WO2021108954A1 - 基于传感器阵列的检测控制方法和装置 - Google Patents

基于传感器阵列的检测控制方法和装置 Download PDF

Info

Publication number
WO2021108954A1
WO2021108954A1 PCT/CN2019/122407 CN2019122407W WO2021108954A1 WO 2021108954 A1 WO2021108954 A1 WO 2021108954A1 CN 2019122407 W CN2019122407 W CN 2019122407W WO 2021108954 A1 WO2021108954 A1 WO 2021108954A1
Authority
WO
WIPO (PCT)
Prior art keywords
sensor array
array elements
effective pressure
energy
elements
Prior art date
Application number
PCT/CN2019/122407
Other languages
English (en)
French (fr)
Inventor
焦旭
Original Assignee
北京微动数联科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京微动数联科技有限公司 filed Critical 北京微动数联科技有限公司
Priority to CN201980003424.4A priority Critical patent/CN111093485B/zh
Priority to PCT/CN2019/122407 priority patent/WO2021108954A1/zh
Publication of WO2021108954A1 publication Critical patent/WO2021108954A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1113—Local tracking of patients, e.g. in a hospital or private home
    • A61B5/1114—Tracking parts of the body
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
    • A61B5/6892—Mats
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0247—Pressure sensors
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the invention belongs to the field of information technology, and particularly relates to a detection control method and device based on a sensor array.
  • a detection control method based on a sensor array the sensor array including a plurality of sensor array elements, and the method includes:
  • a control command is generated in response to the presence of the element that obtains the effective pressure.
  • a detection control device based on a sensor array includes a plurality of sensor array elements, and the device includes:
  • a signal collection unit used to collect the signals of the multiple sensor array elements in the sensor array
  • a calculation unit configured to calculate the energy corresponding to each of the plurality of sensor array elements based on the signals sent by the plurality of sensor array elements;
  • a judging unit for judging whether there is an array element that obtains an effective pressure among the multiple sensor array elements according to the energy corresponding to each of the multiple sensor array elements;
  • the command generation unit is used to generate control commands in response to the presence of the element that obtains the effective pressure.
  • an electronic device including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the method of the first aspect when the computer program is executed by the processor.
  • a computer-readable storage medium which stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute the method provided in the first aspect.
  • a computer program product in a fifth aspect, includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the method provided in the first aspect.
  • the non-wearable technology based detection of the user's action can be converted into a control instruction, the data volume of the control instruction is small and the privacy of the user can be protected.
  • Fig. 1 is a schematic diagram of a signal acquisition sensor array according to an embodiment.
  • Fig. 2 is a cross-sectional view of the signal acquisition sensor array shown in Fig. 1 according to an embodiment.
  • Fig. 3 is a flowchart of a detection control method based on a sensor array according to an embodiment of the present invention.
  • Fig. 4 is an exemplary diagram for explaining the solution of the present invention according to an embodiment of the present invention.
  • Fig. 5 is a schematic diagram of a detection control device based on a sensor array according to an embodiment of the present invention.
  • Fig. 6 is a structural diagram of an electronic device provided by an embodiment of the present application.
  • Fig. 1 is a schematic diagram of a signal acquisition sensor array according to an embodiment.
  • Fig. 2 is a cross-sectional view of the signal acquisition sensor array shown in Fig. 1 according to an embodiment.
  • a signal acquisition sensor array 10 includes: a connection layer 105, at least two sensor units 111 and 112, and a signal acquisition circuit 107 for connecting each sensor unit 111 or 112 with The signal line 104 electrically connected to the signal collection circuit 107, each of the sensor units 111 or 112 further includes: a first shock-resistant substrate 101 or 102; a sensor element 103, which is connected to the first shock-resistant substrate 101 or 102 corresponds one-to-one and is arranged between the first shock-absorbing substrate 101 or 102 and the connecting layer 105; wherein the at least two sensor units are arranged in an array on the connecting layer at intervals.
  • the shock-absorbing substrate here refers to a material that has a shock-absorbing effect (attenuation effect), such as sponge, rubber, foam and other materials.
  • the shock-absorbing substrate can be made into a sheet shape or a block shape with a recessed shape. If it is made into a block with a recessed shape, the sensor element can be accommodated in the recessed shape, and by adjusting the size of the recess, the shock resistance effect can be further adjusted.
  • the signal lines illustrated in Figures 1 and 2 are connected in series between the sensor units, but those skilled in the art should know that they can also be connected to each sensor unit 111 or 112 and the signal acquisition circuit 107 with signal lines. between.
  • At least two kinds of sensor units are arranged in an array at intervals, and the sensor elements in the sensor units are arranged in a one-to-one correspondence with the first shock-absorbing substrate and are arranged between the first shock-absorbing substrate and the connecting layer, so that Different signals are attenuated to different degrees after being transmitted to each sensor unit, and because the first shock-absorbing substrate is separated, the strong coupling of forces between each sensor unit is released, resulting in different physiological signals with very different signal amplitudes. All are accurately detected by the sensor array.
  • Figure 1 shows an 8 ⁇ 8 array. Those skilled in the art need to understand that this is only an example, and rows and columns of other values can also be used for combination.
  • a substrate layer 106 is further provided between each sensor element 103 and the connection layer 105, which is used to carry the sensor element and the related conditioning circuit, so that the whole has a relatively high rigidity and avoids damage.
  • a plurality of the sensor units 111 or 112 share a signal collection circuit 107.
  • a larger area of acquisition can be realized with fewer acquisition circuits, which not only helps to save costs, but also reduces the time interval of signal acquisition and increases the rate of signal acquisition by using technologies such as serial buses.
  • at least one signal acquisition circuit 107 is further connected to the central processing unit of the entire array.
  • the product of the shock-absorbing characteristics of the first shock-absorbing substrate included in the sensor unit 111, the sensitivity of the included sensor element, and the sensitivity of the corresponding signal acquisition circuit is that the product of the other sensor unit 112 includes The product of the shock-absorbing characteristics of the first shock-absorbing substrate, the sensitivity of the included sensor element, and the sensitivity of the corresponding signal acquisition circuit is more than twice the product.
  • the anti-vibration characteristic refers to the attenuation multiple of the vibration.
  • the anti-vibration characteristic of a material is 40%, which means that it can attenuate the vibration by 40%, and only 60% of the vibration can be transmitted from one side to the other.
  • the meaning of the sensitivity of the sensor and the sensitivity of the acquisition circuit has been fully defined in the prior art, and will not be repeated for the sake of brevity.
  • the sensor element may be a piezoelectric sheet, or a strain gauge, a piezoresistive sensor, etc., or a combination of multiple kinds thereof.
  • the sensor element is provided with an operational amplifier circuit, which can amplify the initial signal.
  • the different sensitivities of the sensor elements can be achieved by setting different element types or different magnifications of operational amplifier circuits.
  • the sensor arrays of Figure 1 and Figure 2 include multiple sensor array elements for collecting signals. It should be noted that Fig. 1 and Fig. 2 only show a specific way of the structure and composition of the sensor array for collecting signals. Those skilled in the art can understand that any other forms of signal-collecting sensor arrays can be used, and these all fall within the scope of this application.
  • a detection control method based on a pressure sensor array is proposed. By detecting the signals of multiple elements in the sensor array, it is determined whether there is an element that obtains effective pressure. In the case of, determine the corresponding semantics and generate control instructions. Then, according to the generated control command, the corresponding control action can be implemented.
  • Fig. 3 is a flowchart of a detection control method based on a sensor array according to an embodiment of the present invention.
  • the sensor array is a pressure sensor array and includes a plurality of sensor array elements.
  • the method includes the following steps:
  • Step S301 Collect the signals of multiple sensor array elements in the sensor array.
  • a pressure sensor array includes I ⁇ J array elements, where I and J are both positive integers, and their product is greater than or equal to 2.
  • the signal of each sensor array element is collected at a certain sampling rate, and the sampling result is recorded as S ij (n), where i, j are the coordinates of the array element (1 ⁇ i ⁇ I, 1 ⁇ j ⁇ J).
  • the adoption rate can be a preset frequency, such as 50 Hz
  • the sampling result S ij (n) can be a voltage quantized value, and the unit can be millivolt (mV) or volt (V);
  • n is a count of sampling, such as The first sampling, the second sampling, etc.
  • the sampling result S ij (n) is filtered.
  • the filter is designed to filter out the frequencies outside the frequency range of the effective pressure, so as to retain the effective pressure to the maximum extent and filter out interference factors.
  • the pressure sensor array is a mattress, and when the user is lying on it, the mattress can detect breathing, heartbeat, and body movements.
