Fall detection system based on wearer voice recognition

Abstract

The invention provides a fall detection system based on wearer voice recognition, which comprises a fall-resistant garment, the neckline and the waist of the fall-resistant garment are provided with magic tape devices, and N pairs of sensor modules are fixed in the magic tape devices, the sensor module detects acceleration vector data alpha and angular velocity vector data omega of a wearer in real time and transmits the acceleration vector data alpha and the angular velocity vector data omega to the microcontroller module, and the microcontroller module outputs a control instruction to the safety air bag module. The miniature microphone collects voiceprint information of a wearer in real time and transmits the voiceprint information to the microcontroller module. The beneficial effects are that the wrestling behavior of the wearer can be comprehensively judged according to the speed, the direction and the voiceprint information of the wearer, the wrestling judgment accuracy of the wearer is improved, the timeliness of fall protection is enhanced, the use cost is low, and the method is suitable for most families.

Description

Technical Field

[0001] This invention relates to the field of protective wearable devices, and in particular to a fall detection system based on wearer voice recognition. Background Technology

[0002] Currently, falls among the elderly are a hot topic of public concern. With the continuous increase in China's aging population, falls among the elderly are becoming more frequent. Due to the special physical condition of the elderly, a fall can result in injuries ranging from fractures to life-threatening situations. Therefore, to protect the daily safety of the elderly, many protective products have been launched on the market, such as protective clothing and safety belts. However, these products often have problems with inaccurate fall detection and timely protection. Furthermore, most of these products are expensive and disposable, making them unsuitable for ordinary households.

[0003] The drawbacks of existing technology are: insufficient accuracy in judging falls, inadequate timeliness of protection, and high operating costs. Summary of the Invention

[0004] This invention provides a fall detection system based on wearer voice recognition, which improves the accuracy of fall judgment and provides timely safety protection for wearers who are about to fall.

[0005] To achieve the above objectives, the present invention provides a fall detection system based on wearer voice recognition, comprising a fall-protecting suit. The fall-protecting suit has Velcro devices at the collar and waist, and N pairs of sensor modules are fixed inside the Velcro devices. The sensor modules detect the wearer's acceleration vector data α and angular velocity vector data ω in real time and send them to a microcontroller module. The microcontroller module outputs control commands to the airbag module. The key feature is that a miniature microphone is also installed at the collar of the fall-protecting suit. The miniature microphone collects the wearer's voiceprint information in real time and transmits the voiceprint information to the microcontroller module.

[0006] The N pairs of sensor modules are used to collect acceleration vector data α and angular velocity vector data ω from various positions such as the wearer's collar and waist in real time, ensuring that the wearer can be detected by the corresponding sensor module no matter which position they fall from; the Velcro device's design for fixing the sensor modules ensures that each pair of sensor modules always collects acceleration vector data α and angular velocity vector data ω from the corresponding position.

[0007] The miniature microphone is used to collect the wearer's voiceprint information in real time.

[0008] By combining the wearer's acceleration vector data α, angular velocity vector data ω, and voiceprint information, the probability of false fall detection is greatly reduced, and the accuracy of fall detection is improved.

[0009] Preferably, the sensor module includes an acceleration sensor and a gyroscope sensor. The sensor module collects the acceleration vector data α and angular velocity vector data ω of the wearer's neck and waist in real time, specifically including but not limited to the acceleration vector data α and angular velocity vector data ω in all directions such as front and back, left and right, front left and back right, and front right and back left.

[0010] The acceleration vector data α and angular velocity vector data ω together constitute the velocity vector data v of the wearer.

[0011] One sensor module worn on the neck and one sensor module worn on the waist that detect the same direction are a pair of sensor modules.

[0012] The acceleration sensor is used to detect the acceleration vector data α of the wearer's neck and waist in real time; the gyroscope sensor is used to detect the angular velocity vector data ω of the wearer's neck and waist in real time.

[0013] Preferably, the miniature microphone collects the voiceprint information of the wearer in real time and transmits it to the microcontroller module; the sensor module detects the velocity vector data v of two different parts of the wearer's neck and waist in real time and transmits it to the microcontroller module. The microcontroller module calculates the velocity ratio r detected by each pair of sensor modules in real time.

