TWM608249U - Audio recognition conversion and intelligent restoration communication device for rescue - Google Patents

Abstract

This creation is to provide an audio recognition conversion and intelligent restoration communication device for rescue use, which includes: at least one communication device, which is provided with a processing unit, and the processing unit is coupled to an environmental monitoring device, a physiological recognition device, a radio device, and A communication module, the processing unit is to perform voice recognition on the volume value and content of the radio device and convert it into text messages; a master control terminal is provided with an analysis module, and the analysis module is coupled to a Audio database, an audio playback unit, and a communication unit. The analysis module analyzes the volume value, semantics, physiological detection value, and environmental detection value of the text message to determine the urgency of the text message for playback Corresponding text audio; in this way, when a major disaster occurs and the mobile phone cannot communicate, this creation can use a long-distance low-bandwidth communication system to convert the voice into text for communication, and can be based on semantics, physiological detection values, and The environmental detection value judges whether the disaster relief personnel wearing the communication device prompts important information or encounters danger, so as to facilitate the commander at the main control terminal to control the progress, safety, location and condition of the disaster relief personnel, and to dispatch and command to improve the efficiency of disaster relief By.

Description

Audio recognition conversion and intelligent restoration communication device for rescue

This creation is to provide a kind of audio recognition conversion and intelligent restoration communication device for rescue, especially a kind of voice conversion to text transmission to reduce the use bandwidth, suitable for emergency communication occasions, and intelligently based on semantics and physiological detection The value and the environmental detection value are restored with human voice, so as to facilitate the judgment of the disaster relief situation.

On the other hand, fires, earthquakes and other disasters often cause heavy casualties; and after disasters, government or private rescuers often need to go to the disaster area for rescue. The degree of hard work is self-evident, and the basic fire-fighting and disaster relief equipment often weighs 20 to 20. 30 kilograms, which is quite heavy and difficult to move, and makes the use of communication devices extremely inconvenient. Therefore, rescue personnel are often in a state of individual combat, and their own risk index increases. They usually rely on experienced rescue personnel. In order to save people and get out of trouble in dangerous situations.

Technology is advancing with each passing day, and semiconductor technology is also improving day by day. The current mobile communication equipment is developed, and the equipment for detecting environmental information or life information can be miniaturized or even wearable. However, in the scene of a disaster, sometimes mobile communication cannot be used. For example, the 311 earthquake in Japan caused the main communication base station to collapse. Recently, KT, the largest telecommunications company in South Korea, had a fire in its branch office building on Chungjeong Road, Seodaemun District, Seoul, which made the surrounding general communication equipment unavailable. People in difficulty can only rely on traditional communication equipment that is bulky and heavy for signal transmission.

Not only that, because of the higher bandwidth of the conventional temporary base station, the transmission distance is shorter, and in the disaster relief environment, it is shielded by the collapsed building, which makes the signal transmission difficult. If the rescuer goes deep into the disaster area, it is difficult to transmit the signal. Communication will be interrupted, resulting in the inability to communicate with the disaster relief command center in real time, and the on-site commander will not be able to issue disaster relief orders in time, and will not be able to know the current situation and location of the rescuers. This will delay the rescue opportunity, and even worse, if the rescue is When personnel encounter an emergency, they will not be able to provide assistance in time, and there will be unpredictable dangers for rescuers and victims.

In addition, although there are portable physiological devices that can monitor physiological conditions, such as apple watch, Samsung S3, and Xiaomi bracelets, they are only used to monitor personal physiological conditions, and the emergency field time is very precious and urgent. Therefore, rescuers cannot focus on the existing information. Moreover, even if the physiological information can be transmitted to the temporary base station, as mentioned above, it has the problem of signal interruption, so it is difficult to exert its effect on the rescue scene.

As far as voice-to-text conversion is concerned, today there are voice recognition software such as google voice and apple siri, and computer dictionaries also have the function of converting between text and voice. However, even if text messages are transferred after conversion, it is still difficult to grasp the exact status. Or it is urgency, and the time on the first aid site is very precious and urgent, and the commander cannot concentrate on reading all the text messages, so the rescue commander is still unable to actually grasp the rescue situation and situation.

