８：モデル回答
３０ａ、３０ｂ、３０ｃ、３０ｄ、３０ｄ'、３０ｅ、３０ｆ、３０ｄ：音素
３２ａ、３２ｂ、３２ｃ、３２ｄ：異常の有る現実回答
３４：車両
３６：スピーカー
３８：マイク
４０：停止指示部
４４：自動停止装置
４６：停止信号生成部
４８：キャンセル部
５２：現実回答記憶部
５４：回答学習部 10, 42, 50: Physical condition detection system 12: Voice analysis server 14: Driver terminal 16: Administrator terminal 18: Network 20: Question storage unit 22: Model answer storage unit 24: Question transmission unit 26: Voice analysis unit 28: Model answers 30a, 30b, 30c, 30d, 30d', 30e, 30f, 30d: Phonemes 32a, 32b, 32c, 32d: Abnormal reality Answers 34: Vehicle 36: Speaker 38: Microphone 40: Stop indicator 44: Automatic Stop device 46: Stop signal generation unit 48: Cancel unit 52: Reality answer storage unit 54: Answer learning unit

Claims (4)

  1. 音声分析サーバー、運転者端末および管理者端末がネットワークによって通信可能に接続されており、
    前記音声分析サーバーが、
    運転者に対する質問を記憶した質問記憶部と、
    前記質問に対する運転者の音声によるモデル回答を記憶したモデル回答記憶部と、
    前記質問記憶部に記憶された質問を運転者端末に送信する質問送信部と、
    前記モデル回答と運転者の現実回答とを比較し、モデル回答と現実回答との差から運転者の体調を分析する音声分析部と、
    として機能し、
    前記運転者端末が、
    前記質問を発するスピーカーと、
    前記運転者の音声による現実回答を取得するマイクと、
    として機能し、
    前記質問送信部が一定時間に１または複数回質問を送信し、
    前記管理者端末が音声分析サーバーから運転者の体調の分析結果を取得する体調検知システム。     The voice analysis server, driver terminal and administrator terminal are connected by a network so that they can communicate with each other.
    The voice analysis server
    A question storage unit that memorizes questions to the driver,
    A model answer storage unit that stores the model answer by the driver's voice to the question,
    A question transmission unit that transmits the question stored in the question storage unit to the driver terminal, and
    A voice analysis unit that compares the model answer with the driver's actual answer and analyzes the driver's physical condition from the difference between the model answer and the actual answer.
    Acts as
    The driver terminal
    The speaker that asks the question and
    A microphone that obtains a real answer by the driver's voice,
    Acts as
    The question transmitter sends a question once or multiple times in a fixed time,
    A physical condition detection system in which the administrator terminal acquires an analysis result of the driver's physical condition from a voice analysis server.
  2. 前記モデル回答と運転者の現実回答との比較が、質問から回答開始までの時間、回答を開始してから終了するまでの時間、回答する運転者の音声の抑揚、回答の正確性の少なくとも１つを含む請求項１の体調検知システム。 The comparison between the model answer and the driver's actual answer is at least one of the time from the question to the start of the answer, the time from the start to the end of the answer, the inflection of the driver's voice to answer, and the accuracy of the answer. The physical condition detection system of claim 1, which includes one.
  3. 前記運転者が運転する車両に自動停止装置が備えられており、
    前記管理者端末が自動停止装置に停止信号を送信する停止信号生成部を備えた請求項２の体調検知システム。     The vehicle driven by the driver is equipped with an automatic stop device.
    The physical condition detection system according to claim 2, further comprising a stop signal generation unit in which the administrator terminal transmits a stop signal to the automatic stop device.
  4. 前記運転者端末が現実回答をキャンセルする信号を生成するキャンセル部を備え、
    前記音声分析サーバーが現実回答を受信後の所定時間内にキャンセルする信号を受信すると、音声分析部は分析した結果をキャンセルする請求項３の体調検知システム。     The driver terminal is provided with a canceling unit that generates a signal for canceling the actual answer.
    The physical condition detection system according to claim 3, wherein when the voice analysis server receives a signal for canceling the actual answer within a predetermined time after receiving the actual answer, the voice analysis unit cancels the analysis result.
PCT/JP2019/010798 2019-03-15 2019-03-15 Physical condition detection system WO2020188623A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2021506791A JP7359201B2 (en) 2019-03-15 2019-03-15 Physical condition detection system
PCT/JP2019/010798 WO2020188623A1 (en) 2019-03-15 2019-03-15 Physical condition detection system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2019/010798 WO2020188623A1 (en) 2019-03-15 2019-03-15 Physical condition detection system