  • the sampling result S ij (n) contains signals related to breathing, heartbeat, and body movements. It is generally believed that users form user intentions and instructions by applying physical movements on the mattress. Then, you need to filter out the signals related to breathing and heartbeat.
  • the signal related to the heartbeat is very weak and can be ignored, and the signal related to breathing has a lower frequency than the signal related to body movement. Therefore, the sampling result S ij (n) can be high-pass filtered to reduce
  • the high-pass cutoff frequency is set at 0.5Hz to filter out low-frequency signal components caused by the user's breathing vibration. For another example, there may be noise in the sensor array, and unwanted noise can be filtered out through filtering. After filtering the sampling result S ij (n), a filtered signal K ij (n) is obtained.
  • the filtering scheme is determined according to specific situations, and the filtering cut-off frequency can also be considered to be set, which all fall within the scope of this application.
  • Step S302 Calculate the energy corresponding to each of the multiple sensor array elements based on the signals sent by the multiple sensor array elements.
  • the K ij (n) signal (if not filtered, the S ij (n) signal) of a preset time length (for example, 1.5 seconds) is calculated as the weighted sum of squares as the corresponding array element Pressure energy E ij (m):
  • the weight of the weighted square summation is designed as a function of the preset time and sampling rate, that is, the weighting function w(n):
  • the above calculation is the energy of an element located at the position (i, j) of the sensor array for a preset time length (for example, 1.5 seconds), which is denoted as E ij (1), for example. After an interval of time (for example, 0.1 second), the energy of the next time length (for example, 1.5 seconds) is counted, for example, it is recorded as E ij (2).
  • E ij (1) the energy of an element located at the position (i, j) of the sensor array for a preset time length (for example, 1.5 seconds), which is denoted as E ij (1), for example.
  • E ij (2) the energy of the next time length
  • the m in E ij (m) is the number of energy calculations.
  • Step S303 judging whether there is an array element that obtains effective pressure among the plurality of sensor array elements according to the energy corresponding to each of the plurality of sensor array elements.
  • step S302 the energy obtained by each sensor array element is calculated, and the energies of multiple sensor array elements are compared to determine the array element with the largest energy. That is to say, by comparing the energy of multiple sensor array elements, it is possible to know which element has the largest energy, and the element that obtains the largest energy is determined as the element that obtains the effective pressure. Moreover, it is preferable to compare the energy levels of the local multiple sensor array elements to reduce the amount of calculation, increase the calculation speed, and reduce the cost of the calculation hardware.
  • the following method can be used to determine which element has the largest energy: when the energy of the element (x, y) meets the following two conditions:
  • E x-1,y (m), E x+1,y (m), E x,y-1 (m) and E x,y+1 (m) represent the vicinity of the array element (x,y)
  • the energy of the array element can be determined as the maximum energy point of the space (whole space or partial space)
  • the array element (x, y) is the array element that obtains the effective pressure.
  • the following method can be used to determine whether the energy of the corresponding array element with the largest energy is the maximum energy of the array element within a set time period.
  • E x,y (m-1), E x,y (m) and E x,y (m+1) indicate that the array element (x,y) is in the m-1th, mth and m+1th The calculated energy.
  • the array element (x, y) is the maximum energy point in time (whole time or partial time), and the array element (x, y) is the array element that obtains the effective pressure.
  • E x,y (m) is the maximum energy point in time and space, or time and time. At the same time, E x,y (m) is also required to meet certain threshold conditions, namely E x,y (m) >TH, TH is the preset threshold.
  • the above-mentioned judging whether there is an element that obtains effective pressure in the sensor array includes judging the maximum energy point of space (whole space or partial space), the maximum energy point of time (full time or partial time) in the sensor array, and the energy of the element must be greater than the previous Set threshold.
  • the above judgment methods can be used alone or in combination, such as combining the maximum energy point of the judgment space ((whole space or partial space) with the maximum energy point of judgment time (entire time or partial time), or combining the judgment space (whole space or partial time). Local space)
  • the maximum energy point is combined with whether it is greater than a preset threshold, etc.
  • step S304 a control instruction is generated in response to the presence of an element that obtains effective pressure.
  • This step may include determining the corresponding semantics according to the number, rhythm, frequency and/or position of the effective pressure obtained by the effective pressure element within a preset time, and according to the semantics The control instruction is generated.
  • the array element receives 3 consecutive effective pressures to indicate that the mattress is awakened.
  • the preset time for example, within 10 seconds
  • the CPU will convert the 3 consecutive effective pressures into corresponding control
  • the instruction is to wake up the mattress.
  • one array element corresponds to one semantic after obtaining effective pressure, and another element corresponds to another different semantic after obtaining effective pressure; the array element is subjected to a effective pressure Means that it means one semantics, and it receives b times of effective pressure to indicate another different semantics (among which, a and b are different); the interval of continuous effective pressure does not exceed a time interval (for example, 1 second) to indicate a semantics, and it is effective The interval of stress exceeding this time interval indicates another different semantics, and so on.
  • a time interval for example, 1 second
  • the semantics are converted into corresponding control instructions to control the response actions.
  • Fig. 4 is an exemplary diagram for explaining the solution of the present invention according to an embodiment of the present invention.
  • Figure 4 is an example diagram of controlling a smart desk lamp through a smart mattress.
  • the smart mattress includes a sensor array, a control module, and a communication module;
  • the smart desk lamp includes a desk lamp body and a communication module. Both the smart mat and the smart desk lamp communicate with the server.
  • the sensor array detects the signal, through the signal processing of the control module and the detection and control method based on the sensor array as described in this application, the user's actions can be recognized and converted into control instructions; after the control instructions are sent to the server ,
  • the server can control the command to be sent to the smart lamp.
  • the desk lamp body realizes the switch action.
  • the instruction may not be forwarded through the server, or the control instruction may be directly transmitted between the smart mat and the lamp through the communication module.
  • the detection and control method based on the sensor array of the present invention can detect the user's actions based on non-wearable technology and convert the actions into control instructions, and the user will not be subject to excessive physical constraints like wearable products.
  • the user experience is better, so that the detection can be applied to long-term occasions such as sleeping at night; and the user can issue control instructions through simple interaction with non-wearable products in critical scenarios, which can be used in middle-aged and disabled people.
  • the human care scenario is more suitable for the needs of the user; and the data volume of the control instruction is small, which can protect the privacy of the user.
  • a detection control method based on a pressure sensor array is proposed. By detecting the signals of multiple elements in the sensor array, it is determined whether there is an element that obtains effective pressure. In the case of, determine the corresponding semantics and generate control instructions. Then, according to the generated control command, the corresponding control action can be implemented.
  • Fig. 5 is a schematic diagram of a detection control device based on a sensor array according to an embodiment of the present invention.
  • the sensor array is a pressure sensor array and includes a plurality of sensor array elements.
  • the device includes the following units:
  • the signal collection unit 501 is used to collect signals of multiple sensor array elements in the sensor array.
  • a pressure sensor array includes I ⁇ J array elements, where I and J are both positive integers, and their product is greater than or equal to 2.
  • the signal of each sensor array element is collected at a certain sampling rate, and the sampling result is recorded as S ij (n), where i, j are the coordinates of the array element (1 ⁇ i ⁇ I, 1 ⁇ j ⁇ J).
  • the adoption rate can be a preset frequency, such as 50 Hz
  • the sampling result S ij (n) can be a voltage quantized value, and the unit can be millivolt (mV) or volt (V);
  • n is a count of the adoption, such as The first sampling, the second sampling, etc.
  • a filtering unit is further included for filtering the sampling result S ij (n) after the sampling signal is obtained.
  • the filter is designed to filter out the frequencies outside the frequency range of the effective pressure, so as to retain the effective pressure to the maximum extent and filter out interference factors.
  • the pressure sensor array is a mattress, and when the user is lying on it, the mattress can detect breathing, heartbeat, and body movements.
  • the sampling result S ij (n) contains signals related to breathing, heartbeat, and body movements. It is generally believed that users form user intentions and instructions by applying physical movements on the mattress. Then, you need to filter out the signals related to breathing and heartbeat.
