JP2016146870A - Lifesaving support device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a lifesaving support device for performing proper lifesaving support to a user by voice.SOLUTION: A message output section outputs a guiding message for lifesaving support by utilization of a self device, a voice recognition section recognizes an utterance content of input voice, and a level determination section extracts a directive for directing change of an output level from the utterance content, and determines the output level of the guiding message on the basis of the directive.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a lifesaving support apparatus.

The primary life support (BLS) is to maintain the chance of lifesaving for a victim who seems to have stopped breathing and pulsation due to the occurrence of an accident or incident, without using special equipment or medicine. It is a lifesaving measure. BLS consists mainly of cardiopulmonary resuscitation (CPR) consisting of chest compressions and artificial respiration, and an automated external defibrillator (AED). With the spread of AED in public facilities and streets, the public participation of BLS by the general public and the implementation rate of BLS are increasing.
Such accidents and incidents can occur in all ages, but the number of victims whose cardiopulmonary function stops tends to increase with age. In addition, victims tend to occur in an environment with relatively high noise, such as on the side of a road with relatively heavy traffic outdoors. On the other hand, many people can be disabled and lifesaving outside.

  Examples of devices for supporting BLS (hereinafter referred to as lifesaving support devices) include CPR devices and AEDs. Some life support devices present voice guidance, characters, and pictures for guiding an appropriate operation method to a lifesaving person. For example, U.S. Patent No. 6,057,049 detects a user interface configured to deliver a prompt to a caregiver to assist a caregiver performing cardiac resuscitation to a patient, and to detect the progress of the cardiac resuscitation performed by the caregiver. A sensor configured to provide a signal containing information indicative of ventilation, a memory in which a ventilation progress prompt is recorded to guide the rescuer to perform ventilation, and ventilation And a processor configured to process the output of the sensor to determine a parameter describing the progress of the sensor and to determine whether a ventilation progress prompt should be selected for delivery. The parameters of ventilation progress include ventilation rate, delivered tidal volume, and flow rate. The prompt includes a voice prompt for instructing the caregiver to confirm the patient's responsiveness by a voice message.

JP 2007-244879 A

However, Patent Document 1 does not describe means for adjusting the volume of a voice message. For example, a voice message may not be transmitted at a volume suitable for a lifesaving person in an environment where there is a lot of noise outdoors or when the user's hearing is insufficient. Therefore, the life-saving person may not understand how to use the life-saving support device and BLS may not be performed, or BLS may not be appropriately performed due to incorrect use.
The present invention has been made in view of the above points, and an object of the present invention is to provide a life-saving support apparatus that performs appropriate life-saving support to a user by voice.

  The present invention has been made in order to solve the above-described problems, and one aspect of the present invention recognizes a message output unit that outputs a life-saving support guidance message by using its own device, and utterance content of an input voice. A lifesaving support apparatus comprising: a voice recognition unit; and a level determination unit that extracts an instruction word for instructing an output level change from the utterance content and determines an output level of the guidance message based on the instruction word.

  According to the present invention, it is possible to perform lifesaving support appropriate for a user by voice.

It is a schematic block diagram which shows the structure of the lifesaving assistance apparatus which concerns on 1st Embodiment. It is a figure which shows the example of the level determination table which concerns on 1st Embodiment. It is a figure which shows an example of the message which concerns on 1st Embodiment. It is a flowchart which shows the lifesaving assistance process which concerns on 1st Embodiment. It is a schematic block diagram which shows the structure of the lifesaving assistance apparatus which concerns on 2nd Embodiment. It is a figure which shows the example of the level determination table which concerns on 2nd Embodiment. It is a figure which shows an example of the message which concerns on 2nd Embodiment. It is a figure which shows the other example of the message which concerns on 2nd Embodiment. It is a figure which shows the example of a guidance message display. It is a flowchart which shows the lifesaving assistance process which concerns on 2nd Embodiment.

(First embodiment)
Hereinafter, a first embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a schematic block diagram illustrating a configuration of a lifesaving support apparatus 10 according to the present embodiment.
The lifesaving support apparatus 10 includes a sound collection unit 111, a reproduction unit 112, a control unit 12, a power switch 131, a communication unit 132, an input unit 133, and a sensor 134. The lifesaving support device 10 is typically a CPR device, an AED, or the like. The lifesaving support device 10 may be an electronic device having a communication function realized by the communication unit 132, such as a mobile phone (including a so-called smartphone), a mobile terminal device (including a so-called tablet terminal device), and the like. .

