CN113892923B

CN113892923B - Physiological parameter detection method and intelligent mattress

Info

Publication number: CN113892923B
Application number: CN202111150744.8A
Authority: CN
Inventors: 王炳坤
Original assignee: De Rucci Healthy Sleep Co Ltd
Current assignee: De Rucci Healthy Sleep Co Ltd
Priority date: 2021-09-29
Filing date: 2021-09-29
Publication date: 2022-11-18
Anticipated expiration: 2041-09-29
Also published as: CN113892923A

Abstract

The invention discloses a physiological parameter detection method and an intelligent mattress. The physiological parameter detection method is applied to an intelligent mattress, wherein the intelligent mattress comprises a mattress body, a dot matrix sensor array and a processor, and the dot matrix sensor array is electrically connected with the processor; the lattice sensor array is arranged on the mattress body; the lattice type sensor array is used for sensing human body sign information to obtain a sensor point value graph and a sensor oscillogram; the physiological parameter detection method comprises the following steps: acquiring the sensor point value graph; determining a thoracic-back region and a hip region based on the sensor point value map; extracting respiratory information based on the sensor waveform map of the thoracic-back region; heart rate information is extracted based on the sensor waveform map of the hip region. The effect of improving the accuracy of physiological parameter detection is realized.

Description

Physiological parameter detection method and intelligent mattress

Technical Field

The embodiment of the invention relates to a physiological parameter detection technology, in particular to a physiological parameter detection method and an intelligent mattress.

Background

When obtaining some physiological parameters of a human body (such as heart rate and respiration), the existing intelligent mattress is usually provided with a sensor on the mattress, the sensor is usually positioned under the preset chest position of the human body so as to sense the heart rate and respiration signals of the human body, however, whether the physical sign information of the human body can be measured and influenced by sleeping posture or not is detected, the physical sign information of the human body cannot be sensed by the sensor at the sleeping position of the human body, and therefore, the accuracy of a detection result for detecting the physiological parameters of the human body is not enough.

Disclosure of Invention

The invention provides a physiological parameter detection method and an intelligent mattress, which aim to achieve the effect of improving the accuracy of physiological parameter detection.

In a first aspect, an embodiment of the present invention provides a physiological parameter detection method, which is applied to an intelligent mattress, where the intelligent mattress includes a mattress body, a dot matrix sensor array and a processor, and the dot matrix sensor array is electrically connected to the processor; the lattice type sensor array is arranged on the mattress body; the lattice type sensor array is used for sensing human body sign information to obtain a sensor dot value graph and a sensor oscillogram; the physiological parameter detection method comprises the following steps:

acquiring the sensor point value graph;

determining a chest and back region and a hip region based on the sensor point value map;

extracting respiratory information based on the sensor waveform map of the chest-back region;

heart rate information is extracted based on the sensor waveform map of the hip region. .

In an alternative embodiment of the invention, the sensor point value map comprises sensor point locations and sensor point value magnitudes;

the determining the chest and back area and the hip area based on the sensor point value map comprises:

determining a region support matrix based on the sensor point value map, wherein the region support matrix comprises sensor points with detection values larger than preset detection values and sensor point values;

determining a thoracic-back region and a hip region based on the region support matrix.

In an alternative embodiment of the invention, the determining the thorax region and the buttock region based on the region support matrix comprises:

traversing from the middle column of the area support matrix to two sides to calculate the column sum;

determining a column and a minimum intermediate position, and dividing the area support matrix into a first area and a second area based on the intermediate position; the first area is an area close to the head of the bed, and the second area is an area close to the tail of the bed;

determining the first region as a chest-back region;

determining the second area as a hip area.

In an optional embodiment of the present invention, after determining the region support matrix based on the sensor point value map, the method further includes:

determining sleeping posture information based on the region support matrix;

correspondingly, the extracting of the respiratory information based on the sensor waveform map of the thoracic-back region comprises:

determining respiratory extraction points of the thorax region based on the sleeping posture information and the region support matrix;

and extracting respiration information based on the sensor oscillogram of the respiration extraction point.

In an optional embodiment of the present invention, the determining sleeping posture information based on the regional support matrix comprises:

carrying out binarization processing on the region support matrix based on a preset threshold value to obtain a binarization region support matrix;

calculating the similarity of the binarization area support matrix and a plurality of preset sleeping posture templates respectively;

and determining the sleeping posture information based on the sleeping posture template with the maximum similarity.