  • the signal related to the heartbeat is very weak and can be ignored, and the signal related to breathing has a lower frequency than the signal related to body movement. Therefore, the sampling result S ij (n) can be high-pass filtered to reduce
  • the high-pass cutoff frequency is set at 0.5Hz to filter out low-frequency signal components caused by the user's breathing vibration. For another example, there may be noise in the sensor array, and unwanted noise can be filtered out through filtering. After filtering the sampling result S ij (n), a filtered signal K ij (n) is obtained.
  • the filtering scheme is determined according to specific situations, and the filtering cut-off frequency can also be considered to be set, which all fall within the scope of this application.
  • the calculation unit 502 is configured to calculate the energy corresponding to each of the multiple sensor array elements based on the signals sent by the multiple sensor array elements.
  • the K ij (n) signal (if not filtered, the S ij (n) signal) of a preset time length (for example, 1.5 seconds) is calculated as the weighted sum of squares as the corresponding array element Pressure energy E ij (m):
  • the weight of the weighted square summation is designed as a function of the preset time and sampling rate, that is, the weighting function w(n):
  • the above calculation is the energy of an element located at the position (i, j) of the sensor array for a preset time length (for example, 1.5 seconds), which is denoted as E ij (1), for example. After an interval of time (for example, 0.1 second), the energy of the next time length (for example, 1.5 seconds) is counted, for example, it is recorded as E ij (2).
  • E ij (1) the energy of an element located at the position (i, j) of the sensor array for a preset time length (for example, 1.5 seconds), which is denoted as E ij (1), for example.
  • E ij (2) the energy of the next time length
  • the m in E ij (m) is the number of energy calculations.
  • the judging unit 503 is configured to judge whether there is an array element that obtains an effective pressure among the multiple sensor array elements according to the energy corresponding to each of the multiple sensor array elements.
  • the judging unit 503 judges whether there is a corresponding array element with the largest energy among the multiple sensor array elements calculated at the same time.
  • the energy obtained by each sensor array element is calculated, and the energy amplitude of the multiple sensor array elements is compared to determine the array element with the largest energy. That is to say, by comparing the energy of multiple local sensor array elements or the energy of all sensor array elements, it is possible to know which array element has the largest energy, and the element that obtains the largest energy is determined as the element that obtains the effective pressure.
  • the following method can be used to determine which element has the largest energy: when the energy of the element (x, y) meets the following two conditions:
  • E x-1,y (m), E x+1,y (m), E x,y-1 (m) and E x,y+1 (m) represent the vicinity of the array element (x,y)
  • the energy of the array element can be determined as the maximum energy point of the space (whole space or partial space)
  • the array element (x, y) is the array element that obtains the effective pressure.
  • the judging unit 503 judges whether the energy of the corresponding array element with the largest energy is the maximum energy of the array element within a set time period.
  • the following method can be used to determine whether the energy of the corresponding array element with the largest energy is the maximum energy of the array element within a set time period.
  • E x,y (m-1), E x,y (m) and E x,y (m+1) indicate that the array element (x,y) is in the m-1th, mth and m+1th The calculated energy.
  • the array element (x, y) is the maximum energy point in time (whole time or partial time), and the array element (x, y) is the array element that obtains the effective pressure.
  • the judging unit 503 also needs to judge whether the peak value of the array element with the largest energy among the plurality of sensor array elements at the same time is greater than the preset energy threshold.
  • E x,y (m) is the maximum energy point in time and space, or time and time. At the same time, E x,y (m) is also required to meet certain threshold conditions, namely E x,y (m) >TH, TH is the preset threshold.
  • the above-mentioned judging whether there is an element that obtains effective pressure in the sensor array includes judging the maximum energy point of space (whole space or partial space), the maximum energy point of time (full time or partial time) in the sensor array, and the energy of the element must be greater than the previous Set threshold.
  • the above judgment methods can be used alone or in combination.
  • the maximum energy point of judgment space (whole space or partial space) is combined with the maximum energy point of judgment time (whole time or partial time), or the judgment space (whole space or partial space) can be combined.
  • the combination of the maximum energy point of space and whether it is greater than a preset threshold, etc., are all covered by this application.
  • the instruction generating unit 504 is configured to generate a control instruction in response to the presence of an element that obtains an effective pressure.
  • This step may include determining the corresponding semantics according to the number, rhythm, frequency of the effective pressure obtained by the effective pressure element within a preset time, and/or the position of the effective pressure element, and according to the semantic The control instruction is generated.
  • the array element receives 3 consecutive effective pressures to indicate that the mattress is awakened.
  • the preset time for example, within 10 seconds
  • the CPU will convert the 3 consecutive effective pressures into corresponding control
  • the instruction is to wake up the mattress.
  • one array element corresponds to one semantic after obtaining effective pressure, and another element corresponds to another different semantic after obtaining effective pressure; the array element is subjected to a effective pressure It means that it means one semantics, and it means that it receives b times of effective pressure to mean another different semantics (among which, a and b are different); the interval when the array element receives continuous effective pressure does not exceed a time interval (for example, 1 second) means that a semantic The interval of stress exceeding this time interval indicates another different semantics, and so on.
  • a time interval for example, 1 second
  • the semantics are converted into corresponding control instructions to control the response actions.
  • the detection and control device based on the sensor array of the present invention can convert the non-wearable technology to detect the user's action into a control instruction, the data volume of the control instruction is small and the privacy of the user can be protected.
  • FIG. 6 provides an electronic device including a memory, a processor, and a computer program stored in the memory and capable of running on the processor.
  • the processor executes the computer program, the computer program shown in FIG. 3 is implemented Method and refinement plan.
  • the above device embodiments are only illustrative, and the device of the present disclosure may also be implemented in other ways.
  • the division of units/modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation.
  • multiple units, modules or components may be combined or integrated into another system, or some features may be omitted or not implemented.
  • the functional units/modules in the various embodiments of the present disclosure may be integrated into one unit/module, or each unit/module may exist alone physically, or two or more units/modules may exist.
  • the modules are integrated together.
  • the above-mentioned integrated unit/module can be realized in the form of hardware or software program module.
  • the hardware may be a digital circuit, an analog circuit, and so on.
  • the physical realization of the hardware structure includes but is not limited to transistors, memristors and so on.
  • the processor or chip may be any appropriate hardware processor, such as CPU, GPU, FPGA, DSP, ASIC, and so on.
  • the on-chip cache, off-chip memory, and storage may be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM) ( Dynamic Random Access Memory), Static Random-Access Memory (Static Random-Access Memory), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory HBM (High-Bandwidth Memory), Hybrid Storage Cube HMC (Hybrid Memory Cube) and so on.
  • RRAM resistive random access memory
  • DRAM dynamic random access memory
  • Static Random-Access Memory Static Random-Access Memory
  • EDRAM Enhanced Dynamic Random Access Memory
  • HBM High-Bandwidth Memory
  • Hybrid Storage Cube HMC Hybrid Storage Cube HMC (Hybrid Memory Cube) and so on.
  • the integrated unit/module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer readable memory.
  • the technical solution of the present disclosure essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory.
  • a number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present disclosure.
  • the aforementioned memory includes: U disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
  • An embodiment of the present application also provides a computer-readable storage medium that stores a computer program for electronic data exchange, where the computer program causes a computer to execute the method and detailed solution shown in FIG. 3.
  • the embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute the method shown in FIG. 3 and Refine the plan.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Physiology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Surgery (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Cardiology (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Pulmonology (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种基于传感器阵列（10）的检测控制方法和装置，传感器阵列（10）包括多个传感器阵元（111，112），方法包括：采集传感器阵列（10）中的多个传感器阵元（111，112）的信号（S301）；基于多个传感器阵元（111，112）发送的信号计算多个传感器阵元（111，112）中每一个对应的能量（S302）；根据多个传感器阵元（111，112）中每一个对应的能量判断多个传感器阵元（111，112）中是否存在获得有效压力的阵元（S303）；以及响应于存在获得有效压力的阵元产生控制指令（S304）。通过基于传感器阵列（10）的检测控制方法和装置，能够将基于非可穿戴技术检测用户的动作转换为控制指令，控制指令的数据量小且能够保护用户隐私。

