WO2020211459A1 - 使用对象确定方法、设备及存储介质 - Google Patents

使用对象确定方法、设备及存储介质 Download PDF

Info

Publication number
WO2020211459A1
WO2020211459A1 PCT/CN2019/129571 CN2019129571W WO2020211459A1 WO 2020211459 A1 WO2020211459 A1 WO 2020211459A1 CN 2019129571 W CN2019129571 W CN 2019129571W WO 2020211459 A1 WO2020211459 A1 WO 2020211459A1
Authority
WO
WIPO (PCT)
Prior art keywords
acceleration
smart device
peak
use object
frequency
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2019/129571
Other languages
English (en)
French (fr)
Inventor
臧爱伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Goertek Inc
Original Assignee
Goertek Inc
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 Goertek Inc filed Critical Goertek Inc
Publication of WO2020211459A1 publication Critical patent/WO2020211459A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/10Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning

Definitions

  • This application relates to the field of artificial intelligence technology, and in particular to a method, device and storage medium for determining a use object.
  • smart devices are widely used in people's daily lives. For example, smart phones, smart watches, smart bracelets and other wearable devices have become inseparable from people's lives.
  • these smart devices can also perform step counting and positioning. The different objects used will affect the accuracy of the smart device's step counting or positioning. Therefore, it is necessary to determine the use objects of the smart device.
  • Various aspects of the present application provide a method, a device, and a storage medium for determining a use object, which are used to identify the use object of a smart device, thereby helping to improve the accuracy of subsequent step counting or positioning of the use object.
  • the embodiment of the present application provides a method for determining a use object, including:
  • An embodiment of the present application also provides a smart device, including: an acceleration sensor, a memory, and a processor; wherein the acceleration sensor is used to collect acceleration information in multiple motion directions generated by the smart device during use;
  • the memory is used to store computer programs
  • the processor is coupled to the memory, and is configured to execute the computer program for:
  • the embodiments of the present application also provide a computer-readable storage medium storing computer instructions, which when the computer instructions are executed by one or more processors, cause the one or more processors to execute the steps in the foregoing method.
  • characteristic analysis is performed on acceleration information in multiple motion directions generated by the smart device during use, to obtain the acceleration characteristics of the use object of the smart device, and determine the smart device according to the acceleration characteristics of the use object The intended use object.
  • a method that matches the target of use can be used to count or locate the target, which helps to improve the accuracy of step counting or positioning.
  • FIG. 1 is a schematic flowchart of a method for determining a use object provided by an embodiment of the application
  • FIGS. 2a and 2b are schematic diagrams of the combined acceleration generated by a person when walking and running, respectively, according to an embodiment of the application;
  • 3a and 3b are respectively schematic diagrams of the combined acceleration generated by a small dog when walking and running according to an embodiment of the application;
  • 4a and 4b are respectively schematic diagrams of the combined acceleration generated by a medium-sized dog when walking and running according to an embodiment of the application;
  • Figures 5a and 5b are schematic diagrams of the combined acceleration generated when a large dog walks and runs, respectively, according to an embodiment of the application;
  • 6a and 6b are respectively schematic diagrams after wavelet change corresponding to the combined acceleration of a large dog when walking and running according to an embodiment of the application;
  • FIG. 7a and 7b are respectively schematic diagrams after wavelet change corresponding to the combined acceleration of a person walking and running according to an embodiment of the application;
  • FIG. 8a is a schematic diagram of the distribution of the acceleration ratio of the x-axis and the y-axis when a person is walking according to an embodiment of the application;
  • 8b is a schematic diagram of the distribution of acceleration ratios of the y-axis and the z-axis when a person is walking according to an embodiment of the application;
  • FIG. 8c is a schematic diagram of the distribution of acceleration ratios of the x-axis and the z-axis when a person is walking according to an embodiment of the application;
  • FIG. 9a is a schematic diagram of the distribution of the acceleration ratio of the x-axis and the y-axis when a large dog is running according to an embodiment of the application;
  • FIG. 9b is a schematic diagram of the distribution of acceleration ratios of the y-axis and the z-axis when a large dog is running according to an embodiment of the application;
  • FIG. 9c is a schematic diagram of the distribution of the acceleration ratio of the x-axis and the z-axis when a large dog is running according to an embodiment of the application;
  • FIG. 10 is a schematic structural diagram of a smart device provided by an embodiment of the application.
  • embodiments of the present application provide a solution.
  • the basic idea is to characterize acceleration information in multiple motion directions generated by smart devices during use. Analyze and obtain the acceleration characteristics of the use object of the smart device, and determine the use object of the smart device according to the acceleration characteristics of the use object. In this way, after the target of use of the smart device is identified, a method that matches the target of use can be used to count or locate the target, which helps to improve the accuracy of step counting or positioning.
  • FIG. 1 is a schematic flowchart of a method for determining a use object improved by an embodiment of the application. As shown in Figure 1, the method includes:
  • a smart device refers to an electronic device with step counting or positioning functions, which can be terminal devices such as smart phones, tablet computers, or smart watches, bracelets, smart glasses, Bluetooth headsets, key fobs, etc. Wearable devices, or anti-lost devices, but not limited to this.
  • the smart device is provided with an acceleration sensor, which is used to collect acceleration information in multiple motion directions generated by the smart device during use.
  • an acceleration sensor which is used to collect acceleration information in multiple motion directions generated by the smart device during use.
  • multiple refers to two or more than two, and the specific value can be determined according to the number of input shafts of the acceleration sensor.
  • the acceleration sensor is a three-axis acceleration sensor
  • the multiple movement directions may be three movement directions of front and rear, left and right, and up and down, but it is not limited to this.
  • step 102 feature analysis is performed on the collected acceleration information in multiple motion directions, and at least one acceleration feature of the use object is acquired. Then, according to at least one acceleration characteristic of the use object, pattern recognition is performed on the use object, and then the use object of the smart device is determined.
  • the determined use object of the smart device refers to the type of use object, for example, the determined use object is a human, a small pet, a medium pet, or a large pet.
  • pedometer methods can be used for different types of objects of use.
  • the object of use is a human
  • a pedometer method that conforms to the characteristics of human behavior can be used to perform step counting;
  • the object is an animal, and it can be counted by a step-counting method that conforms to the characteristics of the animal's behavior, which helps to improve the accuracy of counting or positioning the target.
  • a corresponding early warning device in order to improve the security of the smart device and protect the privacy of the user, a corresponding early warning device can also be provided.
  • a special hidden function can be set on the smart device. If it is determined that the user of the smart device is a human, when the preset alarm time arrives, a prompt message carrying the smart device can be sent to the user. Among them, the preset alarm time can be 5 minutes, 10 minutes, etc., but is not limited to this.
  • the early warning period can be preset in the smart device. If it is determined that the user of the smart device is a human, a timer or counter is triggered to time the early warning period, and when each early warning period arrives, the user will be sent with The prompt information of the smart device.
  • the specific value of the early warning period can be flexibly set according to actual needs, for example, 5 minutes, 10 minutes, etc., but is not limited to this.
  • the realization form of the prompt information is also different.
  • the smart device may include an audio component, and accordingly, the prompt information may be a voice signal, that is, a voice signal carrying the smart device is sent to the user; for another example, the smart device may include a display screen, and accordingly, the prompt information may be text Information or image information, that is, to show prompt information to the user on the display screen; for another example, the smart device may include a buzzer, and accordingly, the prompt information may be a buzzer signal, that is, a buzzer signal is sent to the user; etc. .
  • the reminder message sent by the smart device can be cancelled by the user voluntarily.
  • the prompt message can be cancelled; if the user is determined to be passively using or wearing the smart device, it can serve as an early warning to the user. In this way, criminals can be prevented from using the smart device to track the whereabouts of others, the privacy of the user can be protected, and the security performance of the smart device can be improved accordingly.
  • the total acceleration of the object used by the smart device refers to the vector sum of its acceleration information in multiple directions.
  • the acceleration sensor is a three-axis acceleration sensor
  • the resultant acceleration of the object to be used is the vector sum of the acceleration information in the front and rear, left and right, and up and down directions.
  • step 102 is to perform feature analysis on the acceleration information of the use object in multiple motion directions to obtain the peak interval characteristics, peak fluctuation characteristics, and time-frequency characteristics of the combined acceleration of the use object of the smart device. At least one of the characteristics and the chaotic degree characteristics of acceleration.
  • step 103 is to determine the smart device based on at least one of the peak interval feature, peak fluctuation feature, time-frequency feature, and acceleration disorder feature of the target acceleration of the smart device.
  • the target of the equipment is to determine the smart device based on at least one of the peak interval feature, peak fluctuation feature, time-frequency feature, and acceleration disorder feature of the target acceleration of the smart device.
