A vital sign and pain monitoring suit and monitoring method for elderly people with cognitive impairment

Abstract

The present invention relates to a vital sign and pain monitoring suit and a monitoring method for elderly people with cognitive impairment, belonging to the technical field of medical care monitoring. The monitoring suit is provided with a vital sign monitoring pad, a body temperature sensor, a sound recognition component, a blood pressure measuring belt, and a pressure sensing component and a stretching sensor for monitoring limb compulsion on the monitoring suit body. By collecting vital sign data, limb compulsion data, sound information processing and establishing a scoring mechanism, it can help medical staff to effectively evaluate and monitor the occurrence of pain in elderly people with cognitive impairment.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical care monitoring, and in particular relates to a vital sign and pain monitoring suit and a monitoring method for elderly people with cognitive impairment. Background Art

[0002] In the field of elderly care, 67.4% of the elderly have cognitive impairment, 62% of the elderly report pain, but only 37% have pain records, and only 1 / 4 of the pain patients receive analgesia. A survey pointed out that 14% to 18% of elderly patients suffering from acute illness have mental confusion, 50% of the elderly over 85 years old have dementia, and patients with cognitive impairment have more obstacles in reporting pain than cognitively sound elderly people.

[0003] Behavioral observation of elderly people with cognitive impairment is an important method to assess whether they feel pain. Discomfort or pain in elderly people with moderate to severe cognitive impairment is usually expressed through non-verbal behavior. The American Geriatrics Society proposed 6 behaviors related to pain in the elderly, namely: facial expressions, including frowning, sad expression, frightened expression, grimace, forehead wrinkles, closed eyes, and rapid blinking; language and pronunciation, including sighing, groaning, humming, shouting, and heavy breathing; body movements, including body stiffness, tense posture, panic, limited activity, gait or activity changes; changes in interpersonal communication, including aggression, resistance to care, reduced social interaction, social maladjustment, and loneliness; changes in activity patterns and daily behaviors, including refusal to eat, changes in appetite, increased rest time, changes in rest patterns, and sudden cessation of daily life; changes in mental state, including crying, tears, irritability, and depression.

[0004] According to the evaluation method of PACIE, the Pain Assessment Form for Cognitive Impairment, this application selects three items, namely, sound, body posture, and vital signs, as evaluation criteria, and adopts standard quantification, precise monitoring and scoring methods to accurately determine whether elderly people with cognitive impairment experience pain when they are unable to express it, and output vital sign information at the same time. Summary of the invention

[0005] The present invention application is mainly aimed at the deficiencies of the existing technology, and provides a vital sign and pain monitoring suit and monitoring method for elderly people with cognitive impairment, which is used to assist doctors and guardians in obtaining the vital signs of elderly people with cognitive impairment and judging whether they feel pain.

[0006] To achieve the above purpose, the technical solution provided by the present invention is as follows:

[0007] A vital sign and pain monitoring suit for elderly people with cognitive impairment, comprising: a monitoring suit body, a vital sign monitoring pad, a body temperature sensor, a voice recognition component, a blood pressure measuring belt, a left front chest pressure sensing component, a right front chest pressure sensing component, a left abdominal pressure sensing component, a right abdominal pressure sensing component, a left lower abdominal pressure sensing component, a right lower abdominal pressure sensing component, a left back pressure sensing component, a right back pressure sensing component, a first stretching sensor, a second stretching sensor, a third stretching sensor, a fourth stretching sensor, a triaxial acceleration sensor, and a controller component; the vital sign monitoring pad is arranged at the lower left front chest of the monitoring suit body, the body temperature sensor is arranged at the left armpit of the monitoring suit body, the voice recognition component is arranged at the collar of the monitoring suit body, and the blood pressure measuring belt is arranged at the left upper arm of the monitoring suit body; the left front chest position of the monitoring suit body is provided with a left front chest pressure sensing component, the right front chest position of the monitoring suit body is provided with a right front chest pressure sensing component, the left abdomen position of the monitoring suit body is provided with a left abdomen pressure sensing component, and the right abdomen position of the monitoring suit body is provided with a There is a right abdominal pressure sensing component, a left lower abdominal pressure sensing component is provided at the left lower abdominal position of the monitoring suit body, a right lower abdominal pressure sensing component is provided at the right lower abdominal position of the monitoring suit body, a left back pressure sensing component is provided at the back position of the monitoring suit body, and a right back pressure sensing component is provided at the right back position of the monitoring suit body; the first stretch sensor, the second stretch sensor, the third stretch sensor, and the fourth stretch sensor are arranged in an X shape and are provided on the back of the monitoring suit body; the three-axis acceleration sensor is provided at the back waist position of the monitoring suit body, and the controller component is provided at the bottom of the monitoring suit body; the vital sign monitoring pad, the body temperature sensor, the voice recognition component, the blood pressure measuring belt, the left front chest pressure sensing component, the right front chest pressure sensing component, the left abdominal pressure sensing component, the right abdominal pressure sensing component, the left lower abdominal pressure sensing component, the right lower abdominal pressure sensing component, the left back pressure sensing component, the right back pressure sensing component, the first stretch sensor, the second stretch sensor, the third stretch sensor, the fourth stretch sensor, and the three-axis acceleration sensor are respectively connected to the controller component.

[0008] Furthermore, the controller component is provided with a data acquisition module, a CPU module, a storage module, a decoder, a Bluetooth communication module, and a battery pack. The data acquisition module and the storage module are respectively connected to the CPU module, and the CPU module is connected to the decoder and the Bluetooth communication module in sequence. The data acquisition module, the CPU module, the decoder, and the Bluetooth communication module are also respectively connected to the battery pack, and the Bluetooth communication module is also connected to the cloud server.

[0009] Furthermore, a breathing sensor, a heart rate sensor, and a blood oxygen saturation sensor are arranged in the vital sign monitoring pad, and the breathing sensor, the heart rate sensor, and the blood oxygen saturation sensor are respectively connected to the data acquisition module in the controller component.