Description

基于传感器阵列的检测控制方法和装置 技术领域
本发明属于信息技术领域，特别是涉及一种基于传感器阵列的检测控制方法和装置。
背景技术
现有技术中，针对用户的一些表达需求的动作，例如用户想要唤醒某种智能电子设备，或老人摔倒后求救/示警等动作，所采用解决方案多是使用诸如智能手表、手环等可穿戴设备，又或是摄像头、智能音箱等音视频设备来进行检测。可穿戴设备(例如手环)通过感知用户的动作的变化(例如加速度)进行响应。但是，可穿戴设备需要用户实时佩戴，影响舒适感；而摄像头、智能音箱等产生的数据量大且可能泄露用户隐私。
现有技术中存在通过非穿戴设备检测用户动作的方案，对于检测到用户动作后如何应用，例如如何将用户动作转换为控制相关装置的指令等，目前还没有相关的技术发方案。例如，现有技术已提出了使用非穿戴式的传感器阵列检测体动、呼吸及心跳信号的方案。然而，现有技术更多地偏重于对体动、呼吸、心跳等信号的检测，而对于检测到这些信号的后续应用则基本没有涉及。
因此，需要如何将基于非可穿戴技术检测用户的动作转换为控制指令的技术方案，并且希望这种技术方案产生数据量小且不会影响到用户的隐私。
发明内容
因此，我们提出一种基于传感器阵列的检测控制方法和装置，通过检测传 感器阵列中的多个阵元的信号，判断是否存在获得有效压力的阵元，在存在获得有效压力的阵元的情况下，确定对应的语义并产生控制指令。然后，根据所产生的控制指令就能实施响应的控制动作。
根据本发明的第一个方面，提供一种基于传感器阵列的检测控制方法，所述传感器阵列包括多个传感器阵元，所述方法包括：
采集所述传感器阵列中的所述多个传感器阵元的信号；
基于所述多个传感器阵元发送的信号计算所述多个传感器阵元中每一个对应的能量；
根据所述多个传感器阵元中每一个对应的能量判断所述多个传感器阵元中是否存在获得有效压力的阵元；以及
响应于存在获得有效压力的阵元产生控制指令。
根据本发明的第二个方面，提供一种基于传感器阵列的检测控制装置，所述传感器阵列包括多个传感器阵元，所述装置包括：
信号采集单元，用于采集所述传感器阵列中的所述多个传感器阵元的信号；
计算单元，用于基于所述多个传感器阵元发送的信号计算所述多个传感器阵元中每一个对应的能量；
判断单元，用于根据所述多个传感器阵元中每一个对应的能量判断所述多个传感器阵元中是否存在获得有效压力的阵元；以及
指令产生单元，用于响应于存在获得有效压力的阵元产生控制指令。
第三方面，提供一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现第一方面的方法。
第四方面，提供一种计算机可读存储介质，其存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行第一方面提供的方法。
第五方面，提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使计算机执行第一方面提供的方法。
通过本发明的基于传感器阵列的检测控制方法和装置，能够将基于非可穿戴技术检测用户的动作转换为控制指令，控制指令的数据量小且能够保护用户隐私。
附图说明
为进一步清楚解释本发明的特征及技术内容，请参阅以下有关本发明的详细说明与附图，然而所提供的附图仅用于提供参考与说明，并非用来对本发明加以限制。
在下面的附图中：
图1是根据一个实施例的信号采集传感器阵列的示意图。
图2是根据一个实施例的图1所示信号采集传感器阵列的截面图。
图3是根据本发明实施例的基于传感器阵列的检测控制方法的流程图。
图4是根据本发明实施例的用于说明本发明方案的一个示例图。
图5是根据本发明实施例的基于传感器阵列的检测控制装置的示意图。
图6是本申请实施例提供的一种电子设备的结构图。
具体实施方式
以下通过特定的具体实施例来说明本发明所公开的实施方式，本领域技术 人员可由本说明书所公开的内容了解本发明的优点与效果。本发明可通过其他不同的具体实施例加以施行或应用，本说明书中的各项细节也可基于不同观点与应用，在不悖离本发明的构思下进行各种修改与变更。另外，本发明的附图仅为简单示意说明，并非依实际尺寸的描绘。以下的实施方式将进一步详细说明本发明的相关技术内容，但所公开的内容并非用以限制本发明的保护范围。
图1是根据一个实施例的信号采集传感器阵列的示意图。图2是根据一个实施例的图1所示信号采集传感器阵列的截面图。根据图1和图2所示，一种信号采集传感器阵列10，其包括：连接层105，至少两种传感器单元111和112，信号采集电路107，用于将各所述传感器单元111或112与所述信号采集电路107进行电连接的信号线104，每种所述传感器单元111或112进一步包括：第一阻震基材101或102；传感器元件103，其与所述第一阻震基材101或102一一对应且设置于所述第一阻震基材101或102与所述连接层105之间；其中，所述至少两种传感器单元在所述连接层上间隔排列成阵列状。这里的阻震基材是指具有对震动有阻挡效果(衰减效果)的材料，例如海绵、橡胶、泡沫等材料。阻震基材可以制成片状或具有凹陷形状的块状。若制成凹陷形状的块状，可以以凹陷形状容纳传感器元件，通过调整凹陷的大小，可以进一步调节阻震效果。图1和图2所图示的信号线是依次串联于各传感器单元之间，但本领域的技术人员应该知道，也可以分别以信号线连接于每个传感器单元111或112与信号采集电路107之间。通过以阵列形式间隔设置至少两种传感器单元，且将传感器单元中的传感器元件设置为与所述第一阻震基材一一对应且设置于第一阻震基材与连接层之间，使得不同的信号传递到各传感器单元后得到不同程度的衰减，并且由于第一阻震基材是分离的，解除了各个传感器单元之间力的强耦合，从而使得信号幅度差异很大的不同生理信号均被传感器阵列准确地检测 到。
图1中以8×8的阵列进行了图示，本领域的技术人员需要明白，此处仅为示例，也可以用其他数值的行、列进行组合。
可选地，各传感器元件103与连接层105之间还设置有基板层106，用于承载传感器元件和相关调理电路，以使其整体具备较高的刚度，避免受到损坏。
可选地，多个所述传感器单元111或112共用一个信号采集电路107。这样可以以较少的采集电路实现较大面积的采集工作，这样不仅有助于节省成本，还可以通过使用串行总线等技术，降低信号采集的时间间隔，提升信号采集的速率。类似地，至少一个信号采集电路107又进一步连接到整个阵列的中央处理器。
可选地，一种传感器单元111中包括的第一阻震基材的阻震特性、所包括的传感器元件的灵敏度以及所对应的信号采集电路的灵敏度的乘积是另一种传感器单元112中包括的第一阻震基材的阻震特性、所包括的传感器元件的灵敏度以及所对应的信号采集电路的灵敏度的乘积的2倍以上。这里，阻震特性是指对震动的衰减倍数。例如一种材料的阻震特性是40％，意味着其可以将震动衰减40％，而只有60％的震动可以从其一侧传递到另一端。传感器的灵敏度与采集电路的灵敏度的含义在现有技术中已有充分定义，为简洁起见不再赘述。