In an optional embodiment of the present invention, the calculating the similarity between the binarized region support matrix and the preset sleeping posture templates respectively includes:

respectively differentiating the binary region support matrix with a plurality of preset sleeping posture templates and then taking the sum of squares;

correspondingly, the determining the sleeping posture information based on the sleeping posture template with the maximum similarity comprises the following steps:

and determining the sleeping posture information based on the sleeping posture template with the minimum square sum result.

In an optional embodiment of the present invention, after acquiring the sensor point value map, the method further includes:

determining a support region area based on the sensor point value map;

the sleep posture information is determined based on the sleep posture template with the maximum similarity, and the method comprises the following steps:

and determining the sleeping posture information based on the sleeping posture template with the maximum similarity and the area of the support area.

In an optional embodiment of the present invention, the determining the sleeping posture information based on the sleeping posture template with the largest similarity and the area of the support region includes:

determining whether the area of the support area is within a preset support range;

if so, determining the sleeping posture information as the corresponding sleeping posture of the sleeping posture template with the maximum similarity.

In an optional embodiment of the invention, said determining respiratory extraction points of said thoracic and dorsal regions based on said sleeping posture information and said region support matrix comprises:

determining a maximum dorsal support point for the dorsal thoracic region based on the region support matrix;

determining whether the sleeping posture information comprises side lying information;

if yes, determining the sensor point position which is away from the maximum chest and back support point by a preset distance and is positioned at the first position of the maximum chest and back support point as a respiration extraction point; the first orientation is the orientation of the hip region relative to the thorax region;

and if not, determining the maximum chest and back support point as a breathing extraction point.

In an optional embodiment of the invention, said determining the maximum dorsal support point of the dorsal thoracic region based on the region support matrix comprises:

traversing the region support matrix of the chest and back region by using a preset window, and calculating the sum of the point values of the sensors in a plurality of preset windows;

determining the preset window with the largest sum of the sensor point values;

and determining the sensor point with the largest sensor point value in the preset window with the largest sum of the sensor point values as a largest chest and back support point.

In an optional embodiment of the invention, the extracting heart rate information based on the sensor waveform map of the hip region comprises:

determining a maximum hip support point for the hip region;

heart rate information is extracted based on the sensor waveform map of the maximum hip support point.

In an alternative embodiment of the invention, said determining the maximum hip support point for said hip region comprises:

traversing the area support matrix of the hip area by using a preset window, and calculating the sum of the values of the sensor points in the preset windows;

determining the preset window with the largest sum of the sensor point values;

and determining the sensor point position with the largest sensor point value in the preset window with the largest sum of the sensor point values as the largest hip supporting point.

In a second aspect, an embodiment of the present invention further provides an intelligent mattress, which includes a mattress body, a lattice sensor array and a processor, where the lattice sensor array is electrically connected to the processor;

the lattice sensor array is arranged on the mattress body;

the lattice type sensor array is used for sensing human body sign information to obtain a sensor dot value graph and a sensor oscillogram;

the processor is used for executing the physiological parameter detection method of any embodiment of the invention.

In an alternative embodiment of the invention, the array of lattice sensors comprises an array of lattice piezoceramic sensors.

According to the invention, the sensor point value image is obtained, the thoracic and dorsal regions and the hip region are determined based on the sensor point value image, then the respiration information is extracted based on the sensor oscillogram of the thoracic and dorsal regions, the heart rate information is extracted based on the sensor oscillogram of the hip region, the respiration extraction is based on the collection of signals of contraction and expansion of the thoracic cavity caused by respiration, the most obvious change during respiration is the motion of the thoracic cavity, and the stronger the respiration signal is, the smaller the interference is at the place with the largest force application point. Respiratory information is extracted through a sensor oscillogram in the chest and back area, and the obtained respiratory information is accurate. Meanwhile, the buttocks are generally at the position with the largest force (the heartbeat waveform signal at the point with the largest force is strongest and is influenced the weakest by respiration interference), and the influence of fluctuating pressure change of thoracic cavity respiration is basically avoided, so the heart rate information is extracted through a sensor waveform diagram based on the buttocks area, and the obtained heart rate information is more accurate. Therefore, the effect of improving the accuracy of the physiological parameter detection is achieved.