The sound collection unit 111 records the incoming voice and outputs a voice signal representing the recorded voice to the control unit 12. The sound collection unit 111 includes a microphone that converts vibration caused by sound into an audio signal that is an electrical signal. Therefore, for example, a voice signal indicating a voice uttered by a user involved in the lifesaving support apparatus 10 is input to the control unit 12. The user is, for example, a lifesaving person who performs lifesaving support, a student who participates in a class, or the like. Elderly people whose hearing ability is not sufficient in daily life and persons with hearing impairment can also be users. The sound collection unit 111 may be a microphone array including a plurality of microphones.
The reproduction unit 112 reproduces voice based on the voice signal input from the control unit 12, for example, voice of a message for guiding life support (hereinafter referred to as guidance message voice). The reproduction unit 112 includes a speaker, for example. In addition, when reproducing the guidance message voice (for example, step 6-9 in FIG. 3), the reproducing unit 112 performs an operation related to life support at a predetermined time interval (for example, about 120 times per second) ( For example, a cue sound for controlling the speed of cardiopulmonary compression may be reproduced simultaneously. The cue sound may be reproduced from a reproduction unit (not shown) separate from the reproduction unit 112.

  The control unit 12 includes a control device (not shown) such as a central processing unit (CPU) and a storage unit 121, and operates a predetermined program read from the storage unit 121 to save a life. The operation of the entire support device 10 is controlled. The control unit 12 functions as a message output unit 123, a voice recognition unit 125, and a level determination unit 127. The storage unit 121 includes various storage media such as, for example, SRAM (Static Random Access Memory), flash ROM (Read-only Memory), SD (Secure Digital) memory card, hard disk drive (HDD: Hard-disk Drive), solid state. It is configured by any one of drives (SSD: Solid State Drive) or any combination thereof. The storage unit 121 stores, for example, an operating system (OS), device drivers, middleware, application programs, message data 122 indicating a guidance message, and other data as predetermined programs.

  The message output unit 123 reads the message data 122 stored in advance in the storage unit 121, and sequentially specifies the playback sections of the guidance message voice indicated by the read message data 122. The message output unit 123 changes the level (volume) of the guidance message voice in the specified playback section to the volume indicated by the output level determined by the level determination unit 127. The message output unit 123 outputs an audio signal indicating the guidance message audio whose volume has been changed to the reproduction unit 112. The time data indicating the time interval for reading the message data 122 and the reproduction time may be included in the message data, or may be stored in the message output unit 123 in advance.

  The voice recognition unit 125 uses the sound model stored in the sound model unit 126 for the voice signal input from the sound collection unit 111 to generate text data indicating the utterance content of the voice represented by the voice signal. The sound model includes an acoustic model and a language model. The acoustic model is a statistical model indicating the relationship between the phoneme to be recognized and the acoustic feature quantity, for example, a hidden Markov model (HMM). The language model is a statistical model indicating restrictions on the arrangement of phonemes, for example, N-grams, that is, phoneme (sequence) candidates subsequent to a certain phoneme (sequence) and their probabilities. The speech recognition unit 125 calculates an acoustic feature amount (eg, mel cepstrum) from the speech signal every predetermined time (eg, 10 ms), and calculates a likelihood for each phoneme sequence using the acoustic model for the calculated acoustic feature amount. To do. The speech recognition unit 125 specifies text data given by the phoneme string having the highest likelihood using a language model for the calculated phoneme string. The voice recognition unit 125 outputs the specified text data to the level determination unit 127.

In general, an acoustic model indicating the relationship between phonemes and acoustic features depends on the user. The sound model unit 126 may store in advance an acoustic model generated by using the uttered speech of each of a plurality of speakers. The speech recognition unit 125 may specify text data given by the phoneme string having the highest likelihood using a language model from the likelihood for each phoneme string calculated using the acoustic model for each speaker. Thereby, the fall of the speech recognition rate by a user's difference can be suppressed. For example, by using an acoustic model generated by maximizing likelihood based on an utterance accompanied by articulation disorder that is likely to occur in a hearing impaired person as an acoustic model of the speaker, the text data indicating the utterance content is specified. Can do.
The content of the utterance includes a phrase (hereinafter referred to as a change instruction word) that instructs to change the level of the guidance message voice. Examples of the change instruction word include “large”, “up” for instructing an increase in level, “small” for instructing a decrease in level, “down”, and the like. In this embodiment, since the vocabulary to be recognized can be limited to change directives for instructing level change, their synonyms, and other phrases related to the operation of the lifesaving support apparatus 10, a large amount of processing is required to search for recognition results And does not require memory.