  • the average value of the peak interval of the combined acceleration can be calculated, and further, if the average value is less than or equal to the preset interval threshold, the smart device can be determined
  • the object of use is the first category of animals.
  • the preset interval threshold is related to the sampling rate for collecting acceleration information of the smart device during use. Under the same sampling rate, the value of the preset interval threshold can be flexibly set according to the motion behavior characteristics of the actual identified use object.
  • the applicant obtained the combined accelerations of humans, small dogs, medium-sized dogs, and large dogs when walking and running, respectively.
  • the combined accelerations generated by humans walking and running are shown in Figure 2a and Figure 2a. 2b; the resultant acceleration generated by small dogs walking and running are shown in Fig. 3a and Fig. 3b; the resultant acceleration generated by medium dogs walking and running are shown in Fig. 4a and Fig. 4b; large dog walking and running
  • the resulting acceleration is shown in Figure 5a and Figure 5b.
  • the horizontal axis in Figures 2a-5b represents the sampling point, and the vertical axis represents the resultant acceleration.
  • analyze the peak intervals of the combined acceleration generated by humans, small dogs, medium dogs and large dogs when walking and running respectively and obtain the average value of the peak intervals of the combined acceleration of different types of objects as shown in Table 1:
  • the interval threshold can be set to 5.
  • the selection of the interval threshold is related to the sampling rate for acquiring the acceleration information of the smart device in multiple directions; accordingly, if the sampling rate increases, the preset interval threshold also increases; conversely, the preset interval threshold Then decrease.
  • the average value of the peak interval of the total acceleration of the use object is used, and it is not possible to identify whether the use object is a medium-sized dog, a large dog, or a human. That is, if the average value of the peak interval of the combined acceleration of the user is greater than the preset interval threshold, it is impossible to determine whether the user is a medium-sized dog, a large dog, or a human.
  • the peak fluctuation amplitude of the resultant acceleration of the animal with a relatively small body is compared with the peak fluctuation amplitude of the resultant acceleration of the larger animals and humans. Be big. Based on this, in the embodiments of the present application, if the average value of the peak interval of the resultant acceleration of the use object is greater than the preset interval threshold, the use object of the smart device is further determined according to the peak fluctuation characteristics of the resultant acceleration of the use object. Alternatively, the peak fluctuation average value of the resultant acceleration of the use object may be calculated.
  • the peak fluctuation average value of the combined acceleration is greater than or equal to the preset fluctuation threshold, it is determined that the user of the smart device is the second type of animal.
  • the value of the preset fluctuation threshold can be flexibly set according to the actual identified movement behavior characteristics of the use object and the parameters of the acceleration sensor on the smart device.
  • the applicant analyzes the peak fluctuations of the combined acceleration of different types of use objects in Figures 2a-5b, calculates the average value of the peak fluctuations of the combined accelerations of different types of use objects, and obtains the combined acceleration of different types of use objects.
  • the average value of the acceleration peak fluctuation is shown in Table 2 below:
  • the fluctuation threshold can be set to 5000.
  • the average peak fluctuation of the combined acceleration of the object is used If the value is greater than or equal to 5000, it is determined that the target of the smart device is a medium-sized dog.
  • the average value of the peak interval and the average value of the peak fluctuation of the combined acceleration of the use object is used, and it is impossible to identify whether the use object is a large dog or a human. That is, if the average value of the peak interval of the resultant acceleration of the user is greater than the preset interval threshold, and the average value of the peak fluctuation is less than the preset fluctuation threshold, it is impossible to determine whether the user is a large dog or a human.
  • the execution sequence of the use object of the smart device based on the peak interval characteristics and peak fluctuation characteristics of the combined acceleration of the use object.
  • the above only uses the combined acceleration of the use object first. To determine whether the object of use is the first type of animal; if it is determined that the object of use is not the first type of animal, then use the peak fluctuation average of the combined acceleration of the object of use to determine whether the object of use is the second type of animal. Description.
  • the peak fluctuation average value of the combined acceleration of the use object is greater than or equal to a preset fluctuation threshold; if the determination result is yes, it is determined that the use object of the smart device is a second type of animal. Correspondingly, if the judgment result is negative, the average value of the peak interval of the total acceleration is calculated. Further, if the average value of the peak interval of the combined acceleration is less than or equal to the preset interval threshold, it is determined that the object of use of the smart device is the first type of animal.
  • the time-frequency characteristic of the resultant acceleration refers to the relationship between the change frequency of the resultant acceleration and time. Based on this, in the embodiments of the present application, if based on the peak interval characteristics and peak fluctuation characteristics of the total acceleration of the use object, the category of the use object of the smart device cannot be determined, and further based on the time-frequency characteristics of the total acceleration of the use object, Determine who the smart device will use.
  • the resultant acceleration of the use object may be subjected to wavelet analysis to obtain the time-frequency information of the resultant acceleration of the use object of the smart device. Further, the frequency peak of the resultant acceleration can be counted according to the time-frequency information of the resultant acceleration; if the peak value of the resultant acceleration frequency of the used object is greater than or equal to the preset frequency peak threshold, it is determined that the user of the smart device is a human.
  • the peak value of the frequency of the resultant acceleration frequency of the object of use may be the average value of the peak value of the resultant acceleration frequency, or part or all of the peak value of the resultant acceleration frequency.
  • the wavelet function selected for the wavelet analysis of the resultant acceleration is different, and the time-frequency information of the resultant acceleration obtained is different.
  • the Harr function, Daubechies function in the form of db N, where N represents the number of wavelet base layers
  • Morlet function or Symlets function can be used to perform wavelet analysis on the resultant acceleration of the used object to obtain the time-frequency information of the resultant acceleration.
  • the number of layers of the wavelet base used is different, and the time-frequency information of the resultant acceleration obtained is also different.
  • db5 can be used to perform wavelet analysis on the total acceleration of the object used.
  • the time-frequency information of the high-frequency layer d 5 may be used to determine the use object of the smart device.
  • the statistical frequency stratified d information when the peak frequency of the frequency 5, if the peak value is greater than or equal to a preset threshold value of the peak frequency it is determined that the smart device using the object is a human.
  • the preset frequency peak threshold can be set according to the motion behavior characteristics of the use object determined according to actual needs, and is not limited here.
  • the applicant uses wavelet db5 to perform wavelet analysis on the combined acceleration of the above-mentioned large dog walking and running and human walking and running, and obtain the data after the wavelet transformation of the combined acceleration when the large dog is walking, as shown in Figure 6a.
  • the resultant acceleration during running corresponds to the wavelet transformed data as shown in Figure 6b.
  • the resultant acceleration during walking corresponds to the wavelet transformed data as shown in Figure 7a.
  • the resultant acceleration during running corresponds to the wavelet transformed data as shown in Figure 7b. Shown.
  • the frequency peak threshold can be set to any value between 1500 and 2000, for example, it can be set to 1800, 1900, 2000, etc., but is not limited thereto. Based on this, if the frequency peak of the combined acceleration of the using object is greater than or equal to the preset frequency peak threshold, it is determined that the using object of the smart device is a human.
  • the frequency peak of the combined acceleration of the user is smaller than the preset frequency peak threshold, it may not be directly determined that the user of the smart device is not a human being.
  • the frequency distribution of the high-frequency stratification d 5 of the resultant acceleration generated when a person is walking or a large dog is running is between 200 and 500.
  • the frequency peak threshold value may be used by people.
  • the use object can be further determined according to the chaotic characteristics of acceleration.
  • the peak value of the combined acceleration of the use object is less than the preset frequency peak threshold, the confusion degree of the acceleration of the use object of the smart device can be calculated. Further, if the confusion degree of the acceleration of the use object is within the set confusion degree range, it is determined that the use object of the smart device is a human being.
  • the implementation of calculating the degree of confusion of the acceleration of the use object is not limited.
  • the entropy value of the acceleration of the object in a plurality of motion directions may be calculated separately, and the entropy value of the acceleration in each motion direction may be used as the degree of confusion in the motion direction.
  • the entropy value in each direction of movement belongs to the corresponding entropy value range in the respective direction, it is determined that the user of the smart device is a human.
  • there is an entropy value in the direction of motion that does not belong to the corresponding entropy value range in the direction it is determined that the object of use of the smart device is not a human.
  • the acceleration sensor on the smart device uses the acceleration sensor on the smart device as a three-axis acceleration sensor, that is, the acceleration information of the object used by the smart device in multiple directions of movement is the acceleration on the x-axis, y-axis, and z-axis, then the smart device’s Use the acceleration of the object on the x-axis, y-axis and z-axis to calculate the ratio distribution of acceleration on each two coordinate axes; further, calculate every two coordinates according to the ratio distribution of acceleration on each coordinate axis The peak average rate of change of the ratio of the acceleration of the axis, and each peak average rate of change is used as the confusion degree of the acceleration on the corresponding two coordinate axes.