所述传感器元件，可以是压电片，也可以是应变片、压阻传感器等的一种或其中多种的组合。并且传感器元件中设置有运算放大电路，可以对初始信号进行放大。所述传感器元件的灵敏度不同，可以通过设置不同的元件类型或不同的运算放大电路的放大倍数来实现。
图1和图2传感器阵列包括了多个传感器阵元，用于采集信号。需要注意 的是，图1和图2只是展示了采集信号的传感器阵列结构和组成的一种具体方式。本领域技术人员可以理解的是，可以采用其他任何形式的采集信号的传感器阵列，这些都属于本申请覆盖的范围。
根据本发明的一个方面，提出一种基于压力传感器阵列的检测控制方法，通过检测传感器阵列中的多个阵元的信号，判断是否存在获得有效压力的阵元，在存在获得有效压力的阵元的情况下，确定对应的语义并产生控制指令。然后，根据所产生的控制指令就能实施响应的控制动作。
图3是根据本发明实施例的基于传感器阵列的检测控制方法的流程图。在一个实施例中，所述传感器阵列为压力传感器阵列，包括多个传感器阵元。如图3所示，所述方法包括如下步骤：
步骤S301，采集传感器阵列中的多个传感器阵元的信号。
一个压力传感器阵列包括I×J个阵元，其中，I和J均为正整数，其乘积大于等于2。以一定的采样率采集每个传感器阵元的信号，采样结果记为S ij(n)，其中i,j为阵元坐标(1≤i≤I,1≤j≤J)。其中，采用率可以是预先设定的频率，例如50Hz,采样结果S ij(n)可以为电压量化值，单位可以为毫伏(mV)或伏(V)；n是对采样的计数，比如第1次采样、第2次采样等。
在一个可选的实施例中，在获得采样信号后，对采样结果S ij(n)进行滤波。对于压力传感器阵列来说，如果能够确定检测有效压力的频率范围，那么将滤波器进行设计，滤除有效压力的频率范围外的频率，能够最大限度的保留有效压力，滤除干扰因素。例如，压力传感器阵列为一个床垫，用户躺在上面时，床垫可以检测到呼吸、心跳和肢体动作。采样结果S ij(n)包含了与呼吸、心跳和肢体动作有关的信号。通常认为，用户通过将肢体动作施加在床垫上，形成用户意图和指令。那么，需要滤除与呼吸和心跳有关的信号。与心跳有关的信 号非常微弱，可以忽略不计，而与呼吸有感的信号相对于与肢体动作有关的信号来说，频率要低，因此，可以对采样结果S ij(n)采用高通滤波，将高通截止频率设在0.5Hz，滤掉用户呼吸振动引起的低频信号成分。再如，传感器阵列中可能存在噪声，可以通过滤波滤除不需要的噪声。对采样结果S ij(n)进行滤波后得到滤波后的信号K ij(n)。
在上述实施例中，滤波方案是根据具体的情形而确定的，滤波截止频率也是可以认为设定的，这都属于本申请覆盖的范围。
步骤S302，基于所述多个传感器阵元发送的信号计算所述多个传感器阵元中每一个对应的能量。
在一个具体的实施例中，对预设时间长度(例如1.5秒)的K ij(n)信号(若未经滤波，为S ij(n)信号)求取加权平方和，作为相应阵元的压力能量E ij(m)：
Figure PCTCN2019122407-appb-000001
该加权平方求和的权重设计为预设时间和采样率的函数，即加权函数w(n)：
w(n)＝(0.5-0.5cos(2π(n/T-0.5)))/T
其中，i和j表示位于传感器阵列的(i,j)位置的一个阵元，假设这段时间为1.5秒，那么T＝1.5f s，f s为采样率，n为1到T。如果采样率f s为50Hz，那么T等于75，n为1到75。
以上计算的是预设时间长度(例如1.5秒)的位于传感器阵列的(i,j)位置的一个阵元的能量，例如记为E ij(1)。在间隔一个时间后(例如，0.1秒)，再统计下一个时间长度(例如1.5秒)的能量，例如记为E ij(2)。E ij(m)中的m是计算能量的次数。
步骤S303，根据所述多个传感器阵元中每一个对应的能量判断所述多个传感器阵元中是否存在获得有效压力的阵元。
对压力传感器阵列的一个阵元施加压力的时候，由于震动带来的波动传递了能量，其他阵元或多或少也会检测到这个压力。那么，就需要识别传感器阵列中哪个或哪些阵元受到的压力是有效的，即为用户真正需要施加压力的阵元。
根据一个实施例，判断同一时刻计算的多个传感器阵元中是否存在对应的能量最大的阵元。
在步骤S302中计算了各个传感器阵元获得能量，对多个传感器阵元的能量进行幅值比较，确定能量最大的阵元。也就是说，通过比较多个传感器阵元的能量的大小，能够知道哪个阵元的能量最大，将获得最大能量的阵元确定为获得有效压力的阵元。而且，优选地进行局部的多个传感器阵元的能量的大小的比较，以减少计算量，提升计算速度，降低计算硬件的成本。
在一个具体实施例中，可以通过如下方法判断哪个阵元的获得能量最大：当阵元(x,y)的能量满足如下两个条件时：
E x，y(m)＞E x-1，y(m)且E x，y(m)＞E x+1，y(m)
E x，y(m)＞E x，y-1(m)且E x，y(m)＞E x，y+1(m)
其中，E x-1,y(m)、E x+1,y(m)、E x,y-1(m)和E x,y+1(m)表示阵元(x,y)附近阵元的能量，根据上述方法可以判定阵元(x,y)为空间(整个空间或局部空间)最大能量点，阵元(x,y)为获得有效压力的阵元。
需要说明的是，在上述实施例的启发下，本领域技术人员能够想到的其他判断多个传感器阵元中存在对应的能量最大的阵元的方法，都属于本申请覆盖 的范围。
在进一步的实施例中，判断所述对应的能量最大的阵元的能量是否为设定时间段内所述阵元的最大能量。
在一个具体实施例中，可以通过如下方法判断所述对应的能量最大的阵元的能量是否为设定时间段内所述阵元的最大能量。
E x，y(m)＞E x，y(m-1)且E x，y(m)＞E x，y(m+1)
其中，E x,y(m-1)、E x,y(m)和E x,y(m+1)表示阵元(x,y)在第m-1、第m和第m+1次计算的能量。
根据上述进一步的方法可以判定阵元(x,y)为时间(整个时间或局部时间)最大能量点，阵元(x,y)为获得有效压力的阵元。
需要说明的是，在上述实施例的启发下，本领域技术人员能够想到的其他判断所述对应的能量最大的阵元的能量是否为设定时间段内所述阵元的最大能量的方法，都属于本申请覆盖的范围。
在进一步的实施例中，还需要判断判断同一时刻多个传感器阵元中能量最大的阵元在设定时间段内的峰值是否大于预设的能量阈值。
也就是说，E x,y(m)时空间上，或者时间上和时间上最大能量点，同时，还要求E x,y(m)满足一定的阈值条件，即E x,y(m)>TH，TH为预先设定的阈值。