  The level determination unit 127 extracts a change instruction word from the text data input from the speech recognition unit 125. The level determination unit 127 includes a repetition determination unit 128 that counts the number of repetitions of the change instruction word when the change instruction word is repeated or not from a series of text data. In the level determination unit 127, a default output level indicating the reference volume is determined in advance, and the output level is changed according to the extracted change instruction word. The level determination unit 127 determines the change amount of the output level so as to increase as the change instruction word is repeated, and changes the output level according to the determined change amount.

  The power switch 131 is configured to include a member for the user to instruct whether power is supplied (power ON) or not (power OFF), for example, a button, a knob, a touch sensor, and the like. . For example, it may be possible to detect whether the button is pressed or a change in the arrangement of the knob and turn the power on or off. Alternatively, the sensor may detect the opening of the case of the life support device 10 and turn the power on to save the life. The power supply may be turned off by detecting the storage of the support device 10 in the case. The lifesaving support apparatus 10 starts various processes when the power is turned on and stops the various processes when the power is turned off.

  The communication unit 132 communicates with other devices connected to the network, for example, various wireless devices such as mobile phones and server devices. The communication unit 132 may be connected to a network at the time of activation so that various types of data can be transmitted and received. For example, the communication unit 132 may transmit an audio signal indicating the voice of the user and receive an audio signal indicating the voice of a fireman or doctor at a fire department, a lifesaving center, or the like. In addition, the communication part 132 is the data (for example, electrocardiogram data) which shows the acquired patient's activity state, the data (for example, the time and frequency | count which gave defibrillation, cardiopulmonary resuscitation) Implementation status (described later) may be transmitted. The network may be a public wireless network or a short-range wireless network. The public wireless network is, for example, 3G (3rd Generation Mobile Telecommunications Technology), 4G, LTE (Long Term Evolution), IEEE (Institute of Electrical 6 and 80 of the Institute of Electrical and Electronic), etc. Good. The near field wireless network is based on IEEE 802.15.1, IEEE 802.15.4, ISO / IEC: International Organization for Standardization / International Electrotechnical Commission 14443, ISO / IEC 18092, ISO / IEC 18092, etc. It may be.

  The input unit 133 receives a user operation input and generates an operation signal for adjusting various operations of the lifesaving support apparatus 10. The input unit 133 includes, for example, a touch sensor, an input key (keyboard), a mouse, and the like. The level determination unit 127 may determine the output level based on the operation signal input from the input unit 133. Even if it is difficult to operate the input unit 133, such as a user who uses both hands when performing lifesaving support (for example, cardiopulmonary resuscitation) or a user who is unfamiliar with the operation, guidance for life support by voice is desired. Transmitted by volume.

The sensor 134 detects a movement or a change in arrangement of the lifesaving support apparatus 10. The sensor 134 includes, for example, an acceleration sensor, a gyro sensor, and the like. For example, when the lifesaving support device 10 is a CPR device, the detected information is based on the amount of change in the acceleration value in the XYZ-axis direction of the acceleration sensor from the implementation status of cardiopulmonary resuscitation (for example, the start time of chest compression, compression / Used to obtain the recoil time and number of times.
In addition, the lifesaving assistance apparatus 10 is provided with the assistance function part (not shown) for exhibiting the function. For example, when the lifesaving support apparatus 10 is an AED, the support function unit is an electrode pad. The electrode pad is used to acquire an electrical signal (electrocardiogram) indicating pulsation by being worn on the human body of the patient or to give defibrillation to the patient.

  Next, a specific example of output level determination processing by the level determination unit 127 will be described. In the message output unit 123, a level determination table that is data indicating the volume for each output level is set in advance. The message output unit 123 refers to the level determination table, and specifies the volume corresponding to the output level determined by the level determination unit 127. In the example shown in FIG. 2, the level determination table is associated with volume values −4 to 4 for each of the nine output levels from the lower limit (MIN) to the upper limit (MAX). Larger values indicate louder volume. The one-step volume difference indicates a volume difference of 5 dB, for example. The initial value (default) of the output level is 0, for example. The volume whose value is 0 is a preset reference volume. The notation of the volume value is not limited to the above-described example, and may be expressed by a dB value, for example.

  The level determination unit 127 specifies a series of text data sections which are units for counting the number of repetitions and whether or not the change instruction word is repeated. The level determination unit 127 performs a known voice detection process (VAD: Voice Activity Detection) to determine whether the voice section is likely to be uttered or the non-speech section that may not be uttered. For example, the level determination unit 127 determines a non-speech segment longer than a predetermined duration threshold (for example, 0.3 seconds) as an utterance break, and sets a section in which the preceding and following sections are divided by the determined utterance break. It is determined as a section of a series of text data.