  • the acceleration of the object on the x-axis and the y-axis can use the acceleration of the object on the x-axis and the y-axis to calculate the ratio distribution of the acceleration on the x-axis and the y-axis.
  • the ratio distribution of the acceleration on the x-axis and the y-axis is referred to as x/y distribution; further, according to the x/y distribution, calculate the peak average rate of change of the x/y distribution, then the peak average rate of change of the x/y distribution is the confusion degree of the acceleration on x/y.
  • the peak average rate of change of the x/y distribution refers to the average value of the rate of change of two adjacent peaks in the x/y distribution, that is, the rate of change of the next peak in the x/y distribution compared to the previous peak. average value.
  • the ratio of the acceleration on each of the two coordinate axes is calculated, as shown in Figure 8a, Figure 8b and Figure 8c, respectively.
  • the ratio of the acceleration on each two coordinate axes is shown in Figure 9a, Figure 9b and Figure 9c, respectively.
  • the confusion degree range can be set according to the confusion degree of the acceleration on every two coordinate axes when a person is walking. If the confusion degree of the acceleration ratio of the used object on every two coordinate axes is within the preset confusion degree range in the corresponding direction, it is determined that the user object of the smart device is a human.
  • the accuracy of the recognition of the use object of the smart device can be improved; It helps to improve the accuracy of step counting or positioning.
  • the first type of animal is a small dog
  • the second type of animal is a medium-sized dog
  • the third type of animal is a large dog.
  • the above-mentioned combined acceleration peak interval threshold and peak value The fluctuation threshold, the frequency peak threshold corresponding to the time-frequency feature, and the range of the acceleration disorder can all be flexibly set according to the actual category of the use object to be distinguished, and does not constitute a limitation.
  • the small dog can be a Teddy (that is, the height of the shoulder is 28-35 cm); the medium dog can be a Corgi (that is, the height of the shoulder is 38-45 cm); the large dog can be a Satsuma (that is, the height is 48-59 cm) ), but not limited to this.
  • the execution subject of each step of the method provided in the foregoing embodiment may be the same device, or different devices may also be the execution subject of the method.
  • the execution subject of steps 101 and 102 may be device A; for another example, the execution subject of step 101 may be device A, and the execution subject of step 102 may be device B; and so on.
  • the embodiments of the present application also provide a computer-readable storage medium storing computer instructions.
  • the one or more processors are caused to execute the steps in the foregoing method.
  • FIG. 10 is a schematic structural diagram of a smart device provided by an embodiment of the application. As shown in FIG. 10, the smart device includes: an acceleration sensor 10a, a memory 10b, and a processor 10c.
  • the acceleration sensor 10a is used to collect acceleration information in multiple motion directions generated by the smart device during use.
  • the memory 10b is used to store computer programs, and can be configured to store various other data to support operations on the smart device.
  • the processor 10c can execute a computer program stored in the memory 10b to implement corresponding control logic.
  • the memory 10b can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic Disk Magnetic Disk or Optical Disk.
  • the processor 10b when the processor 10b acquires at least one acceleration characteristic of the use object of the smart device, it is specifically configured to: perform characteristic analysis on acceleration information in multiple motion directions generated by the smart device during use, Obtain at least one of the peak interval feature, peak fluctuation feature, time-frequency feature, and acceleration disorder feature of the combined acceleration of the object used by the smart device; wherein, the combined acceleration of the object used by the smart device refers to multiple motion directions The vector sum of the acceleration information.
  • the processor 10b when determining the use object of the smart device, is specifically configured to: according to at least one of the peak interval feature, peak fluctuation feature, time-frequency feature, and acceleration disorder feature of the combined acceleration of the smart device. kind of, determine the target of the smart device.
  • the processor 10b is specifically configured to calculate the average value of the peak interval of the combined acceleration when determining the target of the smart device; if the average value of the peak interval of the combined acceleration is less than or equal to the preset interval threshold, determine the smart device
  • the object of use is the first category of animals.
  • the processor 10b is specifically used to calculate the peak fluctuation average of the combined acceleration when determining the target of the smart device; if the peak fluctuation average of the combined acceleration If the value is greater than or equal to the preset fluctuation threshold, it is determined that the object of use of the smart device is the second type of animal.
  • the processor 10b determines the use object of the smart device, it is specifically used to: perform wavelet analysis on the resultant acceleration to obtain the resultant acceleration value of the use object of the smart device Time-frequency information; if the peak value of the combined acceleration frequency of the used object is greater than or equal to the preset frequency peak threshold, it is determined that the user of the smart device is a human.
  • the processor 10b when determining the use object of the smart device, is specifically used to: calculate the confusion degree of the acceleration of the use object of the smart device;
  • the acceleration chaos is within the set chaos range, and the target of the smart device is determined to be human.
  • the processor 10b calculates the confusion degree of the acceleration of the used object of the smart device, it is specifically used to: use the acceleration of the used object of the smart device on the x-axis, y-axis, and z-axis to calculate each two coordinate axes. According to the ratio distribution of acceleration on each two coordinate axes, calculate the peak average rate of change of the ratio of acceleration of each two coordinate axes, and use each peak average rate of change as the corresponding two coordinates Disturbance of acceleration on the axis.
  • the processor 10b is further configured to: if it is determined that the user of the smart device is a human, when the preset alarm time arrives, send a prompt message carrying the smart device to the user; or, If it is determined that the target of use of the smart device is a human, when each early warning period arrives, a prompt message carrying the smart device is sent to the target of use.
  • the smart device further includes a communication component 10d.
  • the communication component 10d is configured to facilitate wired or wireless communication between the smart device and other devices.
  • Smart devices can access wireless networks based on communication standards, such as WiFi, 2G or 3G, or a combination of them.
  • the communication component receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component may also be based on a near field communication (NFC) module, radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and others Technology to achieve.
  • NFC near field communication
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the smart device further includes a power supply component 10e.
  • the power supply component 10e is configured to provide power to various components of the smart device.
  • the power supply component 10e may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device where the power supply component is located.
  • the smart device may further include a sound input/output unit 10f, which may be configured to output and/or input audio signals, such as projection sound.
  • the sound input/output unit 10f includes a microphone (MIC), and the microphone is configured to receive external audio signals when the device where the audio component is located is in operation mode, such as call mode, recording mode, and voice recognition mode.
  • the received audio signal may be further stored in a memory or transmitted via the communication component 10d.
  • the audio component further includes a speaker for outputting audio signals.
  • the voice input/output unit 10f can be used to realize voice interaction with the user.
  • the smart device may further include a sound processing unit 10g for processing sound signals input or output by the sound input/output unit 10f.
  • the smart device further includes: a display 10h.
  • the display 10h may include a liquid crystal display (LCD) and or a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the smart device may further include an image processing unit 10i for performing signal processing, such as image quality correction related to the image signal output from the processor 10b, and converting its resolution into a resolution according to the screen of the display 10h .
  • the display driving unit 10j sequentially selects each row of pixels of the display 10h, and sequentially scans each row of pixels of the display 10h row by row, thereby providing a pixel signal based on the signal-processed image signal.
  • the smart device also inputs an operation unit (not shown in FIG. 10).
  • the input operation unit includes at least one operation component for performing input operations, such as keys, buttons, switches, or other components with similar functions, and receives user instructions through the operation components and outputs instructions to the processor 10b.
  • the smart device provided in this embodiment performs characteristic analysis on the acceleration information in multiple motion directions generated during use, acquires the acceleration characteristics of the use object of the smart device, and determines the smart device according to the acceleration characteristics of the use object The intended use object. In this way, after the target of use of the smart device is identified, a method that matches the target of use can be used to count or locate the target, which helps to improve the accuracy of step counting or positioning.
  • the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.
  • the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.
  • processors CPU
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-permanent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology.
  • the information can be computer-readable instructions, data structures, program modules, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种使用对象确定方法、设备及存储介质,其中,对智能设备在使用过程中产生的多个运动方向上的加速度信息进行特征分析,获取智能设备的使用对象的加速度特征,并根据使用对象的加速度特征,确定出智能设备的使用对象。这样,在识别出智能设备的使用对象之后,可采用与该使用对象匹配的方式对其进行计步或定位,有助于提高计步或定位的精度。