上述判断传感器阵列中是否存在获得有效压力的阵元，包括判断传感器阵列中空间(整个空间或局部空间)最大能量点、时间(整个时间或局部时间)最大能量点以及阵元的能量必须大于预先设定的阈值。上述判断方法可以单独使用，也可以组合使用，例如将判断空间((整个空间或局部空间)最大能量点与判断时间(整个时间或局部时间)最大能量点组合，或者将判断空间(整个空间或局部空间)最大能量点与是否大于预先设定的阈值进行组合等，这些 都属于本申请覆盖的范围。
步骤S304，响应于存在获得有效压力的阵元产生控制指令。
这一步骤可以包括根据预设时间内所述获得有效压力的阵元获得有效压力的次数、节奏、频率以及/或者所述获得有效压力的阵元的位置确定所对应的语义，根据所述语义产生所述控制指令。
在一个具体实施例中，假设该传感器阵列为床垫，一个预先定义的语义，阵元受到了连续3次的有效压力表示唤醒床垫。在预设时间内(例如10秒内)，检测到一个阵元受到了连续3次的有效压力，那么根据预先设定的语义，通过CPU将受到的连续3次的有效压力转换为相应的控制指令，即唤醒床垫。
还可以规定其他有效压力与语义之间的对应关系，例如，一个阵元获得有效压力后对应一个语义，而另一个阵元获得有效压力后对应另一个不同的语义；阵元受到a次有效压力表示表示一个语义，受到b次有效压力表示另一个不同的语义(其中，a与b不同)；阵元受到连续有效压力的间隔不超过一个时间间隔(例如1秒)表示一个语义，而受到有效压力的间隔超过这个时间间隔表示另一个不同的语义，等等。
需要说明的是，在上述实施例的启发下，本领域技术人员能够想到的其他阵元受到有效压力与语义之间的对应关系都属于本申请覆盖的范围。
这样，在知道获得有效压力的阵元后，根据预设的语义，将语义转换为相应的控制指令，控制响应的动作。
图4是根据本发明实施例的用于说明本发明方案的一个示例图。图4为通过智能床垫控制智能台灯的示例图。在图4中，智能床垫包括传感器阵列、控制模块、通讯模块；智能台灯包括台灯本体和通讯模块。智能垫子和智能台灯均与服务器通讯。传感器阵列检测到信号后，通过控制模块的信号处理，以及 如本申请如上所述的基于传感器阵列的检测控制方法，可以识别用户的动作并转换为控制指令；将所述控制指令发送给服务器后，服务器可以控制指令发送给智能台灯。智能台灯在通过通讯模块收到相关指令后，台灯本体实现开关动作。此处，如果事先约定好通信协议并规定好指令的格式，也可以不通过服务器转发指令，也可以直接通过通讯模块在智能垫子与台灯之间传送控制指令。
从而，通过本发明的基于传感器阵列的检测控制方法，能够基于非可穿戴技术检测用户的动作并将所述动作转换为控制指令，用户不会受到像可穿戴产品那样过多的对于肢体的约束，用户体验更好，从而使得检测可以应用于诸如晚上睡觉等长时间的场合下；并且用户可以在危急的场景下通过与非可穿戴产品的简单互动而发出控制指令，在中老年人、残疾人的护理场景下更加贴合用户的需求；并且，控制指令的数据量小，能够保护用户隐私。
根据本发明的一个方面，提出一种基于压力传感器阵列的检测控制方法，通过检测传感器阵列中的多个阵元的信号，判断是否存在获得有效压力的阵元，在存在获得有效压力的阵元的情况下，确定对应的语义并产生控制指令。然后，根据所产生的控制指令就能实施响应的控制动作。
图5是根据本发明实施例的基于传感器阵列的检测控制装置的示意图。在一个实施例中，所述传感器阵列为压力传感器阵列，包括多个传感器阵元。如图5所示，所述装置包括如下单元：
信号采集单元501，用于采集传感器阵列中的多个传感器阵元的信号。
一个压力传感器阵列包括I×J个阵元，其中，I和J均为正整数，其乘积大于等于2。以一定的采样率采集每个传感器阵元的信号，采样结果记为S ij(n)，其中i,j为阵元坐标(1≤i≤I,1≤j≤J)。其中，采用率可以是预先设定的频率，例如50Hz,采样结果S ij(n)可以为电压量化值，单位可以为 毫伏(mV)或伏(V)；n是对采用的计数，比如第1次采样、第2次采样等。
在一个可选的实施例中，还包括滤波单元，用于在获得采样信号后，对采样结果S ij(n)进行滤波。对于压力传感器阵列来说，如果能够确定检测有效压力的频率范围，那么将滤波器进行设计，滤除有效压力的频率范围外的频率，能够最大限度的保留有效压力，滤除干扰因素。例如，压力传感器阵列为一个床垫，用户躺在上面时，床垫可以检测到呼吸、心跳和肢体动作。采样结果S ij(n)包含了与呼吸、心跳和肢体动作有关的信号。通常认为，用户通过将肢体动作施加在床垫上，形成用户意图和指令。那么，需要滤除与呼吸和心跳有关的信号。与心跳有关的信号非常微弱，可以忽略不计，而与呼吸有感的信号相对于与肢体动作有关的信号来说，频率要低，因此，可以对采样结果S ij(n)采用高通滤波，将高通截止频率设在0.5Hz，滤掉用户呼吸振动引起的低频信号成分。再如，传感器阵列中可能存在噪声，可以通过滤波滤除不需要的噪声。对采样结果S ij(n)进行滤波后得到滤波后的信号K ij(n)。
在上述实施例中，滤波方案是根据具体的情形而确定的，滤波截止频率也是可以认为设定的，这都属于本申请覆盖的范围。
计算单元502，用于基于所述多个传感器阵元发送的信号计算所述多个传感器阵元中每一个对应的能量。
在一个具体的实施例中，对预设时间长度(例如1.5秒)的K ij(n)信号(若未经滤波，为S ij(n)信号)求取加权平方和，作为相应阵元的压力能量E ij(m)：
Figure PCTCN2019122407-appb-000002
该加权平方求和的权重设计为预设时间和采样率的函数，即加权函数w(n)：
w(n)＝(0.5-0.5cos(2π(n/T-0.5)))/T
其中，i和j表示位于传感器阵列的(i,j)位置的一个阵元，假设这段时间为1.5秒，那么T＝1.5f s，f s为采样率，n为1到T。如果采样率f s为50Hz，那么T等于75，n为1到75。
以上计算的是预设时间长度(例如1.5秒)的位于传感器阵列的(i,j)位置的一个阵元的能量，例如记为E ij(1)。在间隔一个时间后(例如，0.1秒)，再统计下一个时间长度(例如1.5秒)的能量，例如记为E ij(2)。E ij(m)中的m是计算能量的次数。
判断单元503，用于根据所述多个传感器阵元中每一个对应的能量判断所述多个传感器阵元中是否存在获得有效压力的阵元。
对压力传感器阵列的一个阵元施加压力的时，其他阵元或多或少也会检测到这个压力。那么，就需要明确传感器阵列中哪个或哪些阵元受到的压力是有效的，即为用户真正需要施加压力的阵元。
根据一个实施例，判断单元503判断同一时刻计算的多个传感器阵元中是否存在对应的能量最大的阵元。
在计算单元502中计算了各个传感器阵元获得能量，对多个传感器阵元的能量进行幅值比较，确定能量最大的阵元。也就是说，通过比较局部多个传感器阵元的能量或者全部传感器阵元的能量的大小，能够知道哪个阵元的能量最大，将获得最大能量的阵元确定为获得有效压力的阵元。