[0010] Furthermore, the data acquisition module in the controller component is connected to the body temperature sensor, the sound recognition component, the left front chest pressure sensing component, the right front chest pressure sensing component, the left abdominal pressure sensing component, the right abdominal pressure sensing component, the left lower abdominal pressure sensing component, the right lower abdominal pressure sensing component, the left back pressure sensing component, the right back pressure sensing component, the first stretch sensor, the second stretch sensor, the third stretch sensor, the fourth stretch sensor, and the three-axis acceleration sensor.

[0011] Furthermore, 20 pressure sensors arranged in a matrix are respectively arranged inside the left front chest pressure sensing assembly, the right front chest pressure sensing assembly, the left abdomen pressure sensing assembly, the right abdomen pressure sensing assembly, the left lower abdomen pressure sensing assembly, the right lower abdomen pressure sensing assembly, the left back pressure sensing assembly, and the right back pressure sensing assembly.

[0012] Furthermore, the blood pressure measuring belt is provided with an air bag, a driving air pump connected to the air bag, a blood pressure sensor, and a microcontroller respectively connected to the blood pressure sensor and the driving air pump.

[0013] Furthermore, the sound recognition component includes a sound sensor, a framing unit, a feature extraction unit, and a sound determination unit connected in sequence, and the sound determination unit is also connected to the acoustic model storage unit;

[0014] A sound sensor, used for inputting a sound signal;

[0015] A framing unit, used for intercepting the input signal with a predetermined time length as a frame unit to generate a framed input signal;

[0016] A feature extraction unit, for generating a multi-dimensional vector of a framed input signal using Mel Cepstral Coefficients (MFCC);

[0017] An acoustic model storage unit, used for storing an acoustic model used as a judgment standard;

[0018] The sound determination unit is used to determine and output an acoustic model having the same characteristics as the input sound signal.

[0019] A method for monitoring vital signs and pain sensation of elderly people with cognitive impairment, comprising the following steps:

[0020] Step 1: Collect vital signs data:

[0021] 1) The data acquisition module collects the heart rate signal, respiratory rate signal, and blood oxygen saturation signal collected by the vital sign monitoring pad, and processes the heart rate k times / minute, respiratory rate h times / minute, and blood oxygen saturation y% through the CPU module, and collects them in real time and transmits them to the cloud server for recording through the Bluetooth communication module;

[0022] 2) The blood pressure signal collected by the blood pressure measurement belt is collected through the data acquisition module, and the blood pressure value is obtained by the CPU module. The blood pressure value is a mmHg, which is measured every 30 minutes and transmitted to the cloud server for record through the Bluetooth communication module;

[0023] 3) The temperature signal collected by the temperature sensor is collected through the data acquisition module, and the temperature value is m℃ after being processed by the CPU module. The temperature is collected and transmitted to the cloud server for recording through the Bluetooth communication module;

[0024] Step 2: Process vital signs data:

[0025] 1) Take the heart rate, respiratory rate, and blood oxygen saturation data 24 hours before the test time as samples, take the median and define it as the normal heart rate k p times / minute, respiratory rate h p times / minute, blood oxygen saturation p %;

[0026] 2) Take the blood pressure data for 24 hours before the test time, take the median and define it as the normal blood pressure value a p mmHg;

[0027] 3) Take the body temperature data 24 hours before the test time, take the median and define it as the normal body temperature value m p ℃;

[0028] Step 3, collect data on physical compulsion:

[0029] 1) The data acquisition module collects signals of the first stretch sensor, the second stretch sensor, the third stretch sensor, and the fourth stretch sensor, and the CPU module processes the signals to obtain the stretching degree E1% of the first stretch sensor, the stretching degree E2% of the second stretch sensor, the stretching degree E3% of the third stretch sensor, and the stretching degree E4% of the fourth stretch sensor;

[0030] 2) The data acquisition module collects the signals of the pressure sensors in the left front chest pressure sensor assembly, the right front chest pressure sensor assembly, the left abdomen pressure sensor assembly, the right abdomen pressure sensor assembly, the left lower abdomen pressure sensor assembly, the right lower abdomen pressure sensor assembly, the left back pressure sensor assembly, and the right back pressure sensor assembly and groups them into 1 to 8 groups. The sensors in each group are numbered 1 to 20. After being processed by the CPU module, the pressure value matrix is ​​obtained as follows: , The unit is N, i is the pressure value group number, i=(1, 8), j is the sensor number, j=(1, 20);

[0031] Step 4: Collect sound information:

[0032] 1) using a sound sensor of a sound recognition component to collect a sound signal, and using a framing unit to intercept the input signal in a frame unit having a predetermined duration to generate a framed input signal;

[0033] 2) Generate a multi-dimensional vector of the framed input signal using Mel Cepstral Coefficients (MFCC) through the feature extraction unit;

[0034] Step 5: Determine the pain status of elderly people with cognitive impairment:

[0035] Step 5.1, evaluate vital signs status:

[0036] The real-time monitored heart rate k times / minute, respiratory rate h times / minute, blood oxygen saturation y%, blood pressure value ammHg, body temperature value m℃ and the heart rate k under normal condition are compared. p times / minute, respiratory rate h p times / minute, blood oxygen saturation p %, blood pressure value is a p mmHg, body temperature value is m p ℃ make difference;

[0037] When the changes in vital signs such as heart rate, respiratory rate, blood oxygen saturation and blood pressure are: heart rate increase <20 times / min, respiratory rate increase <10 times / min, blood oxygen saturation decrease <5%, blood pressure increase <20 mmHg, body temperature increase <1°C, the vital signs score is 0;

[0038] When any of the vital signs, such as heart rate, respiratory rate, blood oxygen saturation, or blood pressure, changes as follows:

[0039] When the heart rate increases by >20 beats / min, the respiratory rate increases by >10 beats / min, the blood oxygen saturation decreases by 5%, the blood pressure increases by >20 mmHg, and the body temperature increases by >1°C, the vital sign score is 1;

[0040] When any of the vital signs, such as heart rate, respiratory rate, blood oxygen saturation, or blood pressure, changes as follows:

[0041] When the heart rate increases by >25 beats / min, the respiratory rate increases by >20 beats / min, the blood oxygen saturation decreases by 10%, the blood pressure increases by >20 mmHg, and the body temperature increases by >1.5°C, the vital signs score is 2 points;

[0042] Step 5.2, evaluate physical compulsion:

[0043] 1) Take the stretching data of the first stretching sensor, the stretching data of the second stretching sensor, the stretching data of the third stretching sensor, and the stretching data of the fourth stretching sensor 24 hours before the detection time point, take the median and define it as the stretching E of the first stretching sensor in the normal state 1p%, the second tensile sensor stretch degree E 2p %, the third tensile sensor stretch degree E 3p %, the fourth tensile sensor stretch degree E 4p %;

[0044] 2) Calculate the change in the stretching degree of the first stretch sensor as Q1 = (E1-E 1p ) / E 1p *100%, the change in the stretching degree of the second stretch sensor is Q2= (E2-E 2p ) / E 2p *100%, the change in the stretching degree of the third stretching sensor is Q3= (E3-E 3p ) / E 3p *100%, the change in the stretching degree of the fourth stretching sensor is Q4=(E4-E 4p ) / E 4p *100%;

[0045] 3) Generate the impact matrix according to the layout of pressure sensors , where i is the pressure value group number, i=(1,8), j is the sensor number, j=(1,20); according to the pressure value matrix collected in step 3 , calculate the average pressure value of each group separately , N=20, i is the pressure value group number, i=(1,8);

[0046] when > When , the influence value of the corresponding point in the matrix will be affected Set to 1;

[0047] when > When , the influence value of the corresponding point in the matrix will be affected Set to 2;

[0048] when > When , the influence value of the corresponding point in the matrix will be affected Set to 3;

[0049] Define the maximum external force pressure influence value G=MAX( );

[0050] 4) When the stretching change of the first stretch sensor, the stretching change of the second stretch sensor, the stretching change of the third stretch sensor, the stretching change of the fourth stretch sensor, and the external force pressure value are respectively: Q1<10%, Q2<10%, Q3<5%, Q4<5%, G=1, the limb compulsion score is 0;

[0051] When any one of the stretching degree change of the first stretching sensor, the stretching degree change of the second stretching sensor, the stretching degree change of the third stretching sensor, the stretching degree change of the fourth stretching sensor, and the external force pressure value reaches: Q1>10%, Q2>10%, Q3>5%, Q4>5%, G=2, the limb compulsion score is 1;

[0052] When any one of the stretching degree change of the first stretching sensor, the stretching degree change of the second stretching sensor, the stretching degree change of the third stretching sensor, the stretching degree change of the fourth stretching sensor, and the external force pressure value reaches: Q1>15%, Q2>15%, Q3>10%, Q4>10%, G=3, the limb compulsion score is assessed as 2;

[0053] Step 5.3, evaluate the sound information:

[0054] Step 5.3.1, establish an evaluation standard acoustic model: collect the groaning sounds of the elderly in mild pain state, moderate pain state, and severe pain state, and generate an evaluation standard acoustic model;

[0055] Step 5.3.2, compare and score the sound information:

[0056] The sound signal collected in step 4 is framed by the framing unit, and the multi-dimensional vector of the framed input signal is generated by the feature extraction unit using the Mel Cepstral Coefficient (MFCC), and compared with the evaluation standard acoustic model library in step 5.3.1 to find the closest acoustic model;

[0057] When the acoustic model that is closest to the evaluation standard is the mild pain state group, the sound information score is 1;

[0058] When the closest evaluation standard acoustic model was the moderate pain state group, the sound information score was rated as 2;

[0059] When the closest evaluation standard acoustic model was the severe pain state group, the sound information score was 3;

[0060] When there is no sound information, the score of the sound information is 0;

[0061] Step 5.4, Determination of pain status of elderly people with cognitive impairment:

[0062] The vital signs scores, limb compulsion scores, and sound information scores evaluated in steps 5.1 to 5.3 are added together to obtain a pain status score of 0 to 7;

[0063] When the pain status score was 0, it was judged that no pain occurred;

[0064] When the pain status score is 1 to 3, it is judged as mild pain;

[0065] When the pain status score is 4 to 5, it is judged as moderate pain;

[0066] When the pain status score is 6 to 7, it is judged as severe pain;

[0067] Furthermore, in step 5.3.1, the specific steps of establishing the evaluation standard acoustic model are: collecting the groaning sounds of the elderly in mild pain state, moderate pain state, and severe pain state respectively, and establishing three groups of information, each with 50 to 100 pieces, respectively, and intercepting the input signal with frame units with a predetermined time length through the framing unit to generate a framed input signal; using Mel cepstral coefficients (MFCC) to generate a multidimensional vector of the framed input signal and store it as the evaluation standard acoustic model.

[0068] Furthermore, in step 5.2 (3), the position of the pressure sensor corresponding to the maximum external force compression influence value G is determined to be the pain occurrence position.

[0069] The beneficial effects of the present invention are:

[0070] 1. The vital sign and pain monitoring suit for elderly people with cognitive impairment described in the present invention can collect vital sign information in real time by setting a vital sign monitoring pad, and upload it to a cloud server for real-time monitoring by medical staff.

[0071] 2. The method for monitoring vital signs and pain sensation in elderly people with cognitive impairment described in the present invention assists in monitoring whether pain occurs in elderly people with cognitive impairment by quantitatively evaluating vital signs, limb compulsion, and sound information. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a front view of the vital sign and pain monitoring clothing for elderly people with cognitive impairment according to the present invention;

[0073] Figure 2 A rear view of the vital sign and pain monitoring suit for elderly people with cognitive impairment according to the present invention;

[0074] Figure 3 This is a schematic diagram of the connection structure of the controller components of the vital sign and pain monitoring clothing for elderly people with cognitive impairment according to the present invention;

[0075] Figure 4 This is a schematic diagram of the connection structure of the sound recognition component of the vital sign and pain monitoring clothing for elderly people with cognitive impairment described in the present invention.