  The level determination unit 127 determines the presence / absence of a change instruction word in a series of text data sections. The level determination unit 127 determines that the amount of change is positive when a change instruction meaning an increase in output level is detected, and detects a change amount when a change instruction indicating a decrease in output level is detected. The positive / negative of is determined to be negative. The level determination unit 127 counts the number of repetitions of the change instruction word, and determines the amount of change in the output level according to the counted number of repetitions and the change instruction word. For example, the level determination unit 127 detects “large” as the change instruction word, and determines the increase amount of the output level when there is no repetition of the detected “large” (the number of repetitions is 1) as one stage. Further, the level determination unit 127 detects “down” as the change instruction word, and when the detected “down” is repeated three times (the detected utterance is “down down down”), the output level decreases. The amount is defined as 3 levels. In addition, when the level determining unit 127 detects “large” and “up” once as change instruction words (the detected utterance is “largely up”), the level determination unit 127 sets the number of repetitions of the change instruction word indicating an increase to 2 It is determined that the output level is increased twice. When the sum of the output level before the change and the increase amount exceeds the upper limit (MAX), the level determination unit 127 determines the output level as the upper limit (MAX). When the sum of the output level before the change and the decrease amount is lower than the lower limit (MIN), the level determination unit 127 determines the output level as the lower limit (MIN).

  The level determination unit 127 may determine the output level according to the ambient sound indicated by the audio signal input from the sound collection unit 111. For example, the level determination unit 127 calculates the level of the audio signal in the non-speech section as the level of the ambient sound. Determine the level. And the level determination part 127 may further change an output level based on a change instruction word and the repetition frequency with the method mentioned above with respect to the output level defined according to the level of ambient sound.

Note that while the message output unit 123 is outputting the audio signal to the reproduction unit 112, the level determination unit 127 may determine to increase the output level (change amount is positive). In that case, the message output unit 123 changes the volume of the output guidance message voice to the volume indicated by the newly determined (increased) output level, and indicates the guidance message voice whose volume has been changed. The audio signal is output to the playback unit 112. Thereby, even when the volume before the output level is increased is too low to hear the message, the guidance message voice is repeatedly reproduced at the increased volume. The start time of the guidance message sound to be repeatedly played is not necessarily limited to the beginning of the message, and may be, for example, at the beginning of a step played at the time when an increase in volume is instructed or before that step.
In that case, the message output unit 123 outputs an audio signal indicating a message for confirming an increase in the output level to the reproduction unit 112. Such a message is, for example, a message “Do you want to increase the volume?”. Therefore, the user is prompted to give an instruction to increase the volume again.

Note that when the message output unit 123 is outputting a voice signal, the voice recognition unit 125 stops voice recognition for the voice signal input from the sound collection unit 111, and the message output unit 123 receives the voice signal. When the output is stopped, voice recognition may be performed on the voice signal input from the sound collection unit 111. Thereby, since the superimposition of the voice by the user's utterance and the guidance message voice reproduced by the reproduction unit 112 is avoided, the voice recognition unit 125 can accurately recognize the content of the user's utterance.
The sound collection unit 111 includes a microphone array including a plurality of microphones, and includes a sound source separation unit (not shown) that performs sound source separation processing (GSS: Geometric Source Separation), and has a directivity main axis in the direction of the user. You may record it with audio. In that case, the input of the audio signal from the sound collection unit 111 and the output of the audio signal from the message output unit 123 may be performed simultaneously.

Next, an example of a message indicated by the message data 122 will be described.
FIG. 3 is a diagram illustrating an example of a message. The example shown in FIG. 3 is an example of a message used when the lifesaving support apparatus 10 is a CPR apparatus, and is composed of nine steps. The message output unit 123 once outputs the audio signal according to Step 1-9 consistently, and then repeatedly outputs the audio signal according to Step 7-9. As shown in step 1, the message output unit 123 reproduces a message voice indicating that the volume can be changed based on the change instruction word spoken by the user, so that the user is guided to the usage.

Next, an example of lifesaving support processing according to the present embodiment will be described.
FIG. 4 is a flowchart showing a lifesaving support process according to the present embodiment.
(Step S101) When the power switch 131 is turned on (YES in Step S101), the lifesaving support apparatus 10 starts various processes, and then proceeds to Step S102. When the power switch 131 is not turned on (NO in step S101), the processing after step S102 is not performed, and it is awaited that the power is turned on.
(Step S <b> 102) The message output unit 123 reads the message data 122 stored in advance in the storage unit 121. Thereafter, the process proceeds to step S103.