[0014] When r < 0, it means that the velocity directions of the wearer's neck and waist are opposite, and the wearer is in a state of about to fall. The greater the absolute value of r, the greater the risk of falling.

[0015] When the voiceprint information of the wearer reaches the warning falling voiceprint threshold, and the velocity ratio r1 < |r| < r2 detected by two or more pairs of sensor modules, it is determined that the wearer is in a state of about to fall. The microcontroller module immediately outputs a control instruction to the airbag module.

[0016] When the voiceprint information of the wearer does not reach the warning falling voiceprint threshold, but the velocity ratio |r| > r2 detected by two or more pairs of sensor modules, it is determined that the wearer is in a state of about to fall. The microcontroller module immediately outputs a control instruction to the airbag module.

[0017] Among them, r1 is the preset falling threshold when the voiceprint information of the wearer reaches the warning falling voiceprint threshold; r2 is the preset falling threshold when it is determined that the wearer is in a state of about to fall regardless of whether the voiceprint information of the wearer reaches the warning falling voiceprint threshold.

[0018] Through the above design, it not only ensures the accurate judgment of the falling behavior of regular wearers, but also meets the falling judgment requirements of wearers with damaged voices or speech impairments.

[0019] This invention determines whether a wearer is about to fall by collecting the wearer's voiceprint information in real time and comparing the speed ratio of the wearer's collar and waist. It further improves the accuracy of fall detection by setting a warning fall voiceprint threshold and a preset fall speed ratio range. Furthermore, it can meet the fall detection and protection needs of various wearer groups, making it highly practical and suitable for widespread production applications.

[0020] Preferably, the airbag module includes an airbag unit and an inflation unit. The airbag unit is disposed at the collar and waist of the protective suit, and the air inlet of the airbag unit is connected to the inflation unit.

[0021] The airbag unit is used to provide real-time protection for the wearer who is in the process of falling, and the inflation unit is used to inflate the airbag unit instantly to improve the timeliness of fall protection.

[0022] Preferably, the microcontroller module also communicates with the connection.

[0023] The smart terminal is used to input the wearer's daily voiceprint information and voiceprint information when exclaiming in surprise into the microcontroller module, so that the microcontroller module can identify and judge the wearer's voiceprint information during subsequent use, thereby improving the accuracy of judging the wearer's fall.

[0024] The smart terminal is a smart device such as a smartphone or laptop.

[0025] The beneficial effects of this invention are: it can comprehensively judge the wearer's falling behavior based on the wearer's speed, direction and voiceprint information, which not only improves the accuracy of the fall judgment, but also enhances the timeliness of fall protection, and has a low cost of use, making it suitable for most families. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0027] The present invention will be further described in detail below with reference to the accompanying drawings and specific examples. The following embodiments or drawings are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0028] like Figure 1As shown: A fall detection system based on the voice recognition of the wearer, including a fall-proof suit. There is a magic tape device 1 at the collar and waist of the fall-proof suit. N pairs of sensor modules are fixed inside the magic tape device 1. The sensor modules detect the acceleration vector data α and angular velocity vector data ω of the wearer in real time and transmit them to the microcontroller module 2. The microcontroller module 2 outputs control instructions to the safety airbag module 3. The key is that: A miniature microphone 4 is also installed at the collar of the fall-proof suit. The miniature microphone 4 collects the voiceprint information of the wearer in real time and transmits the voiceprint information to the microcontroller module 2.

[0029] The sensor module includes an acceleration sensor and a gyroscope sensor. The sensor module collects the acceleration vector data α and angular velocity vector data ω of the wearer's collar and waist in real time, specifically including but not limited to the acceleration vector data α and angular velocity vector data ω in all directions such as front and back, left and right, front left and back right, and front right and back left;

[0030] The acceleration vector data α and angular velocity vector data ω together form the velocity vector data v of the wearer;

[0031] One sensor module worn at the collar and one sensor module worn at the waist that detect the same direction are a pair of sensor modules.

