WO2019015556A1 - 终端运动状态分析方法、移动终端及可读存储介质 - Google Patents

终端运动状态分析方法、移动终端及可读存储介质 Download PDF

Info

Publication number
WO2019015556A1
WO2019015556A1 PCT/CN2018/095858 CN2018095858W WO2019015556A1 WO 2019015556 A1 WO2019015556 A1 WO 2019015556A1 CN 2018095858 W CN2018095858 W CN 2018095858W WO 2019015556 A1 WO2019015556 A1 WO 2019015556A1
Authority
WO
WIPO (PCT)
Prior art keywords
motion
terminal
data
state
acceleration
Prior art date
Application number
PCT/CN2018/095858
Other languages
English (en)
French (fr)
Inventor
郭玮强
李毅聪
马浩
邹力
锺春号
Original Assignee
前海随身宝（深圳）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 前海随身宝（深圳）科技有限公司 filed Critical 前海随身宝（深圳）科技有限公司
Publication of WO2019015556A1 publication Critical patent/WO2019015556A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass

Definitions

  • the present invention relates to the field of communications, and in particular, to a terminal motion state analysis method, a mobile terminal, and a readable storage medium.
  • the main object of the present invention is to provide a method for analyzing a state of motion of a terminal, which aims to solve the problem that the motion state of the terminal cannot be accurately determined when the motion sensor of the low price is judged.
  • the present invention provides a terminal motion state analysis method, and the terminal motion state analysis method includes the following steps:
  • the motion state of the terminal is determined according to the comparison state of the acceleration standard deviation and the back noise value and the duration corresponding to the comparison state.
  • the step of pre-processing the motion data to obtain valid motion data includes:
  • the collected motion data is separately and once differentiated. If the absolute value of the differential result is greater than the preset maximum effective value, it is determined that the collected motion data is invalid data: if the absolute value of the differential result is less than or equal to the preset The maximum effective value determines that the collected motion data is valid data:
  • Each vector data in the valid data is converted into scalar data by a preset conversion method, and the scalar data is used as effective motion data.
  • the step of converting each vector data in the valid data into scalar data by using a preset conversion method, and using the scalar data as the effective motion data further includes:
  • the acceleration is less than the preset minimum threshold after being greater than the preset maximum value, it is determined that the motion state of the terminal is an emergency event state.
  • the step of obtaining the acceleration standard deviation of the terminal in the effective motion effect data, and calculating the back noise value of the terminal by the acceleration standard deviation includes:
  • the current time back noise value is obtained by multiplying the back noise value of the previous time and the subtracted transition coefficient by the product of the acceleration standard deviation and the transition coefficient, wherein the transition coefficient determines the influence of the acceleration standard deviation on the current time back noise value, wherein
  • the initial back noise value is a preset value.
  • the step of the current time back noise value obtained by multiplying the back noise value of the previous time and the subtracted transition coefficient by the product of the acceleration standard deviation and the transition coefficient comprises:
  • the BackgroundNoise old is the unupdated back noise value, the initial value is 0.1; StdDev(acc) is the standard deviation of the acceleration, k is the transition coefficient of the back noise value, the initial value is 0.05, and the value range is [O, l], BackgroundNoise new is the updated back noise value.
  • the step of determining the motion state of the terminal according to the comparison state of the acceleration standard deviation and the back noise value and the duration corresponding to the comparison state includes:
  • the terminal movement state After determining that the terminal is in the moving state, if the comparison state of the acceleration standard deviation and the back noise value satisfies the preset end threshold value, and the duration of the end threshold value is greater than the preset end threshold time, it is determined that the terminal movement state ends.
  • the method further includes:
  • the current terminal After determining that the current state of motion is satisfied, if the comparison state of the acceleration standard deviation and the back noise value satisfies the preset artificial motion threshold value, and the duration of the artificial motion threshold value is greater than the preset artificial motion critical time, the current terminal is determined. The state of motion is artificially taken away.
  • the comparison state of the acceleration standard deviation and the back noise value meets a preset movement threshold value:
  • the comparison state of the acceleration standard deviation and the back noise value satisfies a preset artificial motion threshold value, and the duration of the artificial motion threshold value is greater than the preset artificial motion critical time:
  • StdDev(acc) is the standard deviation of acceleration
  • BackgroundNoise is the calculated back noise value
  • n1, n2, and n3 are comparison coefficients
  • the magnitude relationship is n3>n2>n1
  • min.threshold movement is the preset minimum moving threshold.
  • Time movement is the duration.
  • the present invention further provides a mobile terminal, the mobile terminal comprising: a memory, a processor, and a terminal motion state analysis program stored on the memory and operable on the processor, The steps of the terminal motion state analysis method as described above are implemented when the terminal motion state analysis program is executed by the processor.
  • the present invention further provides a computer readable storage medium, where the terminal motion state analysis program is stored, and the terminal motion state analysis program is implemented by the processor as described above. The steps of the terminal motion state analysis method.