Description

使用对象确定方法、设备及存储介质
本申请要求于2019年4月15日提交中国专利局、申请号为201910301115.7、发明名称为“使用对象确定方法、设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及人工智能技术领域,尤其涉及一种使用对象确定方法、设备及存储介质。
背景技术
随着人工智能技术的不断发展,智能设备被广泛应用于人们的日常生活中,例如,智能手机以及智能手表、智能手环等可穿戴设备已与人们的生活密不可分。这些智能设备除了向人们提供基础功能之外,还可进行计步、定位等。使用对象的不同,会影响智能设备计步或定位的精度,因此有必要确定智能设备的使用对象。
发明内容
本申请的多个方面提供一种使用对象确定方法、设备及存储介质,用以识别智能设备的使用对象,进而有助于提高后续对使用对象进行计步或定位的精度。
本申请实施例提供一种使用对象确定方法,包括:
获取智能设备在使用过程中产生的多个运动方向上的加速度信息;
对所述多个运动方向上的加速度信息进行特征分析,获取所述智能设备的使用对象的至少一个加速度特征;
根据所述使用对象的至少一个加速度特征,确定出所述智能设备的使用对象。
本申请实施例还提供一种智能设备,包括:加速度传感器、存储器和处理器;其中,所述加速度传感器用于采集所述智能设备在使用过程中产生的多个运动方向上的加速度信息;
所述存储器,用于存储计算机程序;
所述处理器耦合至所述存储器,用于执行所述计算机程序以用于:
对所述多个运动方向上的加速度信息进行特征分析,获取所述智能设备的使用对象的至少一个加速度特征;
根据所述使用对象的至少一个加速度特征,确定出所述智能设备的使用对象。
本申请实施例还提供一种存储有计算机指令的计算机可读存储介质,当所述计算机指令被一个或多个处理器执行时,致使所述一个或多个处理器执行上述方法中的步骤。
在本申请实施例中,对智能设备在使用过程中产生的多个运动方向上的加速度信息进行特征分析,获取智能设备的使用对象的加速度特征,并根据使用对象的加速度特征,确定出智能设备的使用对象。这样,在识别出智能设备的使用对象之后,可采用与该使用对象匹配的方式对其进行计步或定位,有助于提高计步或定位的精度。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一部分附图,对于本 领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据提供的附图获得其他的附图。
图1为本申请实施例提供的一种使用对象确定方法的流程示意图;
图2a和图2b分别为本申请实施例提供的人在走路和跑步时产生的合加速度的示意图;
图3a和图3b分别为本申请实施例提供的小型犬走路和跑步时产生的合加速度的示意图;
图4a和图4b分别为本申请实施例提供的中型犬走路和跑步时产生的合加速度的示意图;
图5a和图5b分别为本申请实施例提供的大型犬走路和跑步时产生的合加速度的示意图;
图6a和图6b分别为本申请实施例提供的大型犬走路和跑步时的合加速度对应的小波变化后的示意图;
图7a和图7b分别为本申请实施例提供的人走路和跑步时的合加速度对应的小波变化后的示意图;
图8a为本申请实施例提供的人走路时x轴和y轴的加速度比值的分布示意图;
图8b为本申请实施例提供的人走路时y轴和z轴的加速度比值的分布示意图;
图8c为本申请实施例提供的人走路时x轴和z轴的加速度比值的分布示意图;
图9a为本申请实施例提供的大型犬跑步时x轴和y轴的加速度比值的分布示意图;
图9b为本申请实施例提供的大型犬跑步时y轴和z轴的加速度比值的分布示意图;
图9c为本申请实施例提供的大型犬跑步时x轴和z轴的加速度比值的分布示意图;
图10为本申请实施例提供的一种智能设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行描述,显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
针对现有智能设备计步或定位的精度较低的技术问题,本申请实施例提供一种解决方案,基本思路是:对智能设备在使用过程中产生的多个运动方向上的加速度信息进行特征分析,获取智能设备的使用对象的加速度特征,并根据使用对象的加速度特征,确定出智能设备的使用对象。这样,在识别出智能设备的使用对象之后,可采用与该使用对象匹配的方式对其进行计步或定位,有助于提高计步或定位的精度。
以下结合附图,详细说明本申请各实施例提供的技术方案。
图1为本申请实施例提高的一种使用对象确定方法的流程示意图。如图1所示,该方法包括:
101、获取智能设备在使用过程中产生的多个运动方向上的加速度信息。
102、对智能设备在使用过程中产生的多个运动方向上的加速度信息进行特征分析,获取智能设备的使用对象的至少一个加速度特征。
103、根据使用对象的至少一个加速度特征,确定出智能设备的使用对象。
在本实施例中,智能设备是指具有计步或定位功能的电子设备,其可以为智能手机、平板电脑等终端设备,也可以为智能手表、手环、智能眼镜、蓝牙耳机、钥匙扣等可穿戴设备,或者为防丢器等,但不限于此。
在本实施例中,智能设备上设置有加速度传感器,用于采集智能设备在使用过程中产生的多个运 动方向上的加速度信息。在本申请实施例中,多个是指2个或2个以上,其具体取值可根据加速度传感器的输入轴数目来确定。例如,若加速度传感器为三轴加速度传感器,则多个运动方向可以前后、左右、上下3个运动方向,但不限于此。
进一步,由于不同种类使用对象的结构特征不同,其行动方式、行进动作也就有所区别。使用对象的行为方式和行进动作影响其加速度,不同种类的使用对象也就具有不同的加速度特征。基于此,在步骤102中,对采集到的多个运动方向上的加速度信息进行特征分析,获取该使用对象的至少一个加速度特征。接着,根据使用对象的至少一个加速度特征,对使用对象进行模式识别,进而确定出智能设备的使用对象。在本申请实施例中,确定出的智能设备的使用对象是指使用对象的类别,例如,确定出使用对象为人类、小型宠物、中型宠物或大型宠物等。
在本申请实施例中,针对不同类别的使用对象可采用不同的计步方式,例如,若使用对象为人类,可采用符合人类行为特征的计步方式对其进行计步;又例如,若使用对象为动物,可采用符合动物行为特征的计步方式对其进行计步,这样有助于提高对使用对象计步或定位的精度。
另一方面,在本申请实施例中,为了提高智能设备的安全性,保护使用对象的隐私安全,还可设置相应的预警装置。例如,可在智能设备上设置一个特殊的隐藏功能。若确定出智能设备的使用对象为人类,则在预设的报警时间到达时,可向使用对象发出携带有该智能设备的提示信息。其中,预设的报警时间可以为5分钟、10分钟等,但不限于此。
或者,可在智能设备中预设预警周期,若确定智能设备的使用对象为人类,则触发一定时器或计数器对预警周期进行计时,且在每个预警周期到达时,向使用对象发出携带有该智能设备的提示信息。其中,预警周期的具体取值可根据实际需求进行灵活设定,例如,5分钟、10分钟等,但不限于此。
进一步,根据智能设备的结构形式不同,提示信息的实现形式也就不同。例如,智能设备可包括音频组件,相应地,提示信息可为语音信号,即向使用对象发出携带有智能设备的语音信号;又例如,智能设备可包括显示屏,相应地,提示信息可为文本信息或图像信息等,即在显示屏上向用户展示提示信息;又例如,智能设备可包括蜂鸣器,相应地,提示信息可为蜂鸣信号,即向使用对象发出蜂鸣信号;等等。
进一步,智能设备发出的提示信息,使用对象可自主取消。例如,若使用对象确定是自己主动佩戴或使用该智能设备,可取消提示信息;若使用对象确定是被动使用或佩戴该智能设备,可起到对使用对象预警的作用。这样,可防止不法分子将智能设备用到对他人行踪的跟踪上面,可保护使用对象的隐私安全,相应地可提高智能设备的安全性能。
在本申请实施例中,可采用多种加速度特征对使用对象进行识别。可选地,可采用使用对象的合加速度的波峰间隔特征、峰值波动特征、时频特征或加速度的混乱度特征,对使用对象进行识别。其中,智能设备的使用对象的合加速度是指其在多个方向上的加速度信息的矢量和。例如,若加速度传感器为三轴加速度传感器,则使用对象的合加速度为其在前后、左右、上下三个方向上的加速度信息的矢量和。为了便于描述和区分,在本申请实施例中,将使用对象的前后方向定义为x轴方向、左右方向定义为y轴方向、前后方向定义为z轴方向。基于此,步骤102的一种可选实施方式为:对使用对象在多个运动方向上的加速度信息进行特征分析,得到智能设备的使用对象的合加速度的波峰间隔特征、 峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种。
相应地,步骤103的一种可选实施方式为:根据智能设备的使用对象的合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种,确定出智能设备的使用对象。
进一步,若根据使用对象的波峰间隔特征,确定智能设备的使用对象,则可计算合加速度的波峰间隔的平均值,进一步,若该平均值小于或等于预设的间隔阈值,则可确定智能设备的使用对象为第一类动物。其中,预设的间隔阈值与采集智能设备在使用过程中的加速度信息的采样率有关。在相同的采样率下,预设的间隔阈值的取值可根据实际识别的使用对象的运动行为特征进行灵活设定。