Publications (1)

Publication Number Publication Date
WO2020188623A1 true WO2020188623A1 (en) 2020-09-24

Family

ID=72520654

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/010798 WO2020188623A1 (en) 2019-03-15 2019-03-15 Physical condition detection system

Country Status (2)

Country Link
JP (1) JP7359201B2 (en)
WO (1) WO2020188623A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102021205970A1 (en) 2021-06-11 2022-12-15 Volkswagen Aktiengesellschaft Method for diagnosing a disease, preferably a respiratory disease

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006235772A (en) * 2005-02-23 2006-09-07 Tamotsu Yokoyama Data collection analysis display system
WO2016129276A1 (en) * 2015-02-12 2016-08-18 パナソニックＩｐマネジメント株式会社 Information dissemination method, server, information terminal device, system, and voice interaction system
WO2018066023A1 (en) * 2016-10-03 2018-04-12 三菱電機株式会社 Driving authorization transfer determination device and driving authorization transfer determination method
JP2018140741A (en) * 2017-02-28 2018-09-13 パイオニア株式会社 Control device
WO2018230562A1 (en) * 2017-06-14 2018-12-20 日本電気株式会社 Notification system, notification method, and non-transitory computer-readable medium with program stored thereon

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004314750A (en) 2003-04-15 2004-11-11 Denso Corp Vehicle instrument operation control device
JP4631464B2 (en) 2005-02-23 2011-02-16 パナソニック株式会社 Physical condition determination device and program thereof

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006235772A (en) * 2005-02-23 2006-09-07 Tamotsu Yokoyama Data collection analysis display system
WO2016129276A1 (en) * 2015-02-12 2016-08-18 パナソニックＩｐマネジメント株式会社 Information dissemination method, server, information terminal device, system, and voice interaction system
WO2018066023A1 (en) * 2016-10-03 2018-04-12 三菱電機株式会社 Driving authorization transfer determination device and driving authorization transfer determination method
JP2018140741A (en) * 2017-02-28 2018-09-13 パイオニア株式会社 Control device
WO2018230562A1 (en) * 2017-06-14 2018-12-20 日本電気株式会社 Notification system, notification method, and non-transitory computer-readable medium with program stored thereon

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102021205970A1 (en) 2021-06-11 2022-12-15 Volkswagen Aktiengesellschaft Method for diagnosing a disease, preferably a respiratory disease
WO2022258302A1 (en) 2021-06-11 2022-12-15 Volkswagen Aktiengesellschaft Method for diagnosing a disease, preferably a respiratory disease

Also Published As

Publication number Publication date
JP7359201B2 (en) 2023-10-11
JPWO2020188623A1 (en) 2020-09-24

Similar Documents

Publication Publication Date Title
US20080147262A1 (en) Vehicle help system and method
RU2714805C2 (en) Method and system of vehicle for performing secret call of an operator of rescue services (embodiments)
EP3675121A2 (en) Two-way in-vehicle virtual personal assistant
EP2942012A1 (en) Driver assistance system
JPH0628656B2 (en) Method and apparatus for monitoring asymmetric hemisphere brain function
CN110035358B (en) Vehicle-mounted audio output device, audio output control method, and recording medium
US10332385B2 (en) Location based support request messages responsive to alert recommendation
US11214263B2 (en) Management assistance system
CN113270093B (en) Agent device, agent system, and non-transitory recording medium
WO2020188623A1 (en) Physical condition detection system
JP2021117940A (en) Agent device, agent system, and program
US10293830B2 (en) Systems and methods for recognizing and analyzing emotional states of a vehicle operator
JP2010282368A (en) Driving support device and program
JP2019121970A (en) Interactive device
CN113206861B (en) Information processing apparatus, information processing method, and recording medium
JP7347244B2 (en) Agent devices, agent systems and programs
Monsaingeon et al. Earcons to reduce mode confusions in partially automated vehicles: Development and application of an evaluation method
JP2020000713A (en) Analysis apparatus, analysis method, and computer program
JP2021093087A (en) Agent device
EP3835106A1 (en) Agent management device, program, and agent management method
US11826146B2 (en) Psychomotor vigilance testing for persons tasked with monitoring autonomous vehicles
US11184475B2 (en) Mobile apparatus, terminal apparatus, information processing system, information processing method, program for mobile apparatus, and program for terminal apparatus
JP2020077428A (en) Management support system
US20230311757A1 (en) Vehicle and control method thereof
WO2023053369A1 (en) Information processing device, task management system, information processing method, and recording medium

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: 19920546

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021506791

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19920546

Country of ref document: EP

Kind code of ref document: A1