Drawings

Fig. 1 is a schematic structural diagram of an intelligent mattress applied to a physiological parameter detection method according to an embodiment of the present invention;

FIG. 2 is a flowchart of a physiological parameter detecting method according to an embodiment of the present invention;

fig. 3 is a sensor dot value diagram obtained based on a dot matrix sensor array according to an embodiment of the present invention;

FIG. 4 is a waveform diagram of a sensor for extracting respiratory information according to an embodiment of the present invention;

FIG. 5 is a waveform diagram of a sensor for extracting heart rate information according to an embodiment of the present invention;

fig. 6 is a flowchart of a physiological parameter detecting method according to a second embodiment of the present invention;

fig. 7 is a schematic diagram of the step S230 of determining the thoracic and dorsal regions and the hip region based on the region support matrix according to the second embodiment of the present invention;

fig. 8 is a sensor dot value chart obtained based on a dot matrix sensor array according to a second embodiment of the present invention;

fig. 9 is a flowchart of a physiological parameter detecting method according to a third embodiment of the present invention;

fig. 10 is a schematic diagram of the step of determining the sleeping posture information based on the region support matrix in step S330 according to the third embodiment of the present invention;

fig. 11 is a schematic diagram of the step S350 of determining the respiratory extraction point of the thoracic back region based on the sleeping posture information and the region support matrix according to the third embodiment of the present invention;

fig. 12 is a schematic diagram of a step S370 of extracting heart rate information based on the sensor waveform diagram of the hip region according to the third embodiment of the present invention.

Wherein, 1, a processor; 2. a lattice sensor array; 3. a mattress body.

Detailed Description

The present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a schematic structural diagram of an intelligent mattress applied to a physiological parameter detection method according to an embodiment of the present invention, fig. 2 is a flowchart of a physiological parameter detection method according to an embodiment of the present invention, and fig. 3 is a sensor dot value diagram obtained based on a dot matrix sensor array according to an embodiment of the present invention. The embodiment can be suitable for the physiological parameter detection condition, the method is applied to the intelligent mattress, as shown in fig. 1, the intelligent mattress comprises a mattress body 3, a dot matrix type sensor array 2 and a processor 1, and the dot matrix type sensor array 2 is electrically connected with the processor 1; the lattice type sensor array 2 is arranged on the mattress body 3; the lattice type sensor array 2 is used for sensing human body sign information to obtain a sensor dot value graph and a sensor waveform graph. As shown in fig. 2, the method for detecting physiological parameters specifically includes the following steps:

and S110, acquiring the sensor point value graph.

The human body physical sign information refers to information generated when a human body lies on the intelligent mattress, for example, the human body has gravity, and the human body physical sign information can be information related to the gravity, and is not specifically limited herein.

The lattice sensor array is composed of a plurality of sensors arranged, and as shown in fig. 3, the sensor point diagram refers to a diagram formed by the points of the sensors and the values of the points of the sensors. The waveform diagram is a curve, called a wave, that reflects different displacements of particles at the same time. The waveform plot is used to display one or more curves of measured values as uniformly collected. The sensor waveform is a plot of the voltage values of the sensor at different times.

And S120, determining a chest and back area and a hip area based on the sensor point value graph.

The chest and back area refers to an area contacted by the chest and back of the user on the intelligent mattress, and the hip area refers to an area contacted by the hip of the user on the intelligent mattress.

S130, extracting respiratory information based on the sensor oscillogram of the chest and back area.

The respiratory extraction is based on the collection of signals of contraction and expansion of the chest cavity caused by respiration, the most obvious change during respiration is the motion of the chest cavity, and the stronger the respiratory signal is, the smaller the interference is at the place with the largest force application point. Respiratory information is extracted through a sensor oscillogram in the chest and back area, and the obtained respiratory information is accurate. Fig. 4 is a waveform diagram of a sensor for extracting respiration information according to an embodiment of the present invention, and as shown in fig. 4, the respiration information can be extracted through the waveform diagram of the sensor.

S140, extracting heart rate information based on the sensor oscillogram of the hip area.