例如,在相同的采样率下,申请人获取的人类、小型犬、中型犬以及大型犬分别进行走路和跑步时产生的合加速度,其中,人类走路和跑步时产生的合加速度如图2a和图2b所示;小型犬走路和跑步时产生的合加速度如图3a和图3b所示;中型犬走路和跑步时产生的合加速度如图4a和图4b所示;大型犬走路和跑步时产生的合加速度如图5a和图5b所示。其中,图2a-图5b中横轴表示采样点,纵轴表示合加速度。进一步,对人类、小型犬、中型犬以及大型犬分别进行走路和跑步时产生的合加速度的波峰间隔进行分析,得到不同类型的使用对象的合加速度的波峰间隔平均值如下表1所示:
表1 不同类型的使用对象的合加速度的波峰间隔平均值对比表
Figure PCTCN2019129571-appb-000001
由表1分析可得,若要将小型犬与其他类型的使用对象区分开来,可将间隔阈值设置为5,相应地,若使用对象的合加速度的波峰间隔的平均值小于或等于5,则确定智能设备的使用对象为小型犬。其中,间隔阈值的选择,与获取智能设备在多个方向上的加速度信息的采样率有关;相应地,若采样率增大,则预设的间隔阈值也增大;反之,预设的间隔阈值则减小。
进一步,在实际应用中,只考虑使用对象的合加速度的波峰间隔特征,有可能不能准确确定出使用对象的类别。例如,上述实施例中,利用使用对象的合加速度的波峰间隔的平均值,并无法识别使用对象为中型犬、大型犬还是人类。即若使用对象的合加速度的波峰间隔的平均值大于预设的间隔阈值,则无法确定使用对象是中型犬、大型犬还是人类。
申请人发现,不同类型的使用对象,其合加速度的峰值波动特征不同,且体格比较小的动物的合加速度的峰值波动幅度,相较于体格较大的动物以及人类的合加速度的峰值波动幅度要大。基于此,本申请实施例中,若使用对象的合加速度的波峰间隔的平均值大于预设的间隔阈值,则进一步根据使用对象的合加速度的峰值波动特征,确定智能设备的使用对象。可选地,可计算使用对象的合加速度的峰值波动平均值。进一步,若合加速度的峰值波动平均值大于或等于预设的波动阈值,则确定智能设备的使用对象为第二类动物。其中,预设的波动阈值的取值可根据实际识别的使用对象的运动行为特征以及智能设备上的加速度传感器的参数进行灵活设定。
例如,申请人对图2a-图5b中的不同类型的使用对象的合加速度的峰值波动进行分析,计算不同类型的使用对象的合加速度的峰值波动的平均值,得到不同类型的使用对象的合加速度的峰值波动的平均值如下表2所示:
表2 不同类型的使用对象的合加速度的峰值波动的平均值对比表
Figure PCTCN2019129571-appb-000002
由表2分析可得,若要将中型犬与其他类型的使用对象(大型犬和人类)区分开来,可将波动阈值设置为5000,相应地,若使用对象的合加速度的峰值波动的平均值大于或等于5000,则确定智能设备的使用对象为中型犬。
进一步,在实际应用中,只考虑使用对象的合加速度的波峰间隔特征和/或峰值波动平均值,有可能不能准确确定出使用对象的类别。例如,上述实施例中,利用使用对象的合加速度的波峰间隔平均值和峰值波动的平均值,并无法识别使用对象为大型犬还是人类。即若使用对象的合加速度的波峰间隔的平均值大于预设的间隔阈值,且其峰值波动平均值小于预设的波动阈值,则无法确定使用对象是大型犬还是人类。
值得说明的是,在本申请实施例中,不限定上述根据使用对象的合加速度的波峰间隔特征和峰值波动特征,确定智能设备的使用对象的执行顺序,上述仅以先利用使用对象的合加速度的波峰间隔特征,判断使用对象是否为第一类动物;若确定使用对象不是第一类动物,再利用使用对象的合加速的峰值波动平均值,判断使用对象是否为第二类动物进行示例性说明。例如,还可先判断使用对象的合加速度的峰值波动平均值是否大于或等于预设的波动阈值;若判断结果为是,则确定智能设备的使用对象为第二类动物。相应地,若判断结果为否,则计算合加速度的波峰间隔的平均值。进一步,若合加速度的波峰间隔的平均值小于或等于预设的间隔阈值,则确定智能设备的使用对象为第一类动物。
进一步,申请人还发现,由于不同类型的使用对象的运动行为方式和前进方式不同,则不同类型的使用对象的合加速度的时频特征也就不同。其中,合加速度的时频特征是指:合加速度的变化频率随时间的变化关系。基于此,在本申请实施例中,若根据使用对象的合加速度的波峰间隔特征和峰值波动特征,无法确定出智能设备的使用对象的类别,进一步可根据使用对象的合加速度的时频特征,确定智能设备的使用对象。可选地,若使用对象的合加速度的峰值波动平均值小于预设的波动阈值,可对使用对象的合加速度进行小波分析,获取智能设备的使用对象的合加速度的时频信息。进一步,可根据合加速度的时频信息,统计合加速度的频率的峰值;若使用对象的合加速度的频率的峰值大于或等于预设的频率峰值阈值,则确定智能设备的使用对象为人类。其中,使用对象的合加速度的频率的峰值可以为合加速度频率的峰值的平均值,也可为合加速度频率的部分或全部峰值。
其中,对合加速度进行小波分析选用的小波函数不同,所获取的合加速度的时频信息不同。例如,可采用harr函数、Daubechies函数(表示形式为db N,其中N表示小波基的层数)、Morlet函数或Symlets函数等对使用对象的合加速度进行小波分析,获取合加速度的时频信息,但不限于此。进一步,即便 采用同一小波函数对合加速度进行小波分析,采用的小波基的层数不同,获取的合加速度的时频信息也不同。其中,具体采用的小波函数以及小波基的层数可根据实际需求进行灵活选择,在此不进行限定。例如,可采用db5对使用对象的合加速度进行小波分析。当采用db5对使用对象的合加速度进行小波分析时,合加速度的原始信号可表示为:s=a 5+d 5+d 4+d 3+d 2+d 1;其中,s表示合加速度的原始信号;a 5表示采用db5对使用对象的合加速度进行小波变换后的低频信号的时频信息;d 1~d 5分别表示采用db5对使用对象的合加速度进行小波变换后的各层的高频信号的时频信息。
进一步,对于采用哪层的时频信息,来确定智能设备的使用对象,可根据实际应用中使用对象的运动行为特征进行灵活设定。可选地,可选用高频分层d 5的时频信息,来确定智能设备的使用对象。可选地,可统计高频分层d 5的时频信息的频率的峰值,若该峰值大于或等于预设的频率峰值阈值,则确定智能设备的使用对象为人类。其中,预设的频率峰值阈值可根据实际需要确定的使用对象的运动行为特征进行设定,在此不进行限制。
例如,申请人采用小波db5对上述大型犬走路和跑步以及人走路和跑步时产生的合加速度进行小波分析,得到大型犬走路时的合加速度对应小波变换后的数据如图6a所示,大型犬跑步时的合加速度对应小波变换后的数据如图6b所示,人走路时的合加速度对应小波变换后的数据如图7a所示,人跑步时的合加速度对应小波变换后的数据如图7b所示。进一步,对高频分层d 5的时频信息进行分析可得:人跑步时,其产生的合加速度的高频分层d 5的频率峰值在2000左右,而大型犬在走路时,其产生的合加速度的高频分层d 5的频率几乎在0附近;人走路以及大型犬跑步时,产生的合加速度的高频分层d 5的频率分布均在200~500之间。在该示例中,可将频率峰值阈值设置为1500~2000之间的任一数值,例如,可以设置为1800、1900、2000等,但不限于此。基于此,若使用对象的合加速度的频率峰值大于或等于预设的频率峰值阈值,则确定智能设备的使用对象为人类。
然而,在实际应用中,若使用对象的合加速度的频率峰值小于预设的频率峰值阈值,有可能不能直接确定智能设备的使用对象不是人类。例如,上述实施例中,由于人走路以及大型犬跑步时,产生的合加速度的高频分层d 5的频率分布均在200~500之间,当使用对象的合加速度的频率峰值小于预设的频率峰值阈值,使用对象也可能为人。
为了进一步提高智能设备的使用对象的识别准确度,在本申请实施例中,还可根据加速度的混乱度特征对使用对象进一步进行确定。可选地,若使用对象的合加速度的峰值小于预设的频率峰值阈值,则可计算智能设备的使用对象的加速度的混乱度。进一步,若该使用对象的加速度的混乱度在设定的混乱度范围内,则确定智能设备的使用对象为人类。
在本申请实施例中,对计算使用对象的加速度的混乱度的实施方式不进行限定。例如,可分别计算使用对象在多个运动方向上的加速度的熵值,并将每个运动方向上的加速度的熵值作为该运动方向上的混乱度。进一步,若每个运动方向上的熵值均属于各自方向上对应的熵值范围,则确定智能设备的使用对象为人类。相应地,若存在运动方向上的熵值不属于该方向上对应的熵值范围,则确定智能设备的使用对象不是人类。
可选地,还可根据每两个运动方向上的加速度的比值分布,计算对应的两个运动方向上的加速度的混乱度。下面以智能设备上的加速度传感器为三轴加速度传感器,即智能设备的使用对象的在多个运动方向上的加速度信息分别为x轴、y轴和z轴上的加速度,则可利用智能设备的使用对象分别在x轴、y轴和z轴上的加速度,计算每两个坐标轴上的加速度的比值分布;进一步,根据每连个坐标轴上的加 速度的比值分布,分别计算每两个坐标轴的加速度的比值的峰值平均变化率,并将每个峰值平均变化率作为对应的两个坐标轴上的加速度的混乱度。例如,可利用使用对象在x轴和y轴上的加速度,计算x轴与y轴上的加速度的比值分布,为了便于描述和区分,将x轴与y轴上的加速度的比值分布,简称为x/y分布;进一步,根据x/y分布,计算x/y分布的峰值平均变化率,则x/y分布的峰值平均变化率,为x/y上的加速度的混乱度。其中,x/y分布的峰值平均变化率是指:x/y分布中,相邻的两个峰值的变化率的平均值,即x/y分布中后一个峰值相较于前一个峰值变化率的平均值。