  • motion data is collected by a relatively inexpensive three-axis sensor, and the effective data in the motion data is refined through filtering in multiple steps. Moreover, the motion data in the dynamic background can be processed, thereby eliminating the negative influence of the motion of the dynamic background on the operation result, and the calculation accuracy of the terminal is greatly improved. Achieving the need to accurately determine the state of motion of the terminal at a low cost.
  • FIG. 1 is a schematic structural diagram of a terminal in a hardware operating environment according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a first embodiment of a method for analyzing a motion state of a terminal according to the present invention
  • FIG. 3 is a schematic flow chart of the steps of the S10 in FIG. 2;
  • FIG. 4 is a schematic flow chart of a second embodiment of a method for analyzing a motion state of a terminal according to the present invention.
  • FIG. 5 is a schematic flowchart diagram of a third embodiment of a method for analyzing a motion state of a terminal according to the present invention.
  • FIG. 1 is a schematic structural diagram of a terminal in a hardware operating environment according to an embodiment of the present invention.
  • the terminal of the embodiment of the present invention may be a portable device and a wearable device PC, or may be a smart phone, a tablet computer, an e-book reader, and a MP3 (Moving Picture Experts Group Audio Layer III) player.
  • MP4 Moving Picture Experts Group Audio Layer IV
  • MP3 Motion Picture Experts Group Audio Layer III
  • MP4 is a portable terminal device with a display function such as a player or a portable computer.
  • the terminal may include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002.
  • the communication bus 1002 is used to implement connection communication between these components.
  • the user interface 1003 can include a display, an input unit such as a keyboard, and the optional user interface 1003 can also include a standard wired interface, a wireless interface.
  • the network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface).
  • the memory 1005 may be a high speed RAM memory or a non-volatile memory such as a disk memory.
  • the memory 1005 can also optionally be a storage device independent of the aforementioned processor 1001.
  • the terminal may further include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a Bluetooth, a WiFi module, and the like.
  • sensors such as light sensors, motion sensors, and other sensors.
  • the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display according to the brightness of the ambient light, and the proximity sensor may turn off the display and/or when the mobile terminal moves to the ear. Backlighting.
  • the gravity acceleration sensor can detect the magnitude of acceleration in each direction (usually three axes), and can detect the magnitude and direction of gravity when stationary, and can be used to identify the posture of the mobile terminal (such as horizontal and vertical screen switching, Related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; of course, the mobile terminal can also be equipped with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc. No longer.
  • terminal structure shown in FIG. 1 does not constitute a limitation to the terminal, and may include more or less components than those illustrated, or a combination of certain components, or different component arrangements.
  • a memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a terminal motion state analysis program.
  • the network interface 1004 is mainly used to connect to the background server and perform data communication with the background server;
  • the user interface 1003 is mainly used to connect the client (user end), and perform data communication with the client;
  • the processor 1001 can be used to call the terminal motion state analysis program stored in the memory 1005 and perform the following operations:
  • the motion state of the terminal is analyzed, and the motion state analysis of the terminal includes the following steps:
  • the motion state of the terminal is determined according to the comparison state of the acceleration standard deviation and the back noise value and the duration corresponding to the comparison state.
  • processor 1001 may call the motion state of the terminal stored in the memory 1005 to analyze the application, and further perform the following operations:
  • the step of pre-processing the motion data to obtain valid motion data includes:
  • the collected motion data is separately and once differentiated. If the absolute value of the differential result is greater than the preset maximum effective value, it is determined that the collected motion data is invalid data; if the absolute value of the differential result is less than or equal to the preset The maximum effective value determines that the collected motion data is valid data:
  • Each vector data in the valid data is converted into scalar data by a preset conversion method, and the scalar data is used as effective motion data.
  • a first embodiment of the present invention provides a terminal motion state analysis method, where the terminal motion state analysis method includes the following steps:
  • Step S1O acquiring motion data collected by a motion sensor of the terminal, and pre-processing the motion data to obtain valid motion data;
  • Step S20 obtaining an acceleration standard deviation of the terminal in the effective motion effect data, and calculating a back noise value of the terminal by the acceleration standard deviation;
  • Step S30 determining the motion state of the terminal according to the comparison state of the acceleration standard deviation and the back noise value and the duration corresponding to the comparison state.
  • the terminal collects the motion information by using the motion sensor, and filters the motion data, and filters invalid data such as erroneous data and emergency event data in the motion data by using a preset filtering algorithm to obtain effective motion data.
  • data After the valid data is obtained, the acceleration in the valid data is obtained, and the standard deviation of the acceleration is calculated. After obtaining the standard deviation of the acceleration, the back noise value of the dynamic environment is calculated according to the corresponding calculation formula.
  • the back noise value is a parameter, which is calculated from the standard deviation of the acceleration according to the back noise value calculation formula, and is used to describe the motion state of the environment. After the back noise value is obtained, the back noise value is compared with the standard deviation of the acceleration, and whether the terminal is in motion state can be determined whether the comparison relationship between the two meets the preset correspondence relationship.
  • the motion sensor collects motion data
  • some of the data is more or less invalid data for various reasons.