The buttocks are generally the position with the largest force (the heartbeat waveform signal at the point with the largest force is strongest and is relatively weakest influenced by respiration interference), and are basically not influenced by fluctuating pressure change of thoracic cavity respiration. Fig. 5 is a waveform diagram of a sensor for extracting heart rate information according to an embodiment of the present invention, and as shown in fig. 5, heart rate information can be extracted through the waveform diagram of the sensor.

In addition, according to different application scenarios, the step S130, the step S140 of extracting respiratory information and the step S140 of extracting heart rate information based on the sensor waveform diagram of the chest and back region and the step S140 of extracting heart rate information based on the sensor waveform diagram of the hip region may be performed in the above order or may be performed simultaneously, and in some embodiments, the step S140 of extracting heart rate information based on the sensor waveform diagram of the hip region may be performed first, and then the step S130 of extracting respiratory information based on the sensor waveform diagram of the chest and back region and the step S140 of extracting heart rate information based on the sensor waveform diagram of the hip region may be performed without specific limitation on the execution order of the step S130, the step S140 of extracting respiratory information and the step S140 of extracting heart rate information based on the sensor waveform diagram of the chest and back region.

According to the scheme, the sensor point value graph is obtained, the chest and back area and the hip area are determined based on the sensor point value graph, then the respiration information is extracted based on the sensor waveform graph of the chest and back area, the heart rate information is extracted based on the sensor waveform graph of the hip area, the respiration extraction is based on the collection of signals of contraction and expansion of the thoracic cavity caused by respiration, the most obvious change is the motion of the thoracic cavity during respiration, and the stronger the respiration signal is, the smaller the interference is in the place with the largest force application point. Respiratory information is extracted through a sensor oscillogram in the chest and back area, and the obtained respiratory information is accurate. Meanwhile, the buttocks are generally at the position with the maximum force (the heartbeat waveform signal at the point with the maximum force is strongest and is influenced the weakest by respiration interference), and the influence of fluctuating pressure change of thoracic cavity respiration is basically avoided, so the heart rate information is extracted through a sensor waveform diagram based on the buttocks area, and the obtained heart rate information is more accurate. Therefore, the effect of improving the accuracy of the physiological parameter detection is achieved.

Example two

Fig. 6 is a flowchart of a physiological parameter detection method according to a second embodiment of the present invention, which is optimized based on the first embodiment. Optionally, the sensor point value map includes sensor point positions and sensor point value sizes; the determining of the thorax region and the buttock region based on the sensor point value map comprises: determining a region support matrix based on the sensor point value map, wherein the region support matrix comprises sensor points with detection values larger than preset detection values and sensor point values; determining a thorax region and a hip region based on the region support matrix.

As shown in fig. 6, the method includes:

and S210, acquiring the sensor point value graph.

S220, determining a region support matrix based on the sensor point value graph, wherein the region support matrix comprises sensor point positions and sensor point values, the detection values of which are larger than preset detection values.

The region support matrix is a matrix formed by sensor point values and sensor point values, which are sensed by a human body lying on the mattress body, on the intelligent mattress, and in some embodiments, the region is a region of a sensor point value part 0 in a sensor point value diagram shown in fig. 3, so that the region support matrix can reflect different pressure conditions from the human body to sensors at different positions.

The sensor point location is also called a sensor point location or a sensor point coordinate, the sensor point location may refer to a location of a sensor in a sensor point value diagram formed by the lattice sensor array, the sensor point location may also refer to a sensor point amplitude, and the sensor point location may refer to a value detected by the sensor and capable of reflecting different pressures. The detection value refers to a sensor point value detected by the sensor, and when the detection value is larger than a preset detection value, the pressure generated when the human body is detected to be positioned on the mattress body by the sensor at the sensor point position is shown.

And S230, determining a chest and back area and a hip area based on the area support matrix.

The stress conditions of the sensors corresponding to different sensor point positions are reflected by the area support matrix and come from a human body, so that the chest and back area and the hip area can be conveniently determined based on the area support matrix.

S240, extracting respiratory information based on the sensor oscillogram of the chest and back area.

And S250, extracting heart rate information based on the sensor oscillogram of the hip area.

Exemplarily, as shown in fig. 7, the step S230 of determining the thoracic and dorsal regions and the hip region based on the region support matrix specifically includes:

and S231, traversing from the middle column of the region support matrix to two sides to calculate the column sum.

Where column sum refers to the sum of the sensor point values of that column.