In view of this, the author specially researched and improved the communication methods used in disasters, hoping to improve the above problems with a better design, and after long-term research and development and continuous testing, the original creation came out.

The purpose of this creation is to solve the aforementioned problems. In order to achieve the above goals, our inventors provide an audio recognition conversion and intelligent restoration communication device for rescue, which includes: at least one communication device, which is provided with a processing unit The processing unit is coupled to an environmental monitoring device, a physiological recognition device, a radio device, and a communication module. The environmental monitoring device is used to detect the environment and form an environmental detection value; and the physiological recognition device is The physiological signal is measured and a physiological detection value is formed. The processing unit performs voice recognition on the volume value of the sound of the radio device and the content of the radio and converts it into a text message. The processing unit converts the text message and the environment into a text message. The detection value and the physiological detection value are transmitted through the communication module; and a host terminal, which is provided with an analysis module, the analysis module is coupled to an audio database, an audio playback unit and a communication Unit, the analysis module receives the signal transmitted by the processing unit through the communication unit, and analyzes the volume value, semantics, physiological detection value, and environmental detection value of the text message to determine the urgency of the text message, The audio database stores the volume, intonation and text audio corresponding to the urgency level, and the analysis module selects the corresponding text audio player according to the urgency level.

According to the above-mentioned audio recognition conversion and intelligent restoration communication device for rescue, the processing unit is further coupled to a sound effect playback device, and the analysis module is coupled to a radio unit, and the host uses the radio The unit receives the sound, and is converted into a text signal by the analysis module, and then transmitted to the communication module of the communication device through the communication unit, and the text signal is converted into a sound message by the processing unit, and the text signal is converted into a voice message by the processing unit. The speaker of the sound effect playback device.

According to the above-mentioned audio recognition conversion and intelligent restoration communication device for rescue use, the communication module and the communication unit are transmitted through a Low-Power Wide-Area Network (LPWAN).

According to the above-mentioned audio recognition conversion and intelligent restoration communication device for rescue use, the low-power wide area network is LoRaWAN.

According to the above-mentioned audio recognition conversion and intelligent restoration communication device for rescue use, the environmental monitoring device is used to detect the temperature, carbon dioxide concentration, air pressure, smoke concentration and location information of the environment.

According to the above-mentioned audio recognition conversion and intelligent restoration communication device for rescue, the position information is obtained by the communication device between the environmental monitoring devices and the analysis module of the host Calculate the winner through triangulation.

According to the above-mentioned audio recognition conversion and intelligent restoration communication device for rescue use, the position information is obtained by GPS or GNSS global satellite navigation system positioning.

According to the aforementioned audio recognition conversion and intelligent restoration communication device for rescue use, the physiological recognition device is used to detect blood oxygen and heartbeat.

According to the aforementioned audio recognition conversion and intelligent recovery communication device for rescue, the analysis module is further coupled to a display unit corresponding to the environmental detection value of the communication device.

Based on the above description and settings, it is obvious that this creation mainly has the following advantages and functions, which are detailed as follows:

1. This creative system can convert voice to text transmission to reduce the bandwidth used for emergency communication. It can be intelligently restored with human voice based on semantics, physiological detection values and environmental detection values, so as to facilitate the judgment of disaster relief Whether the personnel prompts important information or encounters danger, so as to facilitate the commander at the main control end to control the progress, safety, location and status of the disaster relief personnel, and to dispatch and command to improve the efficiency of disaster relief.

This creation is an audio recognition conversion and intelligent restoration communication device used for rescue. Its implementation methods, characteristics and effects are listed in several preferred and feasible embodiments and are described in detail below in conjunction with the diagrams for an in-depth understanding. And agree with this creation.