  • the quality, environment, design and other factors of the motion sensor chip may cause invalid data in the output motion data.
  • Well-designed, sensitive sports high-quality sensors are expensive, and the use of expensive motion sensors in the civilian sector leads to a significant increase in costs and an increase in the price of the final product, which is not beneficial to both the enterprise and the user. Case.
  • the back noise value is calculated based on the standard deviation of the acceleration.
  • the back noise value is the amount used to describe the motion in the current dynamic environment. For example, in the subway, the subway itself is sporty, and the terminal will have the same movement as the subway on the subway. Although the motion data brought by the subway motion is not invalid data, the motion data brought by the subway is not the motion of the terminal itself. Therefore, when calculating and analyzing the motion state of the terminal, the motion data brought by the motion of the dynamic environment such as the subway will Influencing and interfering with the conclusions reached.
  • the back noise value changes as the acceleration changes. Because the motion of the dynamic environment is also changing, the acceleration caused by it also changes, so the back noise value needs to be updated in real time, so as to more accurately describe the motion data of the dynamic environment.
  • the back noise value of the current dynamic environment is calculated from the standard deviation of the acceleration.
  • the back noise value is the amount describing the current environmental motion data. For example, in the subway environment, the back noise value describes the motion of the subway.
  • the acceleration standard deviation is compared with the back noise value, and the motion state of the terminal is judged according to the comparison relationship between the two.
  • the comparison relationship between the two conditions satisfies the condition of the terminal movement, it is determined that the terminal is in the moving state, and when the motion state duration of the terminal satisfies the determination of the continuous movement (in the duration, if the stop condition is satisfied, the subsequent judgment is terminated, and the determination is made.
  • the terminal movement has been stopped), and whether the comparison relationship between the acceleration standard deviation and the back noise value satisfies the comparison relationship of the artificial motion (because the invention is mainly used in the anti-theft field, the human movement refers to the human being to steal and take away), if When the two satisfy the comparison relationship of the artificial motion, it is determined that the terminal is artificially moved.
  • the invention collects the motion data of the terminal through the motion sensor installed in the terminal, analyzes and filters the data through the main control chip, and achieves the purpose of judging the motion state of the terminal, thereby realizing the function of theft prevention of the terminal.
  • a relatively inexpensive sensor such as a three-axis sensor can be used without using an expensive and precise motion sensor such as a six-axis sensor, thereby greatly reducing the manufacturing cost of the terminal.
  • the present invention performs multiple filtering processing on the motion data collected by the motion sensor by the algorithm, and the data caused by the hardware problem, the instantaneous large-scale change data of the sudden situation, and the like.
  • the present invention can filter motion data in a dynamic environment by an algorithm to eliminate adverse effects of environmental factors on analysis and judgment.
  • the invention adopts a low-cost motion sensor, so the manufacturing cost is low, and the invalid data is removed by filtering multiple motion data, the adverse effects brought by the low-cost sensor are eliminated, and the accurate judgment can be made in the dynamic environment. The accuracy of the judgment and the user experience when the user is using.
  • the step of pre-processing the motion data in step S10 to obtain valid motion data includes:
  • Step S11 performing the first and second differentiation on the collected motion data respectively. If the absolute value of the differential result is greater than the preset maximum effective value, determining that the collected motion data is invalid data; if the absolute value of the differential result is less than or equal to The preset maximum effective value determines that the collected motion data is valid data:
  • Step S12 converting each vector data in the valid data into scalar data by using a preset conversion method, and using the scalar data as effective motion data.
  • the acceleration in the motion data is first differentiated, and the acceleration changes with time.
  • the acceleration of human motion referring to the motion caused by the body itself without using external force and equipment
  • the limit of the acceleration variation with time is defined as the theoretical maximum.
  • the change of the acceleration with time is greater than the theoretical maximum value, it means that the acceleration change is abnormal or non-human, so that all the data exceeding the theoretical maximum value of the acceleration over time is determined as invalid data.
  • the second differential of acceleration is continued, and the second differential is used to prevent data overflow.
  • the invention filters the data through the human limit of the motion data, the storage rule of the device, filters the invalid data collected by the motion sensor to obtain valid data, and then uses the simple conversion to move the motion data in all directions in the effective data. From vector to scalar, effective motion data is obtained, and effective motion data can greatly simplify subsequent calculation and analysis and obtain higher accuracy.
  • step S12 the method further includes:
  • Step S13 when it is detected that the acceleration in the effective motion data is greater than a preset maximum threshold, detecting whether the acceleration is less than a preset minimum threshold after being greater than the preset maximum value:
  • step S14 if the acceleration is less than the preset minimum threshold after being greater than the preset maximum value, it is determined that the motion state of the terminal is an emergency event state.
  • the motion data of the unexpected situation is not invalid data, but it has the effect of interference for the final analysis and calculation, so it is necessary to make an emergency.
  • the motion data is filtered. Sudden events such as sudden accidental falling of an object, being in a vehicle, sudden sudden braking or rapid acceleration of the vehicle, and the like.