在一个具体实施例中，可以通过如下方法判断哪个阵元的获得能量最大：当阵元(x,y)的能量满足如下两个条件时：
E x，y(m)＞E x-1，y(m)且E x，y(m)＞E x+1，y(m)
E x，y(m)＞E x，y-1(m)且E x，y(m)＞E x，y+1(m)
其中，E x-1,y(m)、E x+1,y(m)、E x,y-1(m)和E x,y+1(m)表示阵元(x,y)附近阵元的能量，根据上述方法可以判定阵元(x,y)为空间(整个空间或局部空间)最大能量点，阵元(x,y)为获得有效压力的阵元。
需要说明的是，在上述实施例的启发下，本领域技术人员能够想到的其他判断多个传感器阵元中存在对应的能量最大的阵元的方法，都属于本申请覆盖的范围。
在进一步的实施例中，判断单元503判断所述对应的能量最大的阵元的能量是否为设定时间段内所述阵元的最大能量。
在一个具体实施例中，可以通过如下方法判断所述对应的能量最大的阵元的能量是否为设定时间段内所述阵元的最大能量。
E x，y(m)＞E x，y(m-1)且E x，y(m)＞E x，y(m+1)
其中，E x,y(m-1)、E x,y(m)和E x,y(m+1)表示阵元(x,y)在第m-1、第m和第m+1次计算的能量。
根据上述进一步的方法可以判定阵元(x,y)为时间(整个时间或局部时间)最大能量点，阵元(x,y)为获得有效压力的阵元。
需要说明的是，在上述实施例的启发下，本领域技术人员能够想到的其他判断所述对应的能量最大的阵元的能量是否为设定时间段内所述阵元的最大能量的方法，都属于本申请覆盖的范围。
在进一步的实施例中，判断单元503还需要判断同一时刻多个传感器阵元中能量最大的阵元在设定时间段内的峰值是否大于预设的能量阈值。
也就是说，E x,y(m)时空间上，或者时间上和时间上最大能量点，同时，还 要求E x,y(m)满足一定的阈值条件，即E x,y(m)>TH，TH为预先设定的阈值。
上述判断传感器阵列中是否存在获得有效压力的阵元，包括判断传感器阵列中空间(整个空间或局部空间)最大能量点、时间(整个时间或局部时间)最大能量点以及阵元的能量必须大于预先设定的阈值。上述判断方法可以单独使用，也可以组合使用，例如将判断空间(整个空间或局部空间)最大能量点与判断时间(整个时间或局部时间)最大能量点组合，或者将判断空间(整个空间或局部空间)最大能量点与是否大于预先设定的阈值进行组合等，这些都属于本申请覆盖的范围。
指令产生单元504，用于响应于存在获得有效压力的阵元产生控制指令。
这一步骤可以包括根据预设时间内所述获得有效压力的阵元获得有效压力的次数、节奏、频率以及/或者所述获得有效压力的阵元的位置确定所对应的语义，根据所述语义产生所述控制指令。
在一个具体实施例中，假设该传感器阵列为床垫，一个预先定义的语义，阵元受到了连续3次的有效压力表示唤醒床垫。在预设时间内(例如10秒内)，检测到一个阵元受到了连续3次的有效压力，那么根据预先设定的语义，通过CPU将受到的连续3次的有效压力转换为相应的控制指令，即唤醒床垫。
还可以规定其他有效压力与语义之间的对应关系，例如，一个阵元获得有效压力后对应一个语义，而另一个阵元获得有效压力后对应另一个不同的语义；阵元受到a次有效压力表示表示一个语义，受到b次有效压力表示另一个不同的语义(其中，a与b不同)；阵元受到连续有效压力的间隔不超过一个时间间隔(例如1秒)表示一个语义，而受到有效压力的间隔超过这个时间间隔表示另一个不同的语义，等等。
需要说明的是，在上述实施例的启发下，本领域技术人员能够想到的其他 阵元受到有效压力与语义之间的对应关系都属于本申请覆盖的范围。
这样，在知道获得有效压力的阵元后，根据预设的语义，将语义转换为相应的控制指令，控制响应的动作。
从而，通过本发明的基于传感器阵列的检测控制装置，能够将基于非可穿戴技术检测用户的动作转换为控制指令，控制指令的数据量小且能够保护用户隐私。
参阅图6，图6提供一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如图3所示的方法以及细化方案。
应该理解，上述的装置实施例仅是示意性的，本披露的装置还可通过其它的方式实现。例如，上述实施例中所述单元/模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。例如，多个单元、模块或组件可以结合，或者可以集成到另一个系统，或一些特征可以忽略或不执行。
另外，若无特别说明，在本披露各个实施例中的各功能单元/模块可以集成在一个单元/模块中，也可以是各个单元/模块单独物理存在，也可以两个或两个以上单元/模块集成在一起。上述集成的单元/模块既可以采用硬件的形式实现，也可以采用软件程序模块的形式实现。
所述集成的单元/模块如果以硬件的形式实现时，该硬件可以是数字电路，模拟电路等等。硬件结构的物理实现包括但不局限于晶体管，忆阻器等等。若无特别说明，所述处理器或芯片可以是任何适当的硬件处理器，比如CPU、GPU、FPGA、DSP和ASIC等等。若无特别说明，所述片上缓存、片外内存、存储器可以是任何适当的磁存储介质或者磁光存储介质，比如，阻变式存储器RRAM(Resistive Random Access Memory)、动态随机存取存储器DRAM(Dynamic  Random Access Memory)、静态随机存取存储器SRAM(Static Random-Access Memory)、增强动态随机存取存储器EDRAM(Enhanced Dynamic Random Access Memory)、高带宽内存HBM(High-Bandwidth Memory)、混合存储立方HMC(Hybrid Memory Cube)等等。
所述集成的单元/模块如果以软件程序模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本披露的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本披露各个实施例所述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本申请实施例还提供一种计算机可读存储介质，其存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行如图3所示的方法以及细化方案。
本申请实施例还提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使计算机执行如图3所示的方法以及细化方案。
以上所述仅为本发明的较佳实施例，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。