例如,在本申请实施例中,计算上述人走路时在x轴、y轴和z轴上的产生的加速度中,每2个坐标轴上加速度的比值,分别如图8a、图8b和图8c所示;并计算上述大型犬跑步时在x轴、y轴和z轴上的产生的加速度中,每2个坐标轴上加速度的比值,分别如图9a、图9b和图9c所示。其中,图8a、图8b和图8c以及图9a、图9b和图9c的横轴表示采样点数,纵轴表示对应的两个坐标轴上的加速度的比值。从图8a、图8b和图8c以及图9a、图9b和图9c分析可得:大型犬跑步时的在各坐标轴上的加速度比值的混乱度均大于人走路时在对应的两个坐标轴上的加速度的混乱度。在基于此,可根据人走路时的每2个坐标轴上的加速度的混乱度设置混乱度范围。若使用对象在每2个坐标轴上的加速度比值的混乱度均属于预设的对应方向上的混乱度范围,则确定智能设备的使用对象为人类。
在本申请实施例中,利用智能设备的使用对象的上述多个加速度特征,逐步将人类和动物区分开来,可提高对智能设备的使用对象识别的准确度;进而在后续采用与使用对象匹配的方式对其进行计步或定位时,有助于提高计步或定位的精度。
值得说明的是,在本申请各实施例中仅以第一类动物为小型犬、第二类动物为中型犬、第三类动物为大型犬进行示例,其中上述合加速度的波峰间隔阈值、峰值波动阈值、时频特征对应的频率峰值阈值以及加速度的混乱度范围均可以根据实际要区分的使用对象的类别进行灵活设定,并不对其构成限定。可选地,小型犬可以为泰迪(即肩高为28-35厘米);中型犬可以为柯基(即肩高38-45厘米);大型犬可以为萨摩(即肩高为48-59cm)等,但不限于此。
需要说明的是,上述实施例所提供方法的各步骤的执行主体均可以是同一设备,或者,该方法也由不同设备作为执行主体。比如,步骤101和102的执行主体可以为设备A;又比如,步骤101的执行主体可以为设备A,步骤102的执行主体可以为设备B;等等。
另外,在上述实施例及附图中的描述的一些流程中,包含了按照特定顺序出现的多个操作,但是应该清楚了解,这些操作可以不按照其在本文中出现的顺序来执行或并行执行,操作的序号如101、102等,仅仅是用于区分开各个不同的操作,序号本身不代表任何的执行顺序。另外,这些流程可以包括更多或更少的操作,并且这些操作可以按顺序执行或并行执行。
相应地,本申请实施例还提供一种存储有计算机指令的计算机可读存储介质,当这些计算机指令被一个或多个处理器执行时,致使一个或多个处理器执行上述方法中的步骤。
图10为本申请实施例提供的一种智能设备的结构示意图。如图10所示,智能设备包括:加速度传感器10a、存储器10b和处理器10c。
在本实施例中,加速度传感器10a用于采集智能设备在使用过程中产生的多个运动方向上的加速度信息。
在本实施例中,其中,存储器10b用于存储计算机程序,并可被配置为存储其它各种数据以支持在智能设备上的操作。其中,处理器10c可执行存储器10b中存储的计算机程序,以实现相应控制逻辑。存储器10b可以由任何类型的易失性或非易失性存储设备或者它们的组合实现,如静态随机存取存储器(SRAM),电可擦除可编程只读存储器(EEPROM),可擦除可编程只读存储器(EPROM),可编程只读存储器(PROM),只读存储器(ROM),磁存储器,快闪存储器,磁盘或光盘。
在一可选实施例中,处理器10b在获取智能设备的使用对象的至少一个加速度特征时,具体用于:对智能设备在使用过程中产生的多个运动方向上的加速度信息进行特征分析,得到智能设备的使用对象的合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种;其中,智能设备的使用对象的合加速度是指多个运动方向上的加速度信息的矢量和。
相应地,处理器10b在确定智能设备的使用对象时,具体用于:根据智能设备的使用对象的合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种,确定出智能设备的使用对象。
进一步,处理器10b在确定智能设备的使用对象时,具体用于:计算合加速度的波峰间隔的平均值;若合加速度的波峰间隔的平均值小于或等于预设的间隔阈值,则确定智能设备的使用对象为第一类动物。
进一步,若合加速度的波峰间隔的平均值大于预设的间隔阈值,处理器10b在确定智能设备的使用对象时,具体用于:计算合加速度的峰值波动平均值;若合加速度的峰值波动平均值大于或等于预设的波动阈值,则确定智能设备的使用对象为第二类动物。
进一步,若合加速度的峰值波动平均值小于预设的波动阈值,处理器10b在确定智能设备的使用对象时,具体用于:对合加速度进行小波分析,获取智能设备的使用对象的合加速度的时频信息;若使用对象的合加速度的频率的峰值大于或等于预设的频率峰值阈值,则确定智能设备的使用对象为人类。
进一步,若使用对象的合加速度的峰值小于预设的频率峰值阈值,处理器10b在确定智能设备的使用对象时,具体用于:计算智能设备的使用对象的加速度的混乱度;若使用对象的加速度的混乱度在设定的混乱度范围内,确定智能设备的使用对象为人类。
进一步,处理器10b在计算智能设备的使用对象的加速度的混乱度时,具体用于:利用智能设备的使用对象分别在x轴、y轴和z轴上的加速度,计算每两个坐标轴上的加速度的比值分布;根据每两个坐标轴上的加速度的比值分布,分别计算每两个坐标轴的加速度的比值的峰值平均变化率,并将每个峰值平均变化率作为对应的两个坐标轴上的加速度的混乱度。
在另一可选实施例中,处理器10b还用于:若确定智能设备的使用对象为人类,则在预设的报警时间到达时,向使用对象发出携带有智能设备的提示信息;或者,若确定智能设备的使用对象为人类,则在每个预警周期到达时,向使用对象发出携带有智能设备的提示信息。
在一些实施例中,智能设备还包括通信组件10d。通信组件10d被配置为便于智能设备和其他设备之间有线或无线方式的通信。智能设备可以接入基于通信标准的无线网络,如WiFi,2G或3G,或它们的组合。在一个示例性实施例中,通信组件经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中,通信组件还可基于近场通信(NFC)模块,射频识别(RFID) 技术,红外数据协会(IrDA)技术,超宽带(UWB)技术,蓝牙(BT)技术和其他技术来实现。
在另一些实施例中,智能设备还包括电源组件10e。电源组件10e被配置为智能设备的各种组件提供电力。电源组件10e可以包括电源管理系统,一个或多个电源,及其他与为电源组件所在设备生成、管理和分配电力相关联的组件。
在一些实施例中,智能设备还可包括声音输入/输出单元10f可被配置为输出和/或输入音频信号,例如投影音响等。例如,声音输入/输出单元10f包括一个麦克风(MIC),当音频组件所在设备处于操作模式,如呼叫模式、记录模式和语音识别模式时,麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器或经由通信组件10d发送。在一些实施例中,音频组件还包括一个扬声器,用于输出音频信号。例如,对于具有语言交互功能的智能设备,可通过声音输入/输出单元10f,实现与用户的语音交互等。
相应地,智能设备还可包括声音处理单元10g,用于对声音输入/输出单元10f输入或输出的声音信号进行处理。
在一些实施例中,智能设备还包括:显示器10h。显示器10h可以包括液晶显示器(LCD)和或者触摸面板(TP)。如果屏幕包括触摸面板,屏幕可以被实现为触摸屏,以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界,而且还检测与所述触摸或滑动操作相关的持续时间和压力。
相应地,智能设备还可包括图像处理单元10i,用于执行信号处理,比如与从处理器10b输出的图像信号相关的图像质量校正,以及将其分辨率转换为根据显示器10h的屏幕的分辨率。然后,显示驱动单元10j依次选择显示器10h的每行像素,并逐行依次扫描显示器10h的每行像素,因而提供基于经信号处理的图像信号的像素信号。
需要说明的是,图10中仅示意性给出部分组件,并不意味着智能设备必须包含图10所示全部组件,也不意味着智能设备只能包括图10所示组件。另外,除图10所示组件之外,智能设备还输入操作单元(图10中未示出)。其中,输入操作单元包括至少一个用来执行输入操作的操作部件,例如按键、按钮、开关或者其他具有类似功能的部件,通过操作部件接收用户指令,并且向处理器10b输出指令。
本实施例提供的智能设备,对其在使用过程中产生的多个运动方向上的加速度信息进行特征分析,获取智能设备的使用对象的加速度特征,并根据使用对象的加速度特征,确定出智能设备的使用对象。这样,在识别出智能设备的使用对象之后,可采用与该使用对象匹配的方式对其进行计步或定位,有助于提高计步或定位的精度。
需要说明的是,本文中的“第一”、“第二”等描述,是用于区分不同的消息、设备、模块等,不代表先后顺序,也不限定“第一”和“第二”是不同的类型。
本领域内的技术人员应明白,本发明的实施例可提供为方法、系统、或计算机程序产品。因此,本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框 图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中,计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。按照本文中的界定,计算机可读介质不包括暂存电脑可读媒体(transitory media),如调制的数据信号和载波。
还需要说明的是,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。