  • the characteristics of emergencies in the motion data are: the acceleration changes in two very short periods of time and very large changes. In short, it is detected that the acceleration suddenly increases and reaches a very large value (greater than the pre- Set the maximum value), then the acceleration becomes a very large value in the opposite direction (less than the preset minimum).
  • the motion law of the effective motion data is consistent with the law of the sudden motion, so that the motion state of the terminal at this time is determined to be a sudden motion.
  • the present invention will filter the case where the motion data caused by the unexpected situation fluctuates greatly.
  • the terminal motion caused by the sudden situation has obvious characteristics of the motion data, and the analysis of such motion data does not bring benefits to the purpose of the terminal for theft prevention, etc., so the motion data of such sudden motion motion is Filtering further simplifies the subsequent calculations and analysis steps.
  • the movement characteristics of the emergency have certain similarities with the characteristics of the human movement, the meaning is different (the artificial possibility is that the sudden movement is not the risk of theft before being stolen), so the movement of the sudden movement Data filtering can improve the accuracy of judging the state of motion of the terminal.
  • the step of acquiring the acceleration standard deviation of the terminal in the effective motion effect data, and calculating the back noise value of the terminal by the acceleration standard deviation includes:
  • Step S21 the current time back noise value is obtained by multiplying the back noise value of the previous time plus the product standard deviation of the acceleration and the subtracted transition coefficient and the transition coefficient, wherein the transition coefficient determines the acceleration standard deviation to the current time back noise value. Effect, where the initial back noise value is the preset value.
  • the back noise value changes according to the motion data of the dynamic environment, and the date of updating the current dynamic environment back noise value in real time has been reached.
  • the influence of the acceleration standard deviation on the current time back noise value is determined by the transition coefficient, wherein the acceleration standard deviation refers to the acceleration standard deviation at the current time.
  • the back noise value is calculated from the standard deviation of the acceleration obtained in the effective motion data.
  • the back noise value is an amount used to describe the motion state of the dynamic environment, and the back noise value is also updated in real time to adapt to the change of the motion state of the dynamic environment, ensuring that the back noise value can accurately perform the motion state of the dynamic environment. description.
  • the back noise value will form a new baseline with the initial baseline.
  • the baseline is a scale parameter or mark in the calculation, and in the present invention, the initial baseline for judging the motion state of the terminal is a stationary state, that is, the baseline is at a stationary state, but in the actual calculation, when in a dynamic environment, the dynamic environment
  • the motion data is collected by the motion sensor of the terminal, causing interference in the calculation.
  • Adding the back noise value to the baseline solves this problem by adding motion data from the dynamic environment to the baseline, depending on the dynamic environment. By calculating the back noise value of the dynamic environment, the error of the motion data detected in the dynamic environment is solved, and the accuracy of the analysis of the motion state of the terminal is improved.
  • step S21 includes:
  • Step S211 calculating a back noise value of the terminal according to the following formula, where the formula is:
  • the BackgroundNoise old is the unupdated back noise value, the initial value is 0.1; StdDev(acc) is the standard deviation of the acceleration, k is the transition coefficient of the back noise value, the initial value is 0.05, and the value range is [O, l], BackgroundNoise new is the updated back noise value.
  • the calculation formula of the back noise value is as shown above, wherein BackgroundNoise old is an unupdated back noise value, and the initial value is 0.05 (ie, the environment is a stationary state).
  • StdDev(acc) is the standard deviation of acceleration, and the acceleration is obtained from the effective motion data.
  • the transition coefficient k is used to determine the transition relationship between the current environment dynamic environment and the dynamic environment of the past time. When k is the minimum value, the current environmental back noise value is the same as the past time noise value; and when k takes the maximum value, the current time
  • the back noise value has the least dependence on the back noise value in the past, which can be understood as the current back noise value as a new back noise value.
  • the value of k is related to the comparison of the back noise value and the effective motion data.
  • the transition coefficient k enables the back noise value to transition from the old environment to the new environment more smoothly when the environment changes.
  • the step of determining the motion state of the terminal according to the comparison state of the acceleration standard deviation and the back noise value and the duration corresponding to the comparison state includes:
  • Step S31 when it is detected that the comparison state of the acceleration standard deviation and the back noise value meets the preset movement threshold, it is determined that the terminal is currently in the moving state;
  • Step S311 after determining that the terminal is in the moving state, if the comparison state of the acceleration standard deviation and the back noise value satisfies the preset end threshold value, and the duration of the end threshold value is greater than the preset end critical time, determining the terminal movement state End.
  • the comparison relationship between the acceleration standard deviation and the back noise value is greater than the preset movement threshold, it is determined whether the terminal is in a moving state, and the moving state indicates that the terminal currently has a significant displacement. After determining that the terminal is in the moving state, the mobile state is continuously monitored. When the comparison between the acceleration standard deviation and the back noise value is less than the preset end threshold, that is, the end condition is satisfied, it is determined that the mobile state of the terminal ends.