[0076] In the figure: 1-monitoring suit body, 2-vital sign monitoring pad, 3-body temperature sensor, 4-sound recognition component, 41-sound sensor, 42-framing unit, 43-feature extraction unit, 44-sound judgment unit, 45-acoustic model storage unit, 5-blood pressure measuring belt, 6-left front chest pressure sensor component, 7-right front chest pressure sensor component, 8-left abdominal pressure sensor component, 9-right abdominal pressure sensor component, 10-left lower abdominal pressure sensor component, 11-right lower abdominal pressure sensor component, 12-left back pressure sensor component, 13-right back pressure sensor component, 14-first stretch sensor, 15-second stretch sensor, 16-third stretch sensor, 17-fourth stretch sensor, 18-three-axis acceleration sensor, 19-controller component, 191-data acquisition module, 192-CPU module, 193-storage module, 194-decoder, 195-Bluetooth communication module, 20-battery pack. DETAILED DESCRIPTION

[0077] The present invention will be further described below with reference to the accompanying drawings.

[0078] like Figure 1 , Figure 2As shown, a vital sign and pain monitoring suit for elderly people with cognitive impairment includes: a monitoring suit body 1, a vital sign monitoring pad 2, a body temperature sensor 3, a voice recognition component 4, a blood pressure measuring belt 5, a left front chest pressure sensing component 6, a right front chest pressure sensing component 7, a left abdominal pressure sensing component 8, a right abdominal pressure sensing component 9, a left lower abdominal pressure sensing component 10, a right lower abdominal pressure sensing component 11, a left back pressure sensing component 12, a right back pressure sensing component 13, a first stretching sensor 14, a second stretching sensor 15, a third stretching sensor 16, a fourth stretching sensor 17, a three-axis tension sensor 18, a third tension sensor 19, a third tension sensor 20, a fourth tension sensor 21, a third tension sensor 22, a third tension sensor 23, a third tension sensor 24, a third tension sensor 25, a third tension sensor 26, a third tension sensor 27, a third tension sensor 28, a third tension sensor 29, a third tension sensor 30, a third tension sensor 31, a third tension sensor 32, a third tension sensor 33, a third tension sensor 34, a third tension sensor 35, a third tension sensor 36, a third tension sensor 37, a third tension sensor 38, a third tension sensor 3 ...9, a third tension sensor 31, a third tension sensor 31, a third tension sensor 32, a third tension sensor 33, a third tension sensor 34, a third tension sensor 35, a third tension sensor 36, a third tension sensor 37, a third tension sensor 38, a third The speed sensor 18 and the controller component 19; the vital sign monitoring pad 2 is arranged at the lower left chest of the monitoring suit body 1, the temperature sensor 3 is arranged at the left armpit of the monitoring suit body 1, the voice recognition component 4 is arranged at the collar of the monitoring suit body 1, and the blood pressure measuring belt 5 is arranged at the left upper arm of the monitoring suit body 1; the left chest position of the monitoring suit body 1 is provided with a left chest pressure sensing component 6, the right chest position of the monitoring suit body 1 is provided with a right chest pressure sensing component 7, the left abdomen position of the monitoring suit body 1 is provided with a left abdomen pressure sensing component 8, and the right abdomen position of the monitoring suit body 1 is provided with a right abdomen pressure sensing component 8. The force sensing component 9, the left lower abdomen position of the monitoring suit body 1 is provided with a left lower abdomen pressure sensing component 10, the right lower abdomen position of the monitoring suit body 1 is provided with a right lower abdomen pressure sensing component 11, the back position of the monitoring suit body 1 is provided with a left back pressure sensing component 12, and the right back position of the monitoring suit body 1 is provided with a right back pressure sensing component 13; the first stretch sensor 14, the second stretch sensor 15, the third stretch sensor 16, and the fourth stretch sensor 17 are arranged in an X shape and are provided on the back of the monitoring suit body 1; the three-axis acceleration sensor 18 is provided at the back waist position of the monitoring suit body 1, and the controller component 19 is arranged at the bottom of the monitoring suit body 1; the vital sign monitoring pad 2, the body temperature sensor 3, the voice recognition component 4, the blood pressure measuring belt 5, the left front chest pressure sensing component 6, the right front chest pressure sensing component 7, the left abdominal pressure sensing component 8, the right abdominal pressure sensing component 9, the left lower abdominal pressure sensing component 10, the right lower abdominal pressure sensing component 11, the left back pressure sensing component 12, the right back pressure sensing component 13, the first stretching sensor 14, the second stretching sensor 15, the third stretching sensor 16, the fourth stretching sensor 17, and the three-axis acceleration sensor 18 are respectively connected to the controller component 19.

[0079] Furthermore, the controller component 19 is provided with a data acquisition module 191, a CPU module 192, a storage module 193, a decoder 194, a Bluetooth communication module 195, and a battery pack 196. The data acquisition module 191 and the storage module 193 are respectively connected to the CPU module 192, and the CPU module 192 is connected to the decoder 194 and the Bluetooth communication module 195 in sequence. The data acquisition module 191, the CPU module 192, the decoder 194, and the Bluetooth communication module 195 are also respectively connected to the battery pack 196, and the Bluetooth communication module 195 is also connected to the cloud server 20.

[0080] Furthermore, a breathing sensor, a heart rate sensor, and a blood oxygen saturation sensor are provided in the vital sign monitoring pad 2 , and the breathing sensor, the heart rate sensor, and the blood oxygen saturation sensor are respectively connected to the data acquisition module 191 in the controller component 19 .

[0081] Further, the data acquisition module 191 in the controller component 19 is connected to the body temperature sensor 3, the voice recognition component 4, the left front chest pressure sensor component 6, the right front chest pressure sensor component 7, the left abdomen pressure sensor component 8, the right abdomen pressure sensor component 9, the left lower abdomen pressure sensor component 10, the right lower abdomen pressure sensor component 11, the left back pressure sensor component 12, the right back pressure sensor component 13, the first stretch sensor 14, the second stretch sensor 15, the third stretch sensor 16, the fourth stretch sensor 17, and the triaxial acceleration sensor 18. The triaxial acceleration data collected by the triaxial acceleration sensor 18 is used to determine whether a fall state occurs, and the triaxial acceleration sensor 18 adopts PCB Piezotronics 356A01 type.