Claims (11)

  1. 一种使用对象确定方法,其特征在于,包括:
    获取智能设备在使用过程中产生的多个运动方向上的加速度信息;
    对所述多个运动方向上的加速度信息进行特征分析,获取所述智能设备的使用对象的至少一个加速度特征;
    根据所述使用对象的至少一个加速度特征,确定出所述智能设备的使用对象。
  2. 根据权利要求1所述的方法,其特征在于,所述对所述多个运动方向上的加速度信息进行分析,获取所述智能设备的使用对象的至少一个加速度特征,包括:
    对所述多个运动方向上的加速度信息进行特征分析,得到所述智能设备的使用对象的合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种;
    其中,所述智能设备的使用对象的合加速度是指所述多个运动方向上的加速度信息的矢量和。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述使用对象至少一个加速度特征,确定出所述智能设备的使用对象,包括:
    根据所述智能设备的使用对象的合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种,确定出所述智能设备的使用对象。
  4. 根据权利要求3所述的方法,其特征在于,所述根据所述智能设备的使用对象的合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种,确定出所述智能设备的使用对象,包括:
    计算所述合加速度的波峰间隔的平均值;
    若所述合加速度的波峰间隔的平均值小于或等于预设的间隔阈值,则确定所述智能设备的使用对象为第一类动物。
  5. 根据权利要求4所述的方法,其特征在于,若所述合加速度的波峰间隔的平均值大于预设的间隔阈值,所述根据所述合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种,确定出所述智能设备的使用对象,还包括:
    计算所述合加速度的峰值波动平均值;
    若所述合加速度的峰值波动平均值大于或等于预设的波动阈值,则确定所述智能设备的使用对象为第二类动物。
  6. 根据权利要求5所述的方法,其特征在于,若所述合加速度的峰值波动平均值小于预设的波动阈值,所述根据所述合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种,确定出所述智能设备的使用对象,还包括:
    对所述合加速度进行小波分析,获取所述智能设备的使用对象的合加速度的时频信息;
    若所述使用对象的合加速度的频率的峰值大于或等于预设的频率峰值阈值,则确定所述智能设备的使用对象为人类。
  7. 根据权利要求6所述的方法,其特征在于,若所述使用对象的合加速度的峰值小于预设的频率峰值阈值,所述根据所述合加速度的波峰间隔特征、峰值波动特征、时频特征以及加速度的混乱度特征中的至少一种,确定出所述智能设备的使用对象,还包括:
    计算所述智能设备的使用对象的加速度的混乱度;
    若所述使用对象的加速度的混乱度在设定的混乱度范围内,确定所述智能设备的使用对象为人类。
  8. 根据权利要求7所述的方法,其特征在于,所述计算所述智能设备的使用对象的加速度的混乱度,包括:
    利用所述智能设备的使用对象分别在x轴、y轴和z轴上的加速度,计算每两个坐标轴上的加速度的比值分布;
    根据所述每两个坐标轴上的加速度的比值分布,分别计算每两个坐标轴的加速度的比值的峰值平均变化率,并将每个峰值平均变化率作为对应的两个坐标轴上的加速度的混乱度。
  9. 根据权利要求1-8任一项所述的方法,其特征在于,还包括:
    若确定所述智能设备的使用对象为人类,则在预设的报警时间到达时,向所述使用对象发出携带有所述智能设备的提示信息;或者,
    若确定所述智能设备的使用对象为人类,则在每个预警周期到达时,向所述使用对象发出携带有所述智能设备的提示信息。
  10. 一种智能设备,其特征在于,包括:加速度传感器、存储器和处理器;其中,所述加速度传感器用于采集所述智能设备在使用过程中产生的多个运动方向上的加速度信息;
    所述存储器,用于存储计算机程序;
    所述处理器耦合至所述存储器,用于执行所述计算机程序以用于:
    对所述多个运动方向上的加速度信息进行特征分析,获取所述智能设备的使用对象的至少一个加速度特征;
    根据所述使用对象的至少一个加速度特征,确定出所述智能设备的使用对象。
  11. 一种存储有计算机指令的计算机可读存储介质,其特征在于,当所述计算机指令被一个或多个处理器执行时,致使所述一个或多个处理器执行权利要求1-9任一项所述方法中的步骤。
PCT/CN2019/129571 2019-04-15 2019-12-28 使用对象确定方法、设备及存储介质 Ceased WO2020211459A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910301115.7 2019-04-15
CN201910301115.7A CN110017834B (zh) 2019-04-15 2019-04-15 使用对象确定方法、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2020211459A1 true WO2020211459A1 (zh) 2020-10-22