  • the motion state of the terminal it is first determined whether the terminal is in a moving state. After determining that the terminal is in the mobile terminal, it is specifically determined whether the current motion is an artificially taken away motion. Therefore, a certain acceleration or speed condition is satisfied, and it is determined that the terminal is in a moving state. However, if the mobile terminal has a very short duration (less than a preset time) in the moving state or the motion data such as acceleration rapidly decreases (the comparison between the acceleration standard deviation and the back noise value is less than the preset end threshold), then It indicates that the terminal has made a short and small displacement, and the tiny displacement does not match the characteristics of the artificial take-off movement. Therefore, the motion whose duration is less than the critical time of motion is not the movement taken by man.
  • the motion state of the terminal is judged by the comparison relationship between the acceleration standard deviation and the back noise value, and the minute motion that does not satisfy the artificial motion condition can be excluded, the operation is simple, and the result accuracy is high. Further, referring to FIG. 5, after step S31, the method further includes:
  • Step S312 after determining that the current state of being moved, if the comparison state of the acceleration standard deviation and the back noise value satisfies the preset artificial motion threshold value, and the duration of the artificial motion threshold value is greater than the preset artificial motion critical time, then determining The current state of motion of the terminal is artificially taken away.
  • the terminal After the terminal maintains the moving state, it is determined whether the motion of the terminal is caused by the human motion.
  • the laws of human movement when walking or running, the movement has obvious laws (for example, when walking, the acceleration of the foot is higher when the step is raised, and the acceleration is smaller when the foot is stepping down. Therefore, the acceleration is also uniformly changed) and is continued.
  • the characteristics of human motion it is judged whether the terminal is in the motion state of artificial motion by comparing the standard deviation of acceleration with the value of back noise.
  • the terminal satisfies the motion state of the human motion, detecting the duration of the state of the human motion, and if the duration also satisfies the preset condition (greater than the motion critical time), determining that the current motion state of the terminal is artificial motion status.
  • the main purpose of the present invention is for theft prevention of the terminal, so the detection of the motion state of the terminal is also based on the characteristics of theft, and it is judged whether it is moved (his stolen) ⁇ judging whether it is a human movement (the criminals carrying the terminal after theft escape) . Therefore, after being in a moving state, it is necessary to detect whether or not to perform an artificial exercise. It is still judged by the comparison between the standard deviation of the acceleration and the back noise value. When the comparison relationship between the two is greater than the artificial motion threshold and the duration of the artificial motion threshold is greater than the preset artificial motion critical time, the terminal motion state is artificial. Movement state.
  • the standard state of the acceleration can be used to judge the motion state of the terminal, and the principle is simple and the work efficiency is high.
  • the comparison state of the acceleration standard deviation and the back noise value satisfies a preset artificial motion threshold value, and the duration of the artificial motion threshold value is greater than the preset artificial motion critical time:
  • StdDev(acc) is the standard deviation of acceleration
  • BackgroundNoise is the calculated back noise value
  • n1, n2, and n3 are comparison coefficients
  • the magnitude relationship is n3>n2>n1
  • min.threshold movement is the preset minimum moving threshold.
  • Time movement is the duration.
  • the acceleration standard deviation is greater than the movement threshold (composed of the product of the comparison coefficient n1 and the back noise value) and is greater than the lowest movement threshold to determine the movement, wherein the comparison coefficient n1 is preset
  • the initial value is 3; when it is judged whether the moving state is over, the acceleration standard deviation is smaller than the ending critical value (composed of the product of the comparison coefficient n2 and the back noise value) and is greater than the lowest moving threshold to determine the movement, wherein the comparison coefficient n2 is preset
  • the initial value is 1.5; when judging whether the terminal is in the artificial motion state, the artificial standard value of the acceleration standard deviation is greater than the artificial motion threshold (composed of the product of the comparison coefficient n3 and the back noise value) and the duration of the comparison relationship is more than 3 seconds, wherein
  • the comparison coefficient n3 presets an initial value of 4.
  • N1, n2, and n3 can be adjusted according to the actual situation of the terminal and the environment to adapt to various situations.
  • the conditions required for the conclusion are very simple (only need to obtain motion data), and the operation is fast (the formula is simple, no complicated operation). Therefore, the motion state of the terminal can be quickly detected, which has great significance for the use of theft prevention and the like.
  • an embodiment of the present invention further provides a computer readable storage medium, where the terminal readable state analysis program is stored, and when the terminal motion state analysis program is executed by the processor, the following operations are implemented:
  • the invention also provides a mobile terminal for analyzing terminal motion state.
  • the mobile terminal for analyzing the motion state of the base terminal of the present invention comprises: a memory, a processor, and a terminal motion state analysis program stored on the memory and operable on the processor, wherein the terminal motion state analysis program is processed by the terminal.
  • the terminal motion state analysis method steps as described above are implemented when the device is executed.
  • embodiments of the present invention also provide a computer readable storage medium.
  • the computer readable storage medium of the present invention stores a terminal motion state analysis program, and the terminal motion state analysis program is executed by the processor to implement the steps of the terminal motion state analysis method as described above.