[0032] The safety airbag module 3 includes an airbag unit and an inflation unit. The airbag unit is arranged at the collar and waist of the fall-proof suit. The air inlet of the airbag unit is connected to the inflation unit.

[0033] The microcontroller module 2 is also connected and communicates with the smart terminal.

[0034] Specifically, the miniature microphone 4 collects the voiceprint information of the wearer in real time and transmits it to the microcontroller module 2; the sensor module detects the velocity vector data v of two different parts of the wearer's collar and waist in real time and transmits it to the microcontroller module 2. The microcontroller module 2 calculates the velocity ratio r detected by each pair of sensor modules in real time;

[0035] When r < 0, it means that the velocity directions of the wearer's neck and waist are opposite, and the wearer is in a state of about to fall. The larger the absolute value of r, the greater the risk of falling;

[0036] When the voiceprint information of the wearer reaches the warning fall voiceprint threshold, and the velocity ratio r1 < |r| < r2 detected by two or more pairs of sensor modules, it is judged that the wearer is in a state of about to fall. The microcontroller module 2 immediately outputs a control instruction to the safety airbag module 3;

[0037] When the wearer's voiceprint information does not reach the warning fall voiceprint threshold, but the speed ratio |r| detected by two or more pairs of sensor modules is greater than r2, it is determined that the wearer is about to fall, and the microcontroller module 2 immediately outputs control commands to the airbag module 3.

[0038] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A fall detection system based on wearer voice recognition, comprising an anti-fall garment, the collar and waist of which are provided with a Velcro device (1), N pairs of sensor modules are fixed in the Velcro device (1), the sensor modules detect the acceleration vector data a and the angular velocity vector data ω of the wearer in real time to a microcontroller module (2), the microcontroller module (2) outputs control instructions to the airbag module (3), characterized in that: The anti-falling clothes is also provided with a microphone (4) at the collar, which collects the voiceprint information of the wearer in real time and transmits the information to the microcontroller module (2).

2. The fall detection system based on wearer's voice recognition of claim 1, wherein: The sensor module contains acceleration sensors and gyroscopic sensors, which collect acceleration vector data α and angular velocity vector data ω of the wearer's collar and waist in real time, including but not limited to acceleration vector data α and angular velocity vector data ω of each direction such as front, back, left, right, left front and right back, and right front and left back. The acceleration vector data α and angular velocity vector data ω together constitute the speed vector data v of the wearer. A sensor module worn on the collar and a sensor module worn on the waist in the same direction form a pair of sensor modules.

3. The fall detection system based on wearer's voice recognition of claim 1, wherein: The microphone (4) collects the voiceprint information of the wearer in real time and transmits it to the microcontroller module (2); the sensor module detects the speed vector data v of the wearer's collar and waist in real time, and transmits it to the microcontroller module (2), which calculates the speed ratio r detected by each pair of sensor modules in real time. When r < 0, it indicates that the speed directions of the wearer's neck and waist are opposite, and the wearer is in a state of about to fall, and the greater the absolute value of r, the greater the risk of falling. When the voiceprint information of the wearer reaches the early warning falling voiceprint threshold, and the speed ratio r1 < |r| < r2 detected by two or more pairs of sensor modules, it is judged that the wearer is in a state of about to fall, and the microcontroller module (2) immediately outputs a control instruction to the safety airbag module (3). When the voiceprint information of the wearer does not reach the early warning falling voiceprint threshold, but the speed ratio |r| > r2 detected by two or more pairs of sensor modules, it is judged that the wearer is in a state of about to fall, and the microcontroller module (2) immediately outputs a control instruction to the safety airbag module (3).

4. The fall detection system based on wearer's voice recognition of claim 1, wherein: The safety airbag module (3) includes an airbag unit and an inflation unit, and the airbag unit is arranged at the collar and waist of the anti-falling clothes, and the air inlet of the airbag unit is connected with the inflation unit.

5. The fall detection system based on wearer's voice recognition of claim 1, wherein: The microcontroller module (2) is also connected with an intelligent terminal for communication.

Images