Family

ID=67191368

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/129571 Ceased WO2020211459A1 (zh) 2019-04-15 2019-12-28 使用对象确定方法、设备及存储介质

Country Status (2)

Country Link
CN (1) CN110017834B (zh)
WO (1) WO2020211459A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116229576A (zh) * 2023-03-13 2023-06-06 北京数感科技有限公司 着地动作类型的确定方法、装置、终端及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110017834B (zh) * 2019-04-15 2021-12-24 歌尔科技有限公司 使用对象确定方法、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107831907A (zh) * 2017-12-07 2018-03-23 深圳先进技术研究院 基于步态识别的身份认证方法及装置
CN108182004A (zh) * 2018-01-19 2018-06-19 百度在线网络技术(北京)有限公司 用于识别承载移动终端的载体的行为模式的方法和装置
US10075846B1 (en) * 2017-08-10 2018-09-11 The Florida International University Board Of Trustees Method for continuous user authentication with wearables
CN108847941A (zh) * 2018-05-31 2018-11-20 上海众人网络安全技术有限公司 身份认证方法、装置、终端及存储介质
CN108932504A (zh) * 2018-07-24 2018-12-04 中国科学院深圳先进技术研究院 身份认证方法、装置、电子设备及存储介质
CN110017834A (zh) * 2019-04-15 2019-07-16 歌尔科技有限公司 使用对象确定方法、设备及存储介质

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10164534A1 (de) * 2001-12-31 2003-07-10 Dirk Parchmann Einrichtung und Verfahren zur Bestimmung von Kenngrößen der Bewegung eines Körpers
US8954251B2 (en) * 2004-10-05 2015-02-10 Vision Works Ip Corporation Absolute acceleration sensor for use within moving vehicles
CN102193633B (zh) * 2011-05-25 2012-12-12 广州畅途软件有限公司 一种数据手套动态手语识别方法
CN103445792B (zh) * 2011-12-31 2017-05-03 北京超思电子技术有限责任公司 计步方法
CN103310192B (zh) * 2013-06-06 2016-05-11 南京邮电大学 一种基于单轴加速度传感器的运动行为识别方法
CN103458051A (zh) * 2013-09-16 2013-12-18 南京大学 体感网及基于体感网的居家行为感知方法
CN104021295B (zh) * 2014-06-12 2017-06-06 广州三星通信技术研究有限公司 用于运动识别的聚类特征融合方法和装置
CN104200234B (zh) * 2014-07-11 2018-10-16 杭州微纳科技股份有限公司 人体动作建模和识别方法
CN104111733B (zh) * 2014-07-29 2017-03-08 上海交通大学 一种手势识别系统及方法
JP2016080620A (ja) * 2014-10-21 2016-05-16 アズビル株式会社 人検知システムおよび方法
CN104991644B (zh) * 2015-06-24 2018-09-04 小米科技有限责任公司 确定移动终端使用对象的方法和装置
CN106339071A (zh) * 2015-07-08 2017-01-18 中兴通讯股份有限公司 一种行为识别方法及设备
CN106618584B (zh) * 2015-11-10 2019-11-22 北京纳通科技集团有限公司 一种用于监测用户下肢运动的方法
CN105589383A (zh) * 2016-01-05 2016-05-18 金陵科技学院 跟踪型用于宠物穿戴的智能设备及其控制方法
CN105806359A (zh) * 2016-05-17 2016-07-27 深圳市纬科联通讯有限公司 一种计步方法及计步器
CN106570479B (zh) * 2016-10-28 2019-06-18 华南理工大学 一种面向嵌入式平台的宠物运动识别方法
CN106643722A (zh) * 2016-10-28 2017-05-10 华南理工大学 一种基于三轴加速度计的宠物运动识别方法
CN107016384A (zh) * 2017-06-05 2017-08-04 深圳天珑无线科技有限公司 可识别运动类型的计步方法、移动终端及存储介质
CN109166275B (zh) * 2018-09-25 2020-08-11 山东科技大学 一种基于加速度传感器的人体跌倒检测方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10075846B1 (en) * 2017-08-10 2018-09-11 The Florida International University Board Of Trustees Method for continuous user authentication with wearables
CN107831907A (zh) * 2017-12-07 2018-03-23 深圳先进技术研究院 基于步态识别的身份认证方法及装置
CN108182004A (zh) * 2018-01-19 2018-06-19 百度在线网络技术(北京)有限公司 用于识别承载移动终端的载体的行为模式的方法和装置
CN108847941A (zh) * 2018-05-31 2018-11-20 上海众人网络安全技术有限公司 身份认证方法、装置、终端及存储介质
CN108932504A (zh) * 2018-07-24 2018-12-04 中国科学院深圳先进技术研究院 身份认证方法、装置、电子设备及存储介质
CN110017834A (zh) * 2019-04-15 2019-07-16 歌尔科技有限公司 使用对象确定方法、设备及存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116229576A (zh) * 2023-03-13 2023-06-06 北京数感科技有限公司 着地动作类型的确定方法、装置、终端及存储介质

Also Published As

Publication number Publication date
CN110017834B (zh) 2021-12-24
CN110017834A (zh) 2019-07-16

Similar Documents

Publication Publication Date Title
US11288514B2 (en) Video processing method and device, and storage medium
AU2016200905B2 (en) A system and method for identifying and analyzing personal context of a user
CN114816610B (zh) 一种页面分类方法、页面分类装置和终端设备
CN108960209A (zh) 身份识别方法、装置及计算机可读存储介质
CN110495819A (zh) 机器人的控制方法、机器人、终端、服务器及控制系统
Ma et al. Medhere: A smartwatch-based medication adherence monitoring system using machine learning and distributed computing
CN112826514A (zh) 一种房颤信号的分类方法、装置、终端以及存储介质
CN104123741A (zh) 生成人脸素描的方法和装置
WO2020211459A1 (zh) 使用对象确定方法、设备及存储介质
Zheng et al. Missile: A system of mobile inertial sensor-based sensitive indoor location eavesdropping
JP2017538976A (ja) タッチジェスチャ特定方法および装置
Alanezi et al. Design, implementation and evaluation of a smartphone position discovery service for accurate context sensing
CN110210045A (zh) 目标区域的人数估算方法、装置及存储介质
CN113762585A (zh) 数据的处理方法、账号类型的识别方法及装置
CN104157168A (zh) 一种应用于人工智能机器人的智能数据库应用系统及交互方法
US20150341483A1 (en) User Mode Estimation on Mobile Device
Kloch et al. Collaborative PDR localisation with mobile phones
Cardone et al. Activity recognition for smart city scenarios: Google play services vs. MoST facilities
Ren Multiple tree model integration for transportation mode recognition
Aarthi et al. Intelligent fall detection system based on sensor and image data for elderly monitoring
CN109284783A (zh) 基于机器学习的大礼拜计数方法、装置、用户设备及介质
Rajanidi et al. Towards Real-Time Human Activity Recognition: A Machine Learning Perspective
CN113761989A (zh) 行为监控方法、装置、计算机及可读存储介质
Cao et al. Towards activity recognition through multidimensional mobile data fusion with a smartphone and deep learning
Han et al. Shad: privacy-friendly shared activity detection and data sharing

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: 19925174

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: 19925174

Country of ref document: EP

Kind code of ref document: A1