  • portions of the technical solution of the present invention that contribute substantially or to the prior art may be embodied in the form of a software product stored in a storage medium (such as a ROM/RAM as described above). , a disk, an optical disk, including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present invention.
  • a terminal device which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Telephone Function (AREA)

Abstract

本发明公开了一种终端运动状态分析方法、移动终端以及可读存储介质。所述终端运动状态分析方法包括以下步骤：获取终端的运动传感器采集到的运动数据，对所述运动数据进行预处理以得到有效运动数据；获取有效运动效数据中终端的加速度标准差，并由加速度标准差计算得出终端的背噪值；根据加速度标准差和背噪值的比较状态以及比较状态对应的持续时间，确定终端的运动状态。本方法通过简单的硬设备即可精确的判断终端的运动状态，在终端的防盗等领域起到巨大的作用。

Description

终端运动状态分析方法、移动终端及可读存储介质 技术领域
本发明涉及通信领域，尤其涉及一种终端运动状态分析方法、移动终端及可读存储介质。
背景技术
随着运动传感器的发展，人们通过运动传感器可以获取到越来越多以及更加精确相关运动信息数据，并且通过对获取到的运动信息数据进行计算和分析，进而能够获得对应运动状态的信息，由此发展而成的防盗等相关技术也越发成熟。
但是由于能够获取到非常精确的运动信息的传感器，往往价格不芋，从而使得相应的装置和设备的价格也水涨船高。但是由简单的传感器进行运动信息的采集往往只能得到较少的数据，而较少的数据会导致计算结果准确率低等不良结果。
发明内容
本发明的主要目的在于提供一种终端运动状态分析方法，旨在解决通过低价格的运动传感器判断终端运动状态时无法准确判断的问题。
为实现上述目的，本发明提供一种终端运动状态分析方法，所述终端运动状态分析方法包括以下步骤：
获取终端的运动传感器采集到的运动数据，对所述运动数据进行预处理以得到有效运动数据；
获取有效运动效数据中终端的加速度标准差，并由加速度标准差计算得出终端的背噪值；
根据加速度标准差和背噪值的比较状态以及比较状态对应的持续时间，确定终端的运动状态。
可选地，所述对所述运动数据进行预处理以得到有效运动数据的步骤包 括：
对采集到的运动数据分别进行一次和两次微分，若微分结果的绝对值大于预设的最大有效值，则判定采集的运动数据为无效数据：若微分结果的绝对值小于或等于预设的最大有效值，则判定采集的运动数据为有效数据：
将所述有效数据中各矢量数据通过预设转换方法转换成标量数据，将该标量数据作为有效运动数据。
可选地，所述将所述有效数据中各矢量数据通过预设转换方法转换成标量数据，将该标量数据作为有效运动数据的步骤之后还包括：
当检测到有效运动数据中加速度大于预设最大临界值时，则检测在大于预设最大值后加速度是否小于预设最小临界值；
若在大于预设最大值后加速度小于预设最小临界值，则判定终端的运动状态为突发事件状态。
可选地，所述获取有效运动效数据中终端的加速度标准差，并由加速度标准差计算得出终端的背噪值的步骤包括：
当前时刻背噪值由上一时刻的背噪值与一减去过渡系数的乘积加上加速度标准差与过渡系数的乘积得到，其中过渡系数决定加速度标准差对当前时刻背噪值的影响，其中初始背噪值为预设值。
可选地，所述当前时刻背噪值由上一时刻的背噪值与一减去过渡系数的乘积加上加速度标准差与过渡系数的乘积得到的步骤包括：
根据以下公式，计算得出终端的背噪值，其中公式为：
BackgroundNoise new＝BackgroundNoise old*(1-k)+StdDev(acc)*k
其中BackgroundNoise old为未更新的背噪值，初始值为0.1；StdDev(acc)为加速度的标准差，k为背噪值的过渡系数，初始值为0.05，取值范围为[O,l],BackgroundNoise new为更新后的背噪值。
可选地，所述根据加速度标准差和背噪值的比较状态以及比较状态对应的持续时间，确定终端的运动状态的步骤包括：
当检测到加速度标准差与背噪值的比较状态满足预设的移动临界值时，判定终端当前处于移动状态；
当判定终端处于移动状态后，若加速度标准差与背噪值的比较状态满足预设的结束临界值，且满足结束临界值的持续时间大于预设的结束临界时间，则 判定终端移动状态结束。
可选地，所述当判定终端处于移动状态后的步骤之后还包括：
在判定当前处于移动状态后，若加速度标准差与背噪值的比较状态满足预设的人为运动临界值，且满足人为运动临界值的持续时间大于预设人为运动临界时间，则判定终端当前的运动状态为人为带走运动。
可选地，所述加速度标准差与背噪值的比较状态满足预设的移动临界值为：