First of all, please refer to Figures 1 to 3. This creation is an audio recognition conversion and smart restoration communication device for rescue use. The execution steps include:

S001: At least one communication device 1 is provided, which can be a wearable device or a mobile communication device, such as a mobile phone, walkie-talkie, etc., and preferably, as shown in Figure 3, the communication device 1 can be directly installed in rescue applications Wearable equipment, such as helmets or face masks, for disaster relief personnel to wear, the communication device 1 is provided with a processing unit 11, the processing unit 11 is coupled to an environmental monitoring device 12, a physiological identification device 13, and a radio device 14 And a communication module 15, and radio is performed by the radio device 14;

S002: The environmental monitoring device 12 is used to detect the environment and form an environmental detection value. The environmental monitoring device 12 is used to detect the temperature, carbon dioxide concentration, air pressure, smoke concentration, and location information of the environment. It can be known that the environmental monitoring device 12 has or includes the functions of a temperature sensing device, a carbon dioxide detector, a barometer, a smoke detector, and a global satellite navigation system positioning device such as GPS and GNSS; the physiological recognition device 13 is to detect physiological signals and form a physiological detection value. The physiological recognition device 13 is used to detect blood oxygen and heartbeat. Therefore, if it is known, the physiological recognition device 13 can be worn on the artery of the user. To facilitate the measurement of blood oxygen and heartbeat;

S003: The processing unit 11 performs voice recognition on the volume value of the sound received by the radio device 14 and its content and converts it into text messages. The processing unit 11 converts the volume value, text messages, environmental detection values, and physiological values. The detected value is signaled through the communication module 15;

S004: Set up a main control terminal 2, which is provided with an analysis module 21. The analysis module 21 is coupled to an audio database 22, an audio playback unit 23 and a communication unit 24. In one embodiment, the The communication module 15 and the communication unit 24 are transmitted through a Low-Power Wide-Area Network (LPWAN). Specifically, the low-power wide-area network is LoRaWAN; the analysis module 21 is The communication unit 24 receives the signal transmitted by the processing unit 11, and analyzes the volume value, semantics, physiological detection value, and environmental detection value of the text message to determine the urgency of the text message. The audio database 22 stores Corresponding to the urgency of the volume, intonation, and text audio, the analysis module 21 selects the corresponding text audio player according to the urgency; and in a specific embodiment, it can be trained by a trainer The urgency of the text message is related to the generation of the text audio, so that the analysis module 21 can select the corresponding text audio and play it. This training method is a conventional technology, so it will not be repeated here.

In a specific embodiment, the main control terminal 2 can be set up in a disaster relief command center, so that when an accident occurs and the communication base station collapses and mobile phone communication cannot be used, a low-power wide area network can be set up The main control terminal 2 of channel transmission, and all disaster relief personnel wear communication device 1, so that through the long-distance low-bandwidth communication system, the voice is converted into text for communication, and can be based on semantics, physiological detection values and environmental detection It can be used to judge whether the disaster relief personnel wearing the communication device 1 prompt important information or encounter danger, so as to facilitate the commander at the main control terminal 2 to control the progress, safety, location and status of the disaster relief personnel, so as to improve the efficiency of disaster relief.

As far as semantic analysis is concerned, in one embodiment, it can be analyzed by a classifier, which is a conventional technology, so it will not be repeated here. In other embodiments, it can be used alone or in conjunction with the aforementioned The semantic classifier uses an operational amplifier (Operational Amplifier, OPA) to generate the wave pattern of the heartbeat of the rescuer when speaking, as shown in Figure 4, and to judge whether his mood and heartbeat are based on the degree of change and frequency of his heart rhythm If there is an abnormality, and after being trained by the trainer, it can assist in determining whether the semantic meaning has a critical component, so that the analysis module 21 can select the corresponding text and audio to play.

Regarding the positioning of the location information of the environmental monitoring device 12, in one embodiment, in addition to positioning by the aforementioned GPS, GNSS and other global satellite navigation system positioning devices, in another embodiment, it can also be by multiple communications The environment monitoring device 12 of the device 1 and the analysis module 21 of the main control terminal 2 are assisted in positioning through the triangulation method, which can improve the accuracy of position positioning.

In another embodiment, the processing unit 11 is further coupled to a sound effect playback device 16, and the analysis module 21 is coupled to a radio unit 25. The analysis module 21 converts into a text signal and transmits it to the communication module 15 of the communication device 1 through the communication unit 24, and converts the text signal into a voice message via the processing unit 11. The sound effect playback device 16 performs playback, so that the master terminal 2 can direct the disaster relief personnel and call and report the information.