[0082] Further, 20 pressure sensors arranged in a matrix are respectively arranged inside the left front chest pressure sensing assembly 6, the right front chest pressure sensing assembly 7, the left abdomen pressure sensing assembly 8, the right abdomen pressure sensing assembly 9, the left lower abdomen pressure sensing assembly 10, the right lower abdomen pressure sensing assembly 11, the left back pressure sensing assembly 12, and the right back pressure sensing assembly 13;

[0083] Furthermore, the blood pressure measuring belt 5 is provided with an air bag (not shown in the figure), a driving air pump (not shown in the figure) connected to the air bag, a blood pressure sensor (not shown in the figure), and a microcontroller (not shown in the figure) connected to the blood pressure sensor and the driving air pump respectively. The driving air pump is MAC20 type, with a size of 19mm×21mm, and an output pressure>300mmHg; the microcontroller is CXD2951 type.

[0084] Furthermore, the voice recognition component 4 includes a voice sensor 41, a framing unit 42, a feature extraction unit 43, and a voice determination unit 44 which are connected in sequence, and the voice determination unit 44 is also connected to an acoustic model storage unit 45;

[0085] A sound sensor 41, used for inputting a sound signal;

[0086] The framing unit 42 is used to intercept the input signal with a predetermined time length as a frame unit to generate a framed input signal;

[0087] The feature extraction unit 43 is used to generate a multi-dimensional vector of the framed input signal using Mel Cepstral Coefficients (MFCC);

[0088] An acoustic model storage unit 45, used to store an acoustic model used as a judgment standard;

[0089] The sound determination unit 44 is used to determine and output an acoustic model having the same characteristics as the input sound signal.

[0090] A method for monitoring vital signs and pain sensation of elderly people with cognitive impairment, comprising the following steps:

[0091] Step 1: Collect vital signs data:

[0092] 1) The heart rate signal, respiratory rate signal, and blood oxygen saturation signal collected by the vital sign monitoring pad 2 are collected through the data acquisition module 191, and the heart rate k times / minute, respiratory rate h times / minute, and blood oxygen saturation y% are obtained through the CPU module 192. The data is collected in real time and transmitted to the cloud server 20 for recording through the Bluetooth communication module 195;

[0093] 2) The blood pressure signal collected by the blood pressure measuring belt 5 is collected through the data acquisition module 191, and the blood pressure value is obtained by the CPU module 192, which is measured every 30 minutes and transmitted to the cloud server 20 for recording through the Bluetooth communication module 195;

[0094] 3) The temperature signal collected by the temperature sensor 3 is collected by the data acquisition module 191, and the temperature value is m°C after being processed by the CPU module 192. The temperature signal is collected and transmitted to the cloud server 20 for recording via the Bluetooth communication module 195;

[0095] Step 2: Process vital signs data:

[0096] 1) Take the heart rate, respiratory rate, and blood oxygen saturation data 24 hours before the test time as samples, take the median and define it as the normal heart rate k p times / minute, respiratory rate h p times / minute, blood oxygen saturation p %;

[0097] 2) Take the blood pressure data for 24 hours before the test time, take the median and define it as the normal blood pressure value a p mmHg;

[0098] 3) Take the body temperature data 24 hours before the test time, take the median and define it as the normal body temperature value m p ℃;

[0099] Step 3, collect data on physical compulsion:

[0100] 1) The signals of the first stretch sensor 14, the second stretch sensor 15, the third stretch sensor 16 and the fourth stretch sensor 17 are collected by the data acquisition module 191, and the stretching degree E1% of the first stretch sensor, the stretching degree E2% of the second stretch sensor, the stretching degree E3% of the third stretch sensor and the stretching degree E4% of the fourth stretch sensor are obtained through processing by the CPU module 192;

[0101] 2) The data acquisition module 191 collects the signals of the pressure sensors in the left front chest pressure sensor assembly 6, the right front chest pressure sensor assembly 7, the left abdomen pressure sensor assembly 8, the right abdomen pressure sensor assembly 9, the left lower abdomen pressure sensor assembly 10, the right lower abdomen pressure sensor assembly 11, the left back pressure sensor assembly 12, and the right back pressure sensor assembly 13 respectively and groups them into groups 1 to 8. The sensors in each group are numbered 1 to 20. After being processed by the CPU module 192, the pressure value matrix is ​​obtained as follows: , The unit is N, i is the pressure value group number, i=(1, 8), j is the sensor number, j=(1, 20);

[0102] Step 4: Collect sound information:

[0103] 1) The sound sensor 41 of the sound recognition component 4 collects the sound signal, and the framing unit 42 intercepts the input signal in a frame unit with a predetermined time length to generate a framed input signal;

[0104] 2) generating a multi-dimensional vector of the framed input signal by using Mel Cepstral Coefficients (MFCC) through the feature extraction unit 43;

[0105] Step 5: Determine the pain status of elderly people with cognitive impairment:

[0106] Step 5.1, evaluate vital signs status:

[0107] The real-time monitored heart rate k times / minute, respiratory rate h times / minute, blood oxygen saturation y%, blood pressure value ammHg, body temperature value m℃ and the heart rate k under normal condition are compared. p times / minute, respiratory rate h p times / minute, blood oxygen saturation p %, blood pressure value is a p mmHg, body temperature value is m p ℃ make difference;

[0108] When the changes in vital signs such as heart rate, respiratory rate, blood oxygen saturation and blood pressure are: heart rate increase <20 times / min, respiratory rate increase <10 times / min, blood oxygen saturation decrease <5%, blood pressure increase <20 mmHg, body temperature increase <1°C, the vital signs score is 0;

[0109] When any of the vital signs, such as heart rate, respiratory rate, blood oxygen saturation, or blood pressure, changes as follows:

[0110] When the heart rate increases by >20 beats / min, the respiratory rate increases by >10 beats / min, the blood oxygen saturation decreases by 5%, the blood pressure increases by >20 mmHg, and the body temperature increases by >1°C, the vital sign score is 1;

[0111] When any of the vital signs, such as heart rate, respiratory rate, blood oxygen saturation, or blood pressure, changes as follows:

[0112] When the heart rate increases by >25 beats / min, the respiratory rate increases by >20 beats / min, the blood oxygen saturation decreases by 10%, the blood pressure increases by >20 mmHg, and the body temperature increases by >1.5°C, the vital signs score is 2 points;

[0113] Step 5.2, evaluate physical compulsion:

[0114] 1) Take the stretching data of the first stretching sensor, the stretching data of the second stretching sensor, the stretching data of the third stretching sensor, and the stretching data of the fourth stretching sensor 24 hours before the detection time point, take the median and define it as the stretching E of the first stretching sensor in the normal state 1p %, the second tensile sensor stretch degree E 2p %, the third tensile sensor stretch degree E 3p %, the fourth tensile sensor stretch degree E 4p %;

[0115] 2) Calculate the change in the stretching degree of the first stretch sensor as Q1 = (E1-E 1p ) / E 1p *100%, the change in the stretching degree of the second stretch sensor is Q2= (E2-E 2p ) / E 2p *100%, the change in the stretching degree of the third stretching sensor is Q3= (E3-E 3p ) / E 3p *100%, the change in the stretching degree of the fourth stretching sensor is Q4=(E4-E 4p ) / E 4p *100%;

[0116] 3) Generate the impact matrix according to the layout of pressure sensors , where i is the pressure value group number, i=(1,8), j is the sensor number, j=(1,20); according to the pressure value matrix collected in step 3 , calculate the average pressure value of each group separately , N=20, i is the pressure value group number, i=(1,8);

[0117] when > When , the influence value of the corresponding point in the matrix will be affected Set to 1;

[0118] when > When , the influence value of the corresponding point in the matrix will be affected Set to 2;

[0119] when > When , the influence value of the corresponding point in the matrix will be affected Set to 3;

[0120] Define the maximum external force pressure influence value G=MAX( );

[0121] 4) When the stretching change of the first stretch sensor, the stretching change of the second stretch sensor, the stretching change of the third stretch sensor, the stretching change of the fourth stretch sensor, and the external force pressure value are respectively: Q1<10%, Q2<10%, Q3<5%, Q4<5%, G=1, the limb compulsion score is 0;

[0122] When any one of the stretching degree change of the first stretching sensor, the stretching degree change of the second stretching sensor, the stretching degree change of the third stretching sensor, the stretching degree change of the fourth stretching sensor, and the external force pressure value reaches: Q1>10%, Q2>10%, Q3>5%, Q4>5%, G=2, the limb compulsion score is 1;

[0123] When any one of the stretching degree change of the first stretching sensor, the stretching degree change of the second stretching sensor, the stretching degree change of the third stretching sensor, the stretching degree change of the fourth stretching sensor, and the external force pressure value reaches: Q1>15%, Q2>15%, Q3>10%, Q4>10%, G=3, the limb compulsion score is assessed as 2;

[0124] Step 5.3, evaluate the sound information:

[0125] Step 5.3.1, establishing an evaluation standard acoustic model: collecting the groaning sounds of the elderly in a mild pain state, a moderate pain state, and a severe pain state, respectively, to establish three groups of information, each with 50 to 100 pieces, respectively intercepting the input signal with a frame unit having a predetermined time length through the framing unit 42 to generate a framed input signal; using the Mel Cepstral Coefficient (MFCC) to generate a multidimensional vector of the framed input signal and store it as an evaluation standard acoustic model;

[0126] Step 5.3.2, compare and score the sound information:

[0127] The sound signal collected in step 4 is framed by the framing unit 42, and the multi-dimensional vector of the framed input signal is generated by the feature extraction unit 43 using the Mel Cepstral Coefficient (MFCC), and compared with the evaluation standard acoustic model library in step 5.3.1 to find the closest acoustic model;

[0128] When the acoustic model that is closest to the evaluation standard is the mild pain state group, the sound information score is 1;

[0129] When the closest evaluation standard acoustic model was the moderate pain state group, the sound information score was rated as 2;

[0130] When the closest evaluation standard acoustic model was the severe pain state group, the sound information score was 3;

[0131] When there is no sound information, the score of the sound information is 0;

[0132] Step 5.4, Determination of pain status of elderly people with cognitive impairment:

[0133] The vital signs scores, limb compulsion scores, and sound information scores evaluated in steps 5.1 to 5.3 are added together to obtain a pain status score of 0 to 7;

[0134] When the pain status score was 0, it was judged that no pain occurred;

[0135] When the pain status score is 1 to 3, it is judged as mild pain;

[0136] When the pain status score is 4 to 5, it is judged as moderate pain;

[0137] When the pain status score is 6 to 7, it is judged as severe pain;

[0138] Furthermore, in step 5.2 (3), the position of the pressure sensor corresponding to the maximum external force compression influence value G is determined to be the pain occurrence position.

[0139] The present invention is not limited to the above-mentioned embodiments, and any obvious improvements or changes to the above-mentioned embodiments made by those skilled in the art will not exceed the concept of the present invention and the protection scope of the appended claims.

Claims

1. A vital sign and pain monitoring suit for elderly people with cognitive impairment, characterized in that: include: Monitoring suit body, vital sign monitoring pad, body temperature sensor, voice recognition component, blood pressure measuring belt, left chest pressure sensing component, right chest pressure sensing component, left abdominal pressure sensing component, right abdominal pressure sensing component, left lower abdominal pressure sensing component, right lower abdominal pressure sensing component, left back pressure sensing component, right back pressure sensing component, first stretching sensor, second stretching sensor, third stretching sensor, fourth stretching sensor, three-axis acceleration sensor, controller component; the vital sign monitoring pad is arranged at the lower left chest of the monitoring suit body, the body temperature sensor is arranged at the left armpit of the monitoring suit body, the voice recognition component is arranged at the collar of the monitoring suit body, and the blood pressure measuring belt is arranged at the left upper arm of the monitoring suit body; the left chest position of the monitoring suit body is provided with a left chest pressure sensing component, the right chest position of the monitoring suit body is provided with a right chest pressure sensing component, the left abdomen position of the monitoring suit body is provided with a left abdominal pressure sensing component, and the right abdomen position of the monitoring suit body is provided with a right abdominal pressure sensing component, The left lower abdomen position of the monitoring suit body is provided with a left lower abdomen pressure sensing component, the right lower abdomen position of the monitoring suit body is provided with a right lower abdomen pressure sensing component, the back position of the monitoring suit body is provided with a left back pressure sensing component, and the right back position of the monitoring suit body is provided with a right back pressure sensing component; the first stretch sensor, the second stretch sensor, the third stretch sensor, and the fourth stretch sensor are arranged in an X shape and are provided on the back of the monitoring suit body; the three-axis acceleration sensor is provided at the back waist position of the monitoring suit body, and the controller component is provided at the bottom of the monitoring suit body; the vital sign monitoring pad, the body temperature sensor, the voice recognition component, the blood pressure measuring belt, the left front chest pressure sensing component, the right front chest pressure sensing component, the left abdominal pressure sensing component, the right abdominal pressure sensing component, the left lower abdomen pressure sensing component, the right lower abdomen pressure sensing component, the left back pressure sensing component, the right back pressure sensing component, the first stretch sensor, the second stretch sensor, the third stretch sensor, the fourth stretch sensor, and the three-axis acceleration sensor are respectively connected to the controller component.