StdDev(acc)＞n1*BackgroundNoise∧StdDev(acc)＞BackgroundNoise+min.threshold movement
所述加速度标准差与背噪值的比较状态满足预设的结束临界值为：
StdDev(acc)＜n2*BackgroundNoise∨StdDev(acc)＜BackgroundNoise+min.threshold movement
所述加速度标准差与背噪值的比较状态满足预设的人为运动临界值，且满足人为运动临界值的持续时间大于预设人为运动临界时间为：
StdDev(acc)＞n3*BackgroundNoise∧Time movement＞3
其中StdDev(acc)为加速度标准差，BackgroundNoise为计算所得背噪值，n1,n2,n3为比较系数，并且大小关系为n3＞n2＞n1,min.threshold movement为预设的最低移动阔值，Time movement为持续时间。
此外，为实现上述目的，本发明还提供一种移动终端，所述移动终端包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的终端运动状态分析程序，所述终端运动状态分析程序被所述处理器执行时实现如上所述终端运动状态分析方法的步骤。
此外，为实现上述目的，本发明还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有终端运动状态分析程序，所述终端运动状态分析整程序被处理器执行时实现如上所述的终端运动状态分析方法的步骤。
本发明提出的终端运动状态分析方法，通过价格较为便宜的三轴传感器进行运动数据的采集，并且通过多个步骤的过滤，将运动数据中的有效数据进行提炼。并且能够对动态背景中的运动数据进行处理，从而消除了动态背景的运动对运算结果带来的负面影响，进而使得终端的运算准确率大大提高。实现了 以低廉的成本，准确判断终端的运动状态的需求。
附图说明
图1是本发明实施例方案涉及的硬件运行环境的终端结构示意图；
图2为本发明终端运动状态分析方法第一实施例的流程示意图；
图3为图2中SlO的步骤的细化流程示意图；
图4为本发明终端运动状态分析方法第二实施例的流程示意图；
图5为本发明终端运动状态分析方法第三实施例的流程示意图。
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
如图1所示，图1是本发明实施例方案涉及的硬件运行环境的终端结构示意图。
本发明实施例终端可以是便携式设备和可穿戴设备PC，也可以是智能手机、平板电脑、电子书阅读器、MP3(Moving Picture Experts Group Audio LayerⅢ，动态影像专家压缩标准音频层面3)播放器、MP4(Moving Picture ExpertsGroup Audio Layer IV，动态影像专家压缩标准音频层面3)播放器、便携计算机等具有显示功能的可移动式终端设备。
如图1所示，该终端可以包括：处理器1001，例如CPU，网络接口1004，用户接口1003，存储器1005，通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard)，可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器，也可以是稳定的存储器(non-volatile memory)，例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地，终端还可以包括摄像头、RF(Radio Frequency，射频)电路， 传感器、音频电路、蓝牙、WiFi模块等等。其中，传感器比如光传感器、运动传感器以及其他传感器。具体地，光传感器可包括环境光传感器及接近传感器，其中，环境光传感器可根据环境光线的明暗来调节显示屏的亮度，接近传感器可在移动终端移动到耳边时，关闭显示屏和/或背光。作为运动传感器的一种，重力加速度传感器可检测各个方向上(一般为三轴)加速度的大小，静止时可检测出重力的大小及方向，可用于识别移动终端姿态的应用(比如横竖屏切换、相关游戏、磁力计姿态校准)、振动识别相关功能(比如计步器、敲击)等；当然，移动终端还可配置陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
本领域技术人员可以理解，图1中示出的终端结构并不构成对终端的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，作为一种计算机存储介质的存储器1005中可以包括操作***、网络通信模块、用户接口模块以及终端运动状态分析程序。
在图1所示的终端中，网络接口1004主要用于连接后台服务器，与后台服务器进行数据通信；用户接口1003主要用于连接客户端(用户端)，与客户端进行数据通信；而处理器1001可以用于调用存储器1005中存储的终端运动状态分析程序，并执行以下操作：
在运动传感器采集到终端的运动数据时，对终端的运动状态进行分析，所述终端运动状态分析包括以下步骤：
获取终端的运动传感器采集到的运动数据，对所述运动数据进行预处理以得到有效运动数据；
获取有效运动效数据中终端的加速度标准差，并由加速度标准差计算得出终端的背噪值；
根据加速度标准差和背噪值的比较状态以及比较状态对应的持续时间，确定终端的运动状态。