In summary, the technical means disclosed in this creation is not only unprecedented, but also achieves the expected purpose and effect. Therefore, it is both novel and progressive. It is truly a new type in the patent law. In terms of structure, it has indeed met the statutory requirements of the Patent Law, and Yan has filed a new patent application in accordance with the law.

However, the above are only preferred embodiments of this creation, and should not be used to limit the scope of implementation of this creation, that is, all equivalent changes and modifications made in accordance with the scope of the patent application for this creation and the contents of the specification should still be used. It belongs to the scope of this creation patent.

1: Communication device 11: Processing unit 12: Environmental monitoring device 13: Physiological identification device 14: Radio device 15: Communication module 16: Sound effect playback device 2: Master 21: Analysis module 22: Audio database 23: Audio playback unit 24: Communication unit 25: Radio unit S001~S004: steps

Figure 1 is a schematic diagram of the structure of this creation. Figure 2 is the flow chart of this creation. Figure 3 is a schematic diagram of the usage status of this creation. Figure 4 is a sine wave pattern generated by this creation through an operational amplifier.

1: Communication device

11: Processing unit

12: Environmental monitoring device

13: Physiological identification device

14: Radio device

15: Communication module

16: Sound effect playback device

2: Master

21: Analysis module

22: Audio database

23: Audio playback unit

24: Communication unit

25: Radio unit

Claims (9)

An audio recognition conversion and intelligent restoration communication device for rescue, which includes: At least one communication device is provided with a processing unit coupled to an environmental monitoring device, a physiological identification device, a radio device and a communication module, the environmental monitoring device is used to detect the environment and form an environmental detection Measured value; and the physiological recognition device detects physiological signals and forms a physiological detection value, and the processing unit performs voice recognition on the volume value of the radio device and the content of the radio and converts it into text messages , The processing unit transmits the volume value, text message, environmental detection value and physiological detection value through the communication module; and A master control terminal is provided with an analysis module, the analysis module is coupled to an audio database, an audio playback unit and a communication unit, the analysis module receives the signal transmitted by the processing unit through the communication unit , And analyze the volume value, semantics, physiological detection value and environmental detection value of the text message to determine the urgency of the text message. The audio database stores the volume, intonation and text audio corresponding to the urgency , The analysis module selects the corresponding text audio player according to the urgency. For example, the audio recognition conversion and intelligent recovery communication device for rescue use as described in the first item of the patent application, wherein the processing unit is further coupled to a sound effect playback device, and the analysis module is coupled to a radio unit, and the master control terminal The sound is received by the radio unit, converted into a text signal by the analysis module, and then transmitted to the communication module of the communication device through the communication unit, and the text signal is converted into sound by the processing unit Message, and played by the sound effect playback device. For example, the audio recognition conversion and intelligent restoration communication device for rescue use described in item 1 or 2 of the scope of patent application, wherein the communication module and the communication unit are connected through a low-power wide-area network (Low-Power Wide-Area Network). , LPWAN) to transmit. For example, the audio recognition conversion and intelligent restoration communication device for rescue use described in item 3 of the scope of patent application, wherein the low-power wide area network is LoRaWAN. Such as the audio recognition conversion and intelligent restoration communication device for rescue use described in item 1 or 2 of the scope of patent application, wherein the environmental monitoring device is used to detect the temperature, carbon dioxide concentration, air pressure, smoke concentration and location information of the environment By. For example, the audio recognition conversion and intelligent restoration communication device for rescue use as described in item 5 of the scope of patent application, wherein the location information is based on a plurality of the communication devices between the environmental monitoring devices and the host Between the analysis modules, the triangulation method is used to calculate the obtainer. For example, the audio recognition conversion and intelligent restoration communication device for rescue use as described in item 5 of the scope of patent application, wherein the position information is obtained by GPS or GNSS global satellite navigation system positioning. For example, the audio recognition conversion and intelligent restoration communication device for rescue use described in item 1 or 2 of the scope of patent application, wherein the physiological recognition device is used to detect blood oxygen and heartbeat. For example, the audio recognition conversion and intelligent restoration communication device for rescue use described in item 1 or 2 of the scope of patent application, wherein the analysis module is further coupled to a display unit corresponding to the environmental detection of the communication device. Measured by.

Images