Claims (11)

  1. 一种基于传感器阵列的检测控制方法，所述传感器阵列包括多个传感器阵元，所述方法包括：
    采集所述传感器阵列中的所述多个传感器阵元的信号；
    基于所述多个传感器阵元发送的信号计算所述多个传感器阵元中每一个对应的能量；
    根据所述多个传感器阵元中每一个对应的能量判断所述多个传感器阵元中是否存在获得有效压力的阵元；以及
    响应于存在获得有效压力的阵元产生控制指令。
  2. 如权利要求1所述的方法，还包括：
    对所采集的所述多个传感器阵元的信号进行高通滤波。
  3. 如权利要求1所述的方法，其中，所述根据所述多个传感器阵元中每一个对应的能量判断所述多个传感器阵元中是否存在获得有效压力的阵元包括：
    判断同一时刻多个传感器阵元中能量最大的阵元在设定时间段内的峰值是否大于预设的能量阈值。
  4. 如权利要求3所述的方法，其中，所述判断同一时刻多个传感器阵元中能量最大的阵元包括：对多个传感器阵元的能量进行幅值比较，确定能量最 大的阵元。
  5. 如权利要求1所述的方法，其中，所述基于所述多个传感器阵元发送的信号计算所述多个传感器阵元中每一个对应的能量包括：
    对预设时间内的所述多个传感器阵元的信号进行加权平方求和，获得所述多个传感器阵元中每一个阵元对应的能量。
  6. 如权利要求1所述的方法，其中，所述加权平方求和的权重为预设时间和采样率的函数。
  7. 如权利要求1所述的方法，其中，所述响应于存在获得有效压力的阵元产生控制指令包括：
    根据预设时间内所述获得有效压力的阵元获得有效压力的次数、节奏、频率以及/或者所述获得有效压力的阵元的位置，确定所对应的语义，根据所述语义产生所述控制指令。
  8. 一种基于传感器阵列的检测控制装置，所述传感器阵列包括多个传感器阵元，所述装置包括：
    信号采集单元，用于采集所述传感器阵列中的所述多个传感器阵元的信号；
    计算单元，用于基于所述多个传感器阵元发送的信号计算所述多个传感器阵元中每一个对应的能量；
    判断单元，用于根据所述多个传感器阵元中每一个对应的能量判断所述多个传感器阵元中是否存在获得有效压力的阵元；以及
    指令产生单元，用于响应于存在获得有效压力的阵元产生控制指令。
  9. 一种电子设备，其特征在于，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如权利要求1-7任一所述的方法。
  10. 一种计算机可读存储介质，其特征在于，其存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行如权利要求1-7任一项所述的方法。
  11. 一种计算机程序产品，其特征在于，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使计算机执行如权利要求1-7任一项所述的方法。
PCT/CN2019/122407 2019-12-02 2019-12-02 基于传感器阵列的检测控制方法和装置 WO2021108954A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980003424.4A CN111093485B (zh) 2019-12-02 2019-12-02 基于传感器阵列的检测控制方法和装置
PCT/CN2019/122407 WO2021108954A1 (zh) 2019-12-02 2019-12-02 基于传感器阵列的检测控制方法和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/122407 WO2021108954A1 (zh) 2019-12-02 2019-12-02 基于传感器阵列的检测控制方法和装置

Publications (1)

Publication Number Publication Date
WO2021108954A1 true WO2021108954A1 (zh) 2021-06-10

Family

ID=70400266

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/122407 WO2021108954A1 (zh) 2019-12-02 2019-12-02 基于传感器阵列的检测控制方法和装置

Country Status (2)

Country Link
CN (1) CN111093485B (zh)
WO (1) WO2021108954A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113804332A (zh) * 2021-09-16 2021-12-17 浙江衡玖医疗器械有限责任公司 基于超声成像系统的温感元件阵列故障诊断方法及其应用

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7006918B2 (en) * 2002-02-08 2006-02-28 University Of Houston Method for stress and stability related measurements in boreholes
CN204133474U (zh) * 2014-08-01 2015-02-04 天道（天津）科技有限公司 婴儿睡眠监控装置
CN105652652A (zh) * 2014-11-14 2016-06-08 深圳君正时代集成电路有限公司 一种智能手表的控制方法、装置及智能手表
CN107087936A (zh) * 2016-02-18 2017-08-25 尧乐网络科技（上海）有限公司 智能床垫及控制方法
CN108814616A (zh) * 2018-04-12 2018-11-16 深圳和而泰数据资源与云技术有限公司 一种坐姿识别的方法及智能座椅
CN109820373A (zh) * 2019-03-28 2019-05-31 重庆邮电大学 基于智能座椅的坐姿自适应调整方法
CN110279250A (zh) * 2019-07-16 2019-09-27 温州医科大学 一种力学智能床垫

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB9001718D0 (en) * 1990-01-25 1990-10-03 British Aerospace Control mechanism
KR20120070846A (ko) * 2010-12-22 2012-07-02 한국전자통신연구원 보행 패턴 분석 장치 및 방법
CN203619132U (zh) * 2013-12-09 2014-06-04 吴建春 阵列床
CN107368796A (zh) * 2017-07-06 2017-11-21 中国科学院合肥物质科学研究院 一种步态获取与交互装置及其交互方法
CN108083075B (zh) * 2018-01-19 2024-05-03 南京信息职业技术学院 一种手扶电梯急停装置
CN108524132A (zh) * 2018-04-28 2018-09-14 深圳先进技术研究院 一种护理水床
CN110087512B (zh) * 2019-03-11 2021-04-30 北京微动数联科技有限公司 信号采集传感器阵列、电子设备及床垫

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7006918B2 (en) * 2002-02-08 2006-02-28 University Of Houston Method for stress and stability related measurements in boreholes
CN204133474U (zh) * 2014-08-01 2015-02-04 天道（天津）科技有限公司 婴儿睡眠监控装置
CN105652652A (zh) * 2014-11-14 2016-06-08 深圳君正时代集成电路有限公司 一种智能手表的控制方法、装置及智能手表
CN107087936A (zh) * 2016-02-18 2017-08-25 尧乐网络科技（上海）有限公司 智能床垫及控制方法
CN108814616A (zh) * 2018-04-12 2018-11-16 深圳和而泰数据资源与云技术有限公司 一种坐姿识别的方法及智能座椅
CN109820373A (zh) * 2019-03-28 2019-05-31 重庆邮电大学 基于智能座椅的坐姿自适应调整方法
CN110279250A (zh) * 2019-07-16 2019-09-27 温州医科大学 一种力学智能床垫

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113804332A (zh) * 2021-09-16 2021-12-17 浙江衡玖医疗器械有限责任公司 基于超声成像系统的温感元件阵列故障诊断方法及其应用
CN113804332B (zh) * 2021-09-16 2024-06-04 浙江衡玖医疗器械有限责任公司 基于超声成像系统的温感元件阵列故障诊断方法及其应用

Also Published As

Publication number Publication date
CN111093485A (zh) 2020-05-01
CN111093485B (zh) 2023-07-14

Similar Documents

Publication Publication Date Title
Huynh et al. Optimization of an accelerometer and gyroscope‐based fall detection algorithm
Khan et al. An unsupervised acoustic fall detection system using source separation for sound interference suppression
Bai et al. Design and implementation of a fall monitor system by using a 3-axis accelerometer in a smart phone
JP6369919B2 (ja) 人の健康状態検出装置
US11304001B2 (en) Speaker emulation of a microphone for wind detection
Popescu et al. Acoustic fall detection using one-class classifiers
Rescio et al. Supervised Expert System for Wearable MEMS Accelerometer‐Based Fall Detector
EP2959827A1 (en) Sleep state estimation device, method and storage medium
CN104586405B (zh) 智能胎动监测装置、监测系统及监测方法
WO2019137110A1 (zh) 可穿戴设备的状态监测方法、装置及可穿戴设备
JP2010273831A (ja) 体動検出装置、睡眠状態測定装置、体動量検出方法及び体動量検出プログラム
WO2021108954A1 (zh) 基于传感器阵列的检测控制方法和装置
US20170172491A1 (en) System and method for detecting muscle activities
CN107929913A (zh) Vr心理放松体验系统
TWI582728B (zh) 疲勞警示系統
Su et al. Multi-view fall detection based on spatio-temporal interest points
KR20190058289A (ko) 적응형 저역 통과 필터를 사용하여 오디오에서 호흡 속도를 검출하는 기법
Min et al. Audio-kinetic model for automatic dietary monitoring with earable devices
Shin et al. Accurate eating detection on a daily wearable necklace
CN114176525B (zh) 睡眠质量分析方法、装置、计算机设备和存储介质
KR102605634B1 (ko) 숨소리 모니터링을 기반으로 하는 저주파 알림 시스템
Lopez et al. Walk and jog characterization using a triaxial accelerometer
TW202021528A (zh) 基於光電容積描記圖訊號取得心律不整資訊的方法及檢測心律不整的裝置
CN105962504A (zh) 智能腰带及其使用方法
CN112741594A (zh) 睡眠监测装置及方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19955090

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19955090

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205N DATED 07.10.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19955090

Country of ref document: EP

Kind code of ref document: A1