S232, determining a column and a minimum middle position, and dividing the area support matrix into a first area and a second area based on the middle position; the first area is an area close to the head of the bed, and the second area is an area close to the tail of the bed.

As shown in fig. 8, when a human body lies on the mattress body, the boundary position between the thoracic region and the back region generally applies a small force to the mattress body, so that the boundary position between the thoracic region and the back region can be conveniently determined by determining the row and the minimum middle position, and then the region support matrix is divided into the first region and the second region, so that the thoracic region and the back region can be conveniently determined.

And S233, determining the first area as a chest and back area.

Wherein the first zone is defined as the thorax region because the thorax region is generally closer to the head of the bed than the buttocks region.

And S234, determining the second area as a hip area.

Wherein the second zone can be identified as the hip zone because the second zone is near the head of the bed and the hip zone is typically closer to the foot than the back of the chest zone.

In the above scheme, according to different application scenarios, step S233, determining the first region as the chest-back region and step S234, and determining the second region as the hip region may be performed according to the above steps or may be performed simultaneously, and in some embodiments, step S234 may be performed first, the second region is determined as the hip region, and then step S233 is performed, and the first region is determined as the chest-back region. The execution sequence of step S233, determining the first region as the chest-back region and step S234, and determining the second region as the hip region is not specifically limited.

EXAMPLE III

Fig. 9 is a flowchart of a physiological parameter detection method according to a third embodiment of the present invention, which is optimized based on the second embodiment. Optionally, after determining the region support matrix based on the sensor point value map, the method further includes: determining sleeping posture information based on the region support matrix; correspondingly, the extracting the respiratory information based on the sensor waveform map of the chest-back region comprises: determining respiratory extraction points of the thorax region based on the sleeping posture information and the region support matrix; and extracting respiration information based on the sensor oscillogram of the respiration extraction point.

As shown in fig. 9, the method has the steps of:

and S310, acquiring the sensor point value graph.

S320, determining a region support matrix based on the sensor point value map, wherein the region support matrix comprises sensor points with detection values larger than preset detection values and sensor point values.

And S330, determining sleeping posture information based on the region support matrix.

The regional support matrix reflects the stress condition of the mattress body, and the stress of the mattress body comes from a user, so the sleeping posture information of the user can be accurately determined according to the shape of the regional support matrix and the like.

S340, determining a chest and back area and a hip area based on the area support matrix.

S350, determining a respiratory extraction point of the chest and back area based on the sleeping posture information and the area support matrix.

And S360, extracting the respiratory information based on the sensor oscillogram of the respiratory extraction point.

The sleeping posture information reflects the sleeping posture of the user on the mattress body, such as supine, prone, left-side, right-side and the like. The respiration extraction point is a sensor point position where a sensor for extracting respiration information from a sensor oscillogram is located. When the sleeping postures of the user are different, the breathing extraction points are determined at different positions of the chest and back area, so that the breathing information of the user can be obtained more accurately.

S370, extracting heart rate information based on the sensor oscillogram of the hip area.

Illustratively, as shown in fig. 10, the determining sleeping posture information based on the region support matrix in step S330 includes:

and S331, carrying out binarization processing on the region support matrix based on a preset threshold value to obtain a binarization region support matrix.

The binarization processing refers to converting each sensor point value in the area support matrix into 0 and 1, the preset threshold value refers to a standard value used for judging 0 and 1, the sensor point value is judged to be 1 when being larger than the preset threshold value, and the sensor point value is judged to be 0 when being smaller than the preset threshold value.

And S332, calculating the similarity between the binarization area support matrix and a plurality of preset sleeping posture templates.

The preset sleeping posture templates are binary matrix templates with only 0 and 1, and similarity is calculated between the binary region support matrix and the preset sleeping posture templates, so that the sleeping posture information of the user can be obtained conveniently.

And S333, determining the sleeping posture information based on the sleeping posture template with the maximum similarity.

When the similarity between the binarization area support matrix and a certain sleeping posture template is the maximum, the fact that the user is most likely to be the sleeping posture corresponding to the current sleeping posture template is explained, and therefore the sleeping posture information can be conveniently determined based on the sleeping posture template with the maximum similarity.