2. The vital sign and pain monitoring clothing for elderly people with cognitive impairment according to claim 1, characterized in that: The controller component is equipped with a data acquisition module, a CPU module, a storage module, a decoder, a Bluetooth communication module, and a battery pack. The data acquisition module and the storage module are respectively connected to the CPU module, and the CPU module is connected to the decoder and the Bluetooth communication module in sequence. The data acquisition module, the CPU module, the decoder, and the Bluetooth communication module are also respectively connected to the battery pack, and the Bluetooth communication module is also connected to the cloud server.

3. The vital sign and pain monitoring clothing for elderly people with cognitive impairment according to claim 2, characterized in that: The vital sign monitoring pad is provided with a breathing sensor, a heart rate sensor, and a blood oxygen saturation sensor, and the breathing sensor, the heart rate sensor, and the blood oxygen saturation sensor are respectively connected to a data acquisition module in the controller component.

4. The vital sign and pain monitoring clothing for elderly people with cognitive impairment according to claim 2, characterized in that: The data acquisition module in the controller component is connected to a body temperature sensor, a sound recognition component, a left front chest pressure sensing component, a right front chest pressure sensing component, a left abdominal pressure sensing component, a right abdominal pressure sensing component, a left lower abdominal pressure sensing component, a right lower abdominal pressure sensing component, a left back pressure sensing component, a right back pressure sensing component, a first stretching sensor, a second stretching sensor, a third stretching sensor, a fourth stretching sensor, and a three-axis acceleration sensor.

5. The vital sign and pain monitoring clothing for elderly people with cognitive impairment according to claim 1, characterized in that: There are 20 pressure sensors arranged in a matrix inside the left front chest pressure sensing assembly, right front chest pressure sensing assembly, left abdomen pressure sensing assembly, right abdomen pressure sensing assembly, left lower abdomen pressure sensing assembly, right lower abdomen pressure sensing assembly, left back pressure sensing assembly, and right back pressure sensing assembly.

6. The vital sign and pain monitoring clothing for elderly people with cognitive impairment according to claim 1, characterized in that: The blood pressure measuring belt is provided with an air bag, a driving air pump connected to the air bag, a blood pressure sensor, and a microcontroller respectively connected to the blood pressure sensor and the driving air pump.

7. The vital sign and pain monitoring clothing for elderly people with cognitive impairment according to claim 1, characterized in that: The voice recognition component includes a voice sensor, a framing unit, a feature extraction unit, and a voice judgment unit connected in sequence, and the voice judgment unit is also connected to an acoustic model storage unit; A sound sensor, used for inputting a sound signal; A framing unit, used for intercepting the input signal with a predetermined time length as a frame unit to generate a framed input signal; A feature extraction unit, for generating a multi-dimensional vector of a framed input signal using Mel Cepstral Coefficients (MFCC); An acoustic model storage unit, used for storing an acoustic model used as a judgment standard; The sound determination unit is used to determine and output an acoustic model having the same characteristics as the input sound signal.