(Step S103) The voice recognition unit 125 performs voice recognition on the voice signal input from the sound collection unit 111, and generates text data indicating the utterance content. The level determination unit 127 determines whether or not the change instruction word is extracted from the series of text data generated by the voice recognition unit 125. If extracted (YES in step S103), the process proceeds to step S104. If not extracted (NO in step S103), the process proceeds to step S108.
(Step S104) The level determination unit 127 determines whether or not the repetition of the change instruction word is detected in the series of text data. When the repetition is detected (step S104 YES), the process proceeds to step S106. If no repetition is detected (NO in step S104), the process proceeds to step S105.
(Step S105) The level determination unit 127 determines the amount of change in level as a basic change amount (for example, 1). Thereafter, the process proceeds to step S107.
(Step S106) The level determining unit 127 determines the amount of level change according to the number of times the change instruction word is repeated in a series of text data. Thereafter, the process proceeds to step S107.

(Step S107) The level determination unit 127 changes the output level according to the determined amount of change. The changed output level is within a range from a predetermined lower limit (MIN) to an upper limit (MAX). The level determination unit 127 controls the volume of the guidance message voice output from the message output unit 123 to the volume specified by the determined output level. Thereafter, the process proceeds to step S108.
(Step S <b> 108) The message output unit 123 sequentially outputs an audio signal indicating the guidance message audio to the reproduction unit 112. Thereafter, the process proceeds to step S109.

(Step S109) While the message output unit 123 outputs the audio signal to the reproduction unit 112, the level determination unit 127 determines whether or not to determine the positive output level change amount (volume increase). If it is determined to be determined (step S109 YES), the process returns to step S108. If it is not determined to be determined (NO in step S109), the process proceeds to step S110.
(Step S110) When the power switch 131 is turned off (YES in Step S110), the lifesaving support apparatus 10 ends various processes, and then ends the process shown in FIG. If the power switch 131 is not turned off (step S110 OFF), the process returns to step S102.

The lifesaving support apparatus 10 according to the present embodiment includes a message output unit 123 that outputs a lifesaving guidance message by using the own apparatus, and a voice recognition unit 125 that recognizes the utterance content of the input voice. In addition, the lifesaving support apparatus 10 includes a level determination unit 127 that extracts an instruction word for instructing a change in output level from the utterance content and determines an output level of the guidance message based on the instruction word.
With this configuration, the user can give an instruction to change the output level of the guidance message by voice during lifesaving support without performing any special operation. Therefore, according to the lifesaving assistance apparatus 10, appropriate lifesaving assistance is realizable by a guidance message.

Moreover, the level determination part 127 changes an output level based on the variation | change_quantity according to the repetition frequency of an instruction word.
With this configuration, the user can easily indicate the degree of change in the output level with the number of repetitions of the instruction word.

Further, the message output unit 123 causes the reproduction unit 112 to reproduce the guidance message sound indicating the guidance message at the volume changed by the level determination unit 127.
With this configuration, the user can instruct to change the volume of the guidance message voice with the utterance voice during the lifesaving support without performing any special operation. Even if the user is not limited to a normal hearing person, even if the user is an elderly person or a hearing-impaired person, the sound volume corresponding to his / her hearing ability and environment can be instructed easily. it can.

When the message output unit 123 causes the reproduction unit 112 to reproduce the guidance message voice and the level determination unit 127 increases the volume, the message output unit 123 outputs the guidance message with the increased volume.
With this configuration, even when it is difficult to listen because the volume of the guidance message voice that has already been output is low, at least a part of the guidance message voice with the increased volume is repeatedly reproduced. The content of the guidance message voice is reliably transmitted to the user, and appropriate life support can be realized.

(Second Embodiment)
Next, a second embodiment of the present invention will be described. About the same structure as embodiment mentioned above, the same code | symbol is attached | subjected and the description is used.
FIG. 5 is a schematic block diagram showing the configuration of the lifesaving support apparatus 10A according to the present embodiment.
The lifesaving support apparatus 10A includes a sound collection unit 111, a reproduction unit 112, a display unit 113A, a control unit 12A, a power switch 131, a communication unit 132, an input unit 133, and a sensor 134.
The display unit 113A displays an image based on the image signal input from the control unit 12A, for example, an image for guiding rescue support (hereinafter, a guidance message display). The guidance message display will be described later. The display unit 113 </ b> A is, for example, a liquid crystal display (LCD), an organic EL display (Organic Electro-luminescence display), or the like.