Specifically, the calculating the similarity between the binarized region support matrix and a plurality of preset sleeping posture templates respectively includes:

respectively differentiating the binary region support matrix with a plurality of preset sleeping posture templates and then taking the sum of squares; correspondingly, the determining the sleeping posture information based on the sleeping posture template with the maximum similarity comprises the following steps: and determining the sleeping posture information based on the sleeping posture template with the minimum square sum result.

The difference is made between the binarization region support matrix and a plurality of preset sleeping posture templates, the sum of squares is obtained, the difference degree between the binarization region support matrix and different preset sleeping posture templates can be conveniently judged, and the similarity between the binarization region support matrix and different preset sleeping posture templates is obtained. When the square sum result is the minimum, the smaller the difference degree between the binarization region support matrix and the preset sleeping posture template is, the maximum similarity between the binarization region support matrix and the preset sleeping posture template is explained, so that the sleeping posture information can be conveniently determined.

In an optional embodiment of the present invention, after acquiring the sensor point value map, the method further includes: determining a support region area based on the sensor point value map; the sleep posture information is determined based on the sleep posture template with the maximum similarity, and the method comprises the following steps: and determining the sleeping posture information based on the sleeping posture template with the maximum similarity and the area of the support area.

The support region area is an area of all sensor points that receive pressure from a user, and since the sensor point value map is composed of sensor points and sensor point values of all sensors at a certain time, the support region area can be determined based on the sensor point value map. The sleeping area of a normal person is within a certain range, namely the area of the supporting area is within a certain range, the sleeping posture information is determined by combining the sleeping posture template with the maximum similarity with the area of the supporting area, the normal sleeping and the non-sleeping (interference of other objects such as quilts, pillows and the like) of the person can be distinguished, the range of the area of the supporting area during the actual sleeping of the person is obtained through quantitative experiments for judgment, and the accuracy of determining the sleeping posture information is improved.

In an optional embodiment of the present invention, the determining the sleeping posture information based on the sleeping posture template with the largest similarity and the area of the support region includes: determining whether the area of the support area is within a preset support range; if yes, the sleeping posture information is determined as the corresponding sleeping posture of the sleeping posture template with the maximum similarity.

The preset support range is the range of the area of the support area when a person normally sleeps, whether the person normally sleeps can be known by determining whether the area of the support area is in the preset support range, and if so, the sleeping posture of the user can be judged, so that the sleeping posture information can be determined to be the corresponding sleeping posture of the sleeping posture template with the maximum similarity, the accuracy of sleeping posture identification is improved, and false identification is prevented.

On the basis of the above embodiment, as shown in fig. 11, the determining, at S350, a respiration extraction point of the thoracic-back region based on the sleeping posture information and the region support matrix includes:

s351, determining the maximum chest and back support point of the chest and back area based on the area support matrix.

Wherein, the maximum chest and back supporting point refers to the point position of the sensor with the maximum stress.

And S352, determining whether the sleeping posture information comprises side lying information.

The lateral lying information is information representing whether the user lies laterally, and the left lateral lying information and the right lateral lying information belong to the lateral lying information.

If yes, go to step S353. If not, go to step S354.

S353, determining the sensor point position which is away from the maximum chest and back supporting point by a preset distance and is located at the first position of the maximum chest and back supporting point as a respiration extraction point; the first orientation is an orientation of the hip region relative to the thorax region.

Wherein, people with different body types have different characteristics of the support matrix under different sleeping postures. For example, a larger sized person lying on their side and a smaller sized person lying on their back may have a closer support matrix. When the patient lies on the side and lies on the back, the point possibly stressed most is the shoulder when the patient lies on the side, namely the point corresponding to the maximum chest and back supporting point is the shoulder. The respiration extraction is based on the collection of signals of contraction and expansion of the chest cavity caused by respiration, the most obvious change during respiration is the movement of the chest cavity, and the stronger the respiration signal is, the smaller the interference is at the place with the largest force application point. Therefore, when the user lies on the side, the sensor point position which is away from the maximum chest and back supporting point by the preset distance and is located at the first position of the maximum chest and back supporting point is determined as the respiratory extraction point, and the extraction accuracy of the respiratory information can be improved.

And S354, determining the maximum chest and back supporting point as a respiratory extraction point.

When the user does not lie on the side, the point with the maximum stress is usually the thorax, namely the maximum thoracic and dorsal support point corresponds to the thorax, and the maximum thoracic and dorsal support point is determined as the respiratory extraction point, so that the accuracy of extracting respiratory information can be improved.