8. A method for monitoring the vital signs and pain sensation of elderly people with cognitive impairment using a vital signs and pain sensation monitoring suit according to claim 1, comprising the following steps: Step 1: Collect vital signs data: 1) The heart rate signal, respiratory rate signal, and blood oxygen saturation signal collected by the vital sign monitoring pad are collected through the data acquisition module, and the heart rate k times / minute, respiratory rate h times / minute, and blood oxygen saturation y% are obtained through the CPU module. The real-time collection is transmitted to the cloud server through the Bluetooth communication module for recording; 2) The blood pressure signal collected by the blood pressure measurement belt is collected through the data acquisition module, and the blood pressure value is obtained by the CPU module. The blood pressure value is measured every 30 minutes and transmitted to the cloud server through the Bluetooth communication module for recording; 3) The temperature signal collected by the temperature sensor is collected through the data acquisition module, and the temperature value is m℃ after being processed by the CPU module. The temperature signal is collected and transmitted to the cloud server for recording through the Bluetooth communication module; Step 2, process vital signs data: 1) Take the heart rate, respiratory rate, and blood oxygen saturation data 24 hours before the test time as samples, take the median and define it as the normal heart rate k p times / minute, respiratory rate h p times / minute, blood oxygen saturation p %; 2) Take the blood pressure data 24 hours before the test time point, take the median and define it as the normal blood pressure value a p mmHg; 3) Take the body temperature data 24 hours before the test time, take the median and define it as the normal body temperature value m p ℃; Step 3, collect data on physical compulsion: 1) Collecting signals of the first stretch sensor, the second stretch sensor, the third stretch sensor, and the fourth stretch sensor through a data acquisition module, and processing them through a CPU module to obtain the stretching degree E1% of the first stretch sensor, the stretching degree E2% of the second stretch sensor, the stretching degree E3% of the third stretch sensor, and the stretching degree E4% of the fourth stretch sensor; 2) The data acquisition module collects the signals of the pressure sensors in the left front chest pressure sensor assembly, the right front chest pressure sensor assembly, the left abdomen pressure sensor assembly, the right abdomen pressure sensor assembly, the left lower abdomen pressure sensor assembly, the right lower abdomen pressure sensor assembly, the left back pressure sensor assembly, and the right back pressure sensor assembly and groups them into 1 to 8 groups. The sensors in each group are numbered 1 to 20. After being processed by the CPU module, the pressure value matrix is ​​obtained as follows: The unit is N, i is the pressure value group number, i = (1, 8), j is the sensor number, j = (1, 20); Step 4: Collect sound information: 1) using a sound sensor of a sound recognition component to collect a sound signal, and using a framing unit to intercept the input signal in a frame unit having a predetermined duration to generate a framed input signal; 2) generating a multidimensional vector of the framed input signal using the Mel cepstral coefficients through the feature extraction unit; Step 5: Determine the pain status of elderly people with cognitive impairment: Step 5.1, evaluate vital signs status: The real-time monitored heart rate k times / minute, respiratory rate h times / minute, blood oxygen saturation y%, blood pressure value ammHg, body temperature value m℃ and the heart rate k under normal condition are compared. p times / minute, respiratory rate h p times / minute, blood oxygen saturation p %, blood pressure value is a p mmHg, body temperature value is m p ℃ make difference; When the changes in vital signs such as heart rate, respiratory rate, blood oxygen saturation and blood pressure are: heart rate increases by <20 beats / min, respiratory rate increases by <10 beats / min, blood oxygen saturation decreases by <5%, blood pressure increases by <20 mmHg, and body temperature increases by <1°C, the vital signs score is 0; When any of the vital signs, such as heart rate, respiratory rate, blood oxygen saturation, or blood pressure, changes as follows: When the heart rate increases by >20 beats / min, the respiratory rate increases by >10 beats / min, the blood oxygen saturation decreases by 5%, the blood pressure increases by >20 mmHg, and the body temperature increases by >1°C, the vital sign score is 1; When any of the vital signs, such as heart rate, respiratory rate, blood oxygen saturation, or blood pressure, changes as follows: When the heart rate increases by >25 beats / min, the respiratory rate increases by >20 beats / min, the blood oxygen saturation decreases by 10%, the blood pressure increases by >20 mmHg, and the body temperature increases by >1.5°C, the vital signs score is 2 points; Step 5.2, evaluate physical compulsion: 1) Take the first stretch sensor stretch data, the second stretch sensor stretch data, the third stretch sensor stretch data, and the fourth stretch sensor stretch data 24 hours before the detection time point, take the median and define it as the stretch of the first stretch sensor in the normal state E 1p %, the second stretch sensor stretch degree E 2p %, the third tensile sensor stretching degree E 3p %, fourth stretch sensor stretch degree E 4p %; 2) Calculate the change in the stretching degree of the first stretch sensor as Q1 = (E1-E 1p ) / E 1p *100%, the change in the stretching degree of the second stretch sensor is Q2 = (E2-E 2p ) / E 2p *100%, the change in the stretching degree of the third stretching sensor is Q3 = (E3-E 3p ) / E 3p *100%, the change in the stretching degree of the fourth stretching sensor is Q4 = (E4-E 4p ) / E 4p *100%; 3) Generate the influence matrix according to the layout of pressure sensors in, i is the pressure value group number, i=(1,8), j is the sensor number, j=(1,20); according to the pressure value matrix collected in step 3 Calculate the average pressure value of each group separately N=20, i is the pressure value group number, i=(1,8); when When , the influence value of the corresponding point in the matrix will be affected Set to 1; when When , the influence value of the corresponding point in the matrix will be affected Set to 2; when When , the influence value of the corresponding point in the matrix will be affected Set to 3; Define the maximum external pressure impact value 4) When the stretching change of the first stretch sensor, the stretching change of the second stretch sensor, the stretching change of the third stretch sensor, the stretching change of the fourth stretch sensor, and the external force pressure value are respectively: Q1<10%, Q2<10%, Q3<5%, Q4<5%, G=1, the limb compulsion score is 0; When any one of the stretching degree change of the first stretching sensor, the stretching degree change of the second stretching sensor, the stretching degree change of the third stretching sensor, the stretching degree change of the fourth stretching sensor, and the external force pressure value reaches: Q1>10%, Q2>10%, Q3>5%, Q4>5%, G=2, the limb compulsion score is assessed as 1; When any one of the stretching degree change of the first stretching sensor, the stretching degree change of the second stretching sensor, the stretching degree change of the third stretching sensor, the stretching degree change of the fourth stretching sensor, and the external force pressure value reaches: Q1>15%, Q2>15%, Q3>10%, Q4>10%, G=3, the limb compulsion score is assessed as 2; Step 5.3, evaluate the sound information: Step 5.3.1, establish an evaluation standard acoustic model: collect the groaning sounds of the elderly in mild pain state, moderate pain state, and severe pain state, and generate an evaluation standard acoustic model; Step 5.3.2, compare and score the sound information: The sound signal collected in step 4 is framed by the framing unit, and the multi-dimensional vector of the framed input signal is generated by the feature extraction unit using the Mel cepstral coefficient, and compared with the evaluation standard acoustic model library in step 5.3.1 to find the closest acoustic model; When the acoustic model that is closest to the evaluation standard is the mild pain state group, the sound information score is 1; When the closest evaluation standard acoustic model was the moderate pain state group, the sound information score was rated as 2; When the closest evaluation standard acoustic model was the severe pain state group, the sound information score was 3; When there is no sound information, the score of the sound information is 0; Step 5.4, Determination of pain status of elderly people with cognitive impairment: The vital signs scores, limb compulsion scores, and sound information scores evaluated in steps 5.1 to 5.3 are added together to obtain a pain status score of 0 to 7; When the pain status score was 0, it was judged that no pain occurred; When the pain status score was 1 to 3, it was judged as mild pain; When the pain status score is 4 to 5, it is judged as moderate pain; When the pain status score was 6 to 7, it was judged that severe pain occurred.

9. A method for monitoring vital signs and pain sensation in elderly people with cognitive impairment according to claim 8, characterized in that: In the step 5.3.1, the specific steps of establishing the evaluation standard acoustic model are: collect the groaning sounds of the elderly in mild pain state, moderate pain state, and severe pain state respectively, and establish 3 groups of information, each with 50 to 100 items; respectively intercept the input signal in frame units with a predetermined time length through the framing unit to generate a framed input signal; use Mel cepstral coefficients to generate a multidimensional vector of the framed input signal and store it as the evaluation standard acoustic model.

10. The method for monitoring vital signs and pain sensation of elderly people with cognitive impairment according to claim 8, characterized in that: In the step 5.2, the position of the pressure sensor corresponding to the maximum external force compression influence value G is determined to be the pain occurrence position.

Images