12 A of control parts are comprised including the memory | storage part 121, and operate | move a predetermined program similarly to the control part 12, and control operation | movement of the lifesaving assistance apparatus 10 whole. The control unit 12A functions as a message output unit 123A, a voice recognition unit 125, and a level determination unit 127.
In the storage unit 121, message data 122A is stored in advance. The message data 122A is data formed by associating a guidance message display with a guidance message voice. In the guidance message display, a picture showing how to use the life support apparatus 10A, a message character indicating the use method, a picture showing a measure relating to life support (not limited to the use method of the life support apparatus 10A), and use thereof Message text indicating the method.

The message output unit 123A reads the message data 122A from the storage unit 121, and sequentially specifies the playback sections of the guidance message voice indicated by the read message data 122A. The message output unit 123A specifies a display section corresponding to the specified playback section among the guidance message displays indicated by the read message data. The message output unit 123A stores in advance a level determination table, which is data formed by associating the volume, character size, and drawing size with each output level.
The message output unit 123A refers to the level determination table, determines the volume corresponding to the output level determined by the level determination unit 127, and changes the volume of the guidance message voice in the specified playback section to the determined volume. The message output unit 123A outputs an audio signal indicating the guidance message audio whose volume has been changed to the reproduction unit 112.

  The message output unit 123A determines a character size and a drawing size corresponding to the output level determined by the level determination unit 127 with reference to the level determination table. The message output unit 123A changes the character size and graphic size of the guidance message display in the specified display section to the predetermined character size and graphic size, respectively. The message output unit 123A combines the image signals indicating the guidance message display in which the character size and the drawing size are changed, and outputs the combined image signal to the display unit 113A.

  Next, an example of the level determination table according to the present embodiment will be described. The level determination table shown in FIG. 6 is formed by associating the value of the character size and the value of the graphic size in addition to the value of the volume for each of the nine output levels. The larger the output level, the larger the character size value and the larger graphic size value associated with each other. The larger each value, the larger the display size. The character size and graphic size having a value of 0 indicate a preset standard character size and standard graphic size (default), respectively. The notation of the character size value and the drawing size value is not limited to this. For example, the value of the character size may be expressed by a font size, and the value of the graphic size may be expressed by a coordinate value.

The upper limit of the character size value and the graphic size value may be provided at an output level lower than the upper limit (MAX) of the output level. This is because the characters and drawings constituting the guidance message display displayed at one time are stored in the display area of the display unit 113A so that the characters and part of the drawing do not protrude from the display area (FIG. 9). reference). In the example shown in FIG. 6, 3 is associated with the upper limit of the character size value with three or more output levels, and 1 is associated with the upper limit of the graphic size value with one or more output levels.
The lower limit of the character size value and the drawing size value may be provided at an output level higher than the lower limit (MIN) of the output level. This is to ensure the visibility of characters and drawings constituting the guidance message display displayed at one time, and to prevent the user from being able to discriminate because they are too small (see FIG. 9). In the example shown in FIG. 6, the lower limit (−1) of the character size value is associated with an output level of −1 or less, and the lower limit (−2) of the graphic size value is associated with an output level of −2 or less. .

In the above description, it is assumed that the message output unit 123A outputs the image signal related to the display section in synchronization with the output timing of the audio signal related to the playback section corresponding to the display section. This is not a limitation. When the ambient sound level is equal to or lower than the predetermined second threshold, the message output unit 123A does not output the image signal indicating the guidance message display, and the ambient sound level is higher than the predetermined second threshold. The image signal may be output, and the output of the audio signal indicating the guidance message audio may be stopped. The second threshold is a value larger than the first threshold described above. As a result, when it is difficult to listen to the guidance message voice due to a high noise level, the reproduction of the unnecessary guidance message voice is stopped, and effective life support is provided by displaying the guidance message.
Further, when the voice recognition unit 125 does not succeed in voice recognition, an image signal indicating guidance message display may be output, and output of the voice signal indicating guidance message voice may be stopped. Thereby, even when the volume cannot be controlled by utterance, effective life support is provided by displaying the guidance message.