Illustratively, the determining a maximum dorsal support point for the dorsal thoracic region based on the region support matrix includes:

traversing the region support matrix of the chest and back region by using a preset window, and calculating the sum of the values of the sensor points in a plurality of preset windows; determining the preset window with the largest sum of the sensor point values; and determining the sensor point position with the largest sensor point value in the preset window with the largest sum of the sensor point values as the largest chest and back support point.

The preset window refers to a window including a plurality of sensor point values and sensor point values, the size of the preset window may be different according to different use conditions, for example, 5 × 5, 3 × 3, 2 × 2, 3 × 4, 3 × 5 and the like, where 3 × 5 refers to 3 rows and 5 columns of windows, the region support matrix is traversed through the windows, then the sensor point with the largest sensor point value in the preset window with the largest sum of the sensor point values is determined as the largest chest and back support point, and compared with the single sensor point value, the calculation speed is faster.

In an alternative embodiment of the present invention, as shown in fig. 12, the step S370 of extracting heart rate information based on the sensor waveform pattern of the hip region includes:

s371, determining the maximum hip supporting point of the hip area.

And S372, extracting heart rate information based on the sensor oscillogram of the maximum hip supporting point.

The maximum hip supporting point refers to the point position of the sensor where the sensor with the largest stress is located, the heartbeat waveform signal of the point with the largest stress is strongest and is influenced the weakest by respiration interference, meanwhile, the influence of fluctuating pressure change of thoracic cavity respiration is basically avoided, and the maximum hip supporting point can be determined through experiments. Therefore, the heart rate information is extracted based on the sensor oscillogram at the maximum hip supporting point of the hip area, and the obtained heart rate information is accurate.

Illustratively, the determining the maximum hip support point for the hip region includes:

traversing the area support matrix of the hip area by using a preset window, and calculating the sum of the point values of the sensors in the preset windows; determining the preset window with the largest sum of the sensor point values. And determining the sensor point position with the largest sensor point value in the preset window with the largest sum of the sensor point values as the largest hip supporting point.

From the above, the area support matrix is traversed through the window, then the sensor point position with the largest sensor point value in the preset window with the largest sum of the sensor point values is determined as the largest hip support point, and compared with the single sensor point values, the calculation speed is high.

Example four

This embodiment four provides an intelligent mattress, as shown in fig. 1, this intelligent mattress includes mattress body 3, dot matrix sensor array 2 and treater 1, and dot matrix sensor array 2 and treater 1 electricity are connected.

The lattice sensor array 2 is arranged on the mattress body 3.

The lattice type sensor array 2 is used for sensing human body sign information to obtain a sensor dot value graph and a sensor oscillogram.

The processor 1 is adapted to perform the method of detecting a physiological parameter of any of the embodiments of the present invention.

Above-mentioned scheme, through setting up dot-matrix sensor array 2, dot-matrix sensor array 2 can the perception human sign information obtain sensor dot value picture and sensor oscillogram, processor 1 is through obtaining sensor dot value picture, and confirm chest back region and buttock region based on sensor dot value picture, then draw respiratory information based on the sensor oscillogram of chest back region, draw heart rate information based on the sensor oscillogram of buttock region, because it draws to breathe to produce the signal of contraction and expansion because of gathering the thorax because of breathing based on the thorax, and the most obvious change is the motion of thorax during breathing, the place that the impetus is the biggest, respiratory signal is stronger, it is less to be disturbed. Respiratory information is extracted through a sensor oscillogram in the chest and back area, and the obtained respiratory information is accurate. Meanwhile, the buttocks are generally at the position with the maximum force (the heartbeat waveform signal at the point with the maximum force is strongest and is influenced the weakest by respiration interference), and the influence of fluctuating pressure change of thoracic cavity respiration is basically avoided, so the heart rate information is extracted through a sensor waveform diagram based on the buttocks area, and the obtained heart rate information is more accurate. Therefore, the effect of improving the accuracy of the physiological parameter detection is achieved.

In an alternative embodiment of the invention, the lattice sensor array 2 comprises a lattice piezoceramic sensor array.

Wherein, the dot matrix piezoceramics sensor array indicates the dot matrix array of constituteing through a plurality of piezoceramics sensors, piezoceramics sensor's advantage: economical, the signal is relatively good for the film, and the mutual interference is small. Therefore, by using the piezoelectric ceramic sensor to form a lattice type piezoelectric ceramic sensor array, the interference received during detection is small, and the piezoelectric ceramic sensor array is economical and has better signals.

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the particular embodiments described herein, and that various obvious changes, rearrangements and substitutions will now be apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in some detail by the above embodiments, the invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the invention, and the scope of the invention is determined by the scope of the appended claims.

Claims

1. A physiological parameter detection method is applied to an intelligent mattress and is characterized in that the intelligent mattress comprises a mattress body, a dot matrix sensor array and a processor, wherein the dot matrix sensor array is electrically connected with the processor; the lattice sensor array is arranged on the mattress body; the lattice type sensor array is used for sensing human body sign information to obtain a sensor point value graph and a sensor oscillogram; the physiological parameter detection method comprises the following steps:

acquiring the sensor point value graph;

determining a thoracic-back region and a hip region based on the sensor point value map;

extracting heart rate information based on the sensor waveform map of the hip region;

wherein the sensor point value map comprises sensor point positions and sensor point value sizes;

determining a thoracic-back region and a hip region based on the region support matrix;

wherein the determining a thorax region and a buttock region based on the region support matrix comprises:

determining the first region as a thoracic-back region;

determining the second area as a hip area;

wherein the extracting heart rate information based on the sensor waveform map of the hip region comprises:

determining a maximum hip support point for the hip region;

extracting heart rate information based on the sensor oscillogram of the maximum hip support point;

wherein the determining a maximum hip support point for the hip region comprises:

determining the preset window with the largest sum of the sensor point values;

and determining the sensor point with the largest sensor point value in the preset window with the largest sum of the sensor point values as a largest hip supporting point.

2. The method of claim 1, wherein after determining a region support matrix based on the sensor point value map, further comprising:

determining sleeping posture information based on the region support matrix;

correspondingly, the extracting the respiratory information based on the sensor waveform map of the chest-back region comprises:

3. The physiological parameter detection method according to claim 2, wherein said determining sleeping posture information based on said regional support matrix comprises:

calculating the similarity of the binarization region support matrix and a plurality of preset sleeping posture templates respectively;

4. The method for detecting physiological parameters according to claim 3, wherein the calculating the similarity between the binarized region support matrix and a plurality of preset sleeping posture templates comprises:

5. The method of claim 3, wherein said obtaining said sensor point value map further comprises:

determining a support region area based on the sensor point value map;

6. The physiological parameter detecting method according to claim 5, wherein the determining the sleeping posture information based on the sleeping posture template with the largest similarity and the supporting area comprises:

7. The method of claim 2, wherein said determining a respiratory extraction point of said thorax region based on said sleeping posture information and said region support matrix comprises:

determining a maximum dorsal support point for the dorsal region based on the region support matrix;

if so, determining the sensor point position which is away from the maximum chest and back support point by a preset distance and is positioned at the first position of the maximum chest and back support point as a respiration extraction point; the first orientation is the orientation of the hip region relative to the thorax region;

and if not, determining the maximum chest and back support point as a respiratory extraction point.

8. A method for detecting physiological parameters according to claim 7, wherein said determining a maximum thoracic back support point for said thoracic back region based on said region support matrix comprises:

traversing the region support matrix of the chest and back region by using a preset window, and calculating the sum of the values of the sensor points in a plurality of preset windows;

determining the preset window with the largest sum of the sensor point values;

and determining the sensor point position with the largest sensor point value in the preset window with the largest sum of the sensor point values as the largest chest and back support point.

9. An intelligent mattress, its characterized in that: the mattress comprises a mattress body (3), a dot matrix sensor array (2) and a processor (1), wherein the dot matrix sensor array (2) is electrically connected with the processor (1);

the lattice type sensor array (2) is arranged on the mattress body (3);

the dot matrix type sensor array (2) is used for sensing human body sign information to obtain a sensor dot value graph and a sensor oscillogram;

the processor (1) is configured to perform the method of physiological parameter detection of any one of claims 1-8.

10. The smart mattress of claim 9, wherein the array of lattice sensors (2) comprises an array of lattice piezoceramic sensors.