Next, an example of a message indicated by the message data 122A will be described.
FIG. 7 is a diagram illustrating an example of a message. The example shown in FIG. 7 is an example of a message used when the lifesaving support apparatus 10A is an AED, and includes 12 steps. Each step is composed of a voice and a character. For example, steps 3 and 5 further include drawings. In other steps, a drawing may be included. As shown in step 1, the message output unit 123 reproduces a message voice indicating that the volume can be changed based on the change instruction word spoken by the user, so that the user is guided to the usage. The message output unit 123 once outputs the audio signal and the image signal according to Step 1-12 consistently, and then repeatedly outputs the audio signal and the image signal according to Step 10-12. However, the message output unit 123A outputs the audio signal and the image signal according to Step 6-12 at a predetermined time interval (for example, about 2 minutes). The predetermined time interval may be arbitrarily set according to the time interval for performing the ECG examination and defibrillation.
When the control unit 12A determines that defibrillation is unnecessary based on the electrocardiogram acquired in step 6, instead of the audio signal and the image signal according to steps 7 and 8, “an electric shock is unnecessary. The audio signal and the image signal related to the message “are output. Further, the control unit 12A outputs a voice signal and an image signal related to a message “shock is completed” after the user presses a blinking button as an example of the input unit 133 and executes defibrillation. To do.

FIG. 8 is a diagram illustrating another example of the message. The example shown in FIG. 8 is an example of a message used when the lifesaving support apparatus 10A is an AED with a communication function, and is composed of 16 steps. Each step is composed of speech and characters. For example, steps 7 and 9 include drawings. In other steps, drawings may be included. As shown in step 1, the message output unit 123 reproduces a message voice indicating that the volume can be changed based on the change instruction word spoken by the user, so that the user is guided to the usage. The message output unit 123 once outputs the audio signal and the image signal according to Step 1-16 consistently, and then repeatedly outputs the audio signal and the image signal according to Step 14-16. However, the message output unit 123 outputs the audio signal and the image signal according to Step 10-16 at a predetermined time interval (for example, about 2 minutes).
If the control unit 12A determines that an electric shock is unnecessary based on the electrocardiogram acquired in step 10, it replaces the audio signal and the image signal according to steps 11 and 12, and “an electric shock is not necessary.” The audio signal and the image signal related to the message are output.
In step 5, the communication function of the communication unit 132 may be available. In this case, the control unit 12A outputs an audio signal related to the message “Contact 119”. However, if the communication function of the communication unit 132 cannot be used because it is in an environment where radio waves from the wireless network do not reach, the control unit 12A says “Please contact 119”. An audio signal related to the message may be output.

Next, guidance message display displayed on the display unit 113A will be described. FIG. 9 shows an example of guidance message display according to step 5 in FIG. 7 or step 9 in FIG. In this example, one step corresponds to one display section.
FIGS. 9A to 9E are guidance message displays when the output levels are −2, −1, 0, 1 and 2, respectively. Of these, FIG. 9C shows the default display of the guidance message when the output level is zero. The volume, character size, and drawing size are all 0.
FIGS. 9A and 9B show the guidance message display that is displayed when an output level lowering (“small”, “down”, etc.) is instructed from the output level 0 as a starting point. An example of In the example shown in FIG. 9A (output level-2), the volume, character size, and graphic size values are -2, -1, and -2, respectively. In the example shown in FIG. 9B (output level −1), the volume, character size, and graphic size values are −1, −1, and −1, respectively.
FIGS. 9D and 9E show the guidance message display that is displayed when an output level increase (“large”, “up”, etc.) is instructed from the output level 0 as a starting point. An example of In the example shown in FIG. 9D (output level 1), the values of volume, character size, and graphic size are 1, 1, and 1, respectively. In the example shown in FIG. 9E (output level 2), the volume, character size, and graphic size values are 2, 2, and 1, respectively.
As described above, when the level of the ambient sound is greater than the predetermined first threshold and not more than the predetermined second threshold, the default output level is greater than 0 and the upper limit (MAX) You may change into the following (for example, 1).

  Note that the number of characters displayed at one time, the presence or absence of a drawing, and the size of the drawing vary from step to step. Therefore, different level determination tables may be used depending on the steps. For example, the upper limit of the character size value set in the level determination table may be smaller as the number of characters is larger, and may be larger as the number of characters is smaller. For the step without a graphic, the graphic size value item may be omitted. Further, the upper limit of the graphic size value set in the level determination table used for a step with a graphic may be larger as the default graphic is smaller and smaller as the default graphic is larger. It should be noted that a common level determination table may be used between steps where the upper limit and lower limit of the character size and graphic size values are common. If there is a drawing, the item of the drawing size value is referred to. If there is no drawing, the item of the drawing size value may be ignored.

Next, an example of lifesaving support processing according to the present embodiment will be described.
FIG. 10 is a flowchart showing a lifesaving support process according to the present embodiment.
In step S101, when the power switch 131 is turned on (YES in step S101), the process proceeds to step S102A.
(Step S102A) The message output unit 123A reads the message data 122A stored in advance in the storage unit 121. Then, the process of step S103-S106 is performed.
(Step S107A) The level determination unit 127 changes the output level according to the determined change amount. However, the changed output level is within a range from a predetermined lower limit (MIN) to an upper limit (MAX). The level determination unit 127 controls the volume of the guidance message voice output by the message output unit 123A to the volume specified by the determined output level. Further, the level determination unit 127 controls the character size and graphic size of the guidance message display output by the message output unit 123A to the character size and graphic size (display size) specified by the determined output level. When the character size and the upper and lower limits of the graphic size are set in the level determination table, the designated character size and graphic size are within the set upper and lower limits. Thereafter, the process proceeds to step S108A.
(Step S108A) The message output unit 123A sequentially outputs an audio signal indicating the guidance message voice to the reproduction unit 112, and sequentially outputs an image signal indicating the guidance message display to the display unit 113A. Thereafter, the process proceeds to step S109 and subsequent steps.

In the lifesaving support apparatus 10 according to the present embodiment, the message output unit 123A causes the display unit 113A to display a guidance message display indicating a guidance message with the size determined by the level determination unit.
With this configuration, the user can instruct to change the size of the display of the guidance message with the utterance voice during the lifesaving support without performing any special operation. Since the user can easily indicate a desired size by voice, it is possible to realize appropriate lifesaving support by displaying a guidance message.

The embodiment described above can also be implemented in the following manner.
(1) A message output unit for outputting a lifesaving guidance message by using the own device, a voice recognition unit for recognizing the utterance content of the input voice, and an instruction word for instructing change of the output level from the utterance content A life support apparatus comprising: a level determination unit that determines an output level of the guidance message based on the instruction word.
(2) The lifesaving support apparatus according to (1), wherein the level determination unit changes the output level based on a change amount corresponding to the number of repetitions of the instruction word.
(3) In the lifesaving support apparatus according to (1) or (2), the message output unit causes the reproduction unit to reproduce the guidance message sound indicating the guidance message at the output level changed by the level determination unit.
(4) In the lifesaving support apparatus according to (3), when the message output unit causes the reproduction message to be reproduced by the message output unit and the level determination unit increases the output level, the message output unit The guidance message is output at the increased output level.
(5) The lifesaving support apparatus according to any one of (1) to (4), wherein a guidance message display indicating the guidance message is displayed on the display unit at an output level determined by the level determination unit.

  As described above, the embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to the above, and various design changes and the like can be made without departing from the scope of the present invention. It is possible to For example, unlike the examples shown in FIGS. 2 and 6, it is assumed that the smaller the level defined in the level determination table is, the larger the volume, the character size, and the drawing size are. In that case, the level change amount determined by the level determination unit 127 may be any one in which positive and negative are reversed from those described above. Taking step S109 (FIGS. 4 and 10) as an example, when the level determination unit 127 increases the volume or the like, the negative change amount is determined instead of determining the positive change amount.

DESCRIPTION OF SYMBOLS 10, 10A ... Lifesaving support apparatus, 111 ... Sound collection part, 112 ... Playback part, 113A ... Display part, 12, 12A ... Control part, 121 ... Memory | storage part, 123, 123A ... Message output part, 125 ... Voice recognition part, 127: Level determining unit, 131: Power switch, 132 ... Communication unit, 133 ... Input unit, 134 ... Sensor

Claims (5)

A message output unit for outputting a lifesaving support guidance message by using its own device;
A speech recognition unit that recognizes the utterance content of the input speech;
A level determining unit that extracts an instruction word that instructs to change an output level from the utterance content, and determines an output level of the guidance message based on the instruction word;
A life support device comprising:   The lifesaving support apparatus according to claim 1, wherein the level determination unit changes the output level based on an amount of change corresponding to the number of repetitions of the instruction word.   3. The lifesaving support apparatus according to claim 1, wherein the message output unit causes the reproduction unit to reproduce the guidance message sound indicating the guidance message at the output level changed by the level determination unit.   The message output unit outputs the guidance message at the increased output level when the message output unit causes the reproduction unit to reproduce the guidance message voice and the level determination unit increases the output level. Item 4. The lifesaving support apparatus according to Item 3.   5. The lifesaving support apparatus according to claim 1, wherein the message output unit causes the display unit to display a guidance message display indicating the guidance message at an output level determined by the level determination unit.

Images