进一步地，处理器1001可以调用存储器1005中存储的终端的运动状态进行分析应用程序，还执行以下操作：
所述对所述运动数据进行预处理以得到有效运动数据的步骤包括：
对采集到的运动数据分别进行一次和两次微分，若微分结果的绝对值大 于预设的最大有效值，则判定采集的运动数据为无效数据；若微分结果的绝对值小于或等于预设的最大有效值，则判定采集的运动数据为有效数据：
将所述有效数据中各矢量数据通过预设转换方法转换成标量数据，将该标量数据作为有效运动数据。
参照图2，本发明第一实施例提供一种终端运动状态分析方法，所述终端运动状态分析方法包括以下步骤：
步骤S1O，获取终端的运动传感器采集到的运动数据，对所述运动数据进行预处理以得到有效运动数据；
步骤S20，获取有效运动效数据中终端的加速度标准差，并由加速度标准差计算得出终端的背噪值；
步骤S30，根据加速度标准差和背噪值的比较状态以及比较状态对应的持续时间，确定终端的运动状态。
具体地，终端通过运动传感器对运动信息进行采集，并且对运动数据进行过滤，通过预设的过滤算法将运动数据中的错误数据、突发事件数据等无效数据进行过滤，得到运动数据中的有效数据。在得到有效数据后，获取有效数据中的加速度，并且计算出加速度的标准差。在得到加速度标准差后，根据对应的计算公式，计算得出动态环境的背噪值。背噪值为一个参数，由加速度的标准差根据背噪值计算公式计算得出，用来描述环境的运动状态。获取到背噪值后，将背噪值与加速度标准差进行比较，通过两者的比较关系是否满足预设的对应关系即可判断终端是否处于运动状态。
在运动传感器采集到运动数据时，其中或多或少的有一些数据是因各种原因导致的无效数据。而导致采集到的数据为无效数据的原因有很多，例如运动传感器芯片的质量、环境、设计等因素，都可能导致输出的运动数据出现无效数据。而设计精良、灵敏的运动高质量传感器则价格昂贵，在民用领域中应用价格昂贵的运动传感器会导致成本大幅度增加，最终产品的价格也随之增高，对于企业和用户而言都不是一个有利的情况。而享受价格较为便宜的运动传感器所带来价格优势时，不可避免的要面对如何从采集到的数据中过滤无效数据，提取有效数据进行后续的应用。
在获取到运动数据中的有效数据后，计算出有效数据中的加速度标准差。根据加速度的标准差计算得出背噪值。背噪值是用以描述当前动态环境中的运 动的量。例如在地铁中，地铁本身是运动的，而终端在地铁上也会具有和地铁一样的运动。虽然地铁运动带来的运动数据并不是无效数据，但是地铁带来的运动数据也不是终端自身的运动，因此在计算与分析终端的运动状态时，地铁等动态环境的运动带来的运动数据会对得出的结论造成影响和干扰。而背噪值会随着加速度变化而变化。因为动态环境的运动也是变化的，所以带来的加速度也随之变化，因此背噪值需要进行实时的更新，从而更准确的对动态环境的运动数据进行描述。
通过公式关系，由加速度标准差计算得出当前动态环境的背噪值，背噪值是描述当前环境运动数据的量，例如在地铁环境中，背噪值则描述地铁的运动。通过将动态环境运动数据加入到计算时的基线中，可以达到消除动态环境对终端运动状态判断的影响(例如在计算体重时，若是已经负重，则需要将负重减去，或者将负重加入到基线才能得到准确的体重数据，而不是从0开始)。将加速度标准差与背噪值进行比较，根据两者的比较关系对终端的运动状态进行判断。在两者的比较关系满足终端移动的条件时，判定终端处于移动状态，并且在终端的运动状态持续时间满足持续移动的判定时(在持续时间内，若是满足停止条件，则结束后续判断，判定终端移动己经停止)，检测加速度标准差与背噪值的比较关系是否满足人为运动的比较关系(因本发明主要用于防盗领域，因此所述人为运动指人为盗取并带走)，若是两者满足了人为运动的比较关系，则判定终端被人为移动。
本发明通过在终端中安装的运动传感器，采集终端的运动数据，在通过主控芯片对数据进行分析以及过滤，达到判断终端的运动状态的目的，从而实现终端的防盗等功能。而本发明在运动传感器的使用上，可以使用价格较为低廉的传感器，例如三轴传感器，而不需要使用六轴传感器等价格昂贵的精确的运动传感器，从而大大降低终端的制造成本。而随之带来的运动数据中的无效数据的问题，本发明通过算法对运动传感器采集到的运动数据进行多重过滤处理，将由于硬件问题导致的数据，突发情况的瞬时大幅度变化数据等无效数据过滤，将传感器带来的劣势进行补缺。并且本发明能够通过算法对动态环境中的运动数据进行过滤，以消除环境因素对分析与判断带来的不良影响。本发明由于使用价格低廉的运动传感器，因此制造成本低，而通过对运动数据多重的过滤去除无效数据，将价格低廉传感器带来的不良影响消除，并且可以在动态 环境中进行准确的判断，增加了判断的准确率以及用户在使用时的用户体验。
进一步地，参照图3，步骤S1O中的对运动数据进行预处理以得到有效运动数据的步骤包括：
步骤S11，对采集到的运动数据分别进行一次和两次微分，若微分结果的绝对值大于预设的最大有效值，则判定采集的运动数据为无效数据；若微分结果的绝对值小于或等于预设的最大有效值，则判定采集的运动数据为有效数据：
步骤S12，将所述有效数据中各矢量数据通过预设转换方法转换成标量数据，将该标量数据作为有效运动数据。
具体地，在运动传感器采集到运动数据后，对运动数据中的加速度进行第一次微分，获得加速度随时间的变化。由于人类体质存在物理极限，即人为运动(指不借助外力和设备仅仅依靠人体自身造成的运动)的加速度存在一个理论最大值，定义加速度随时间变化的极限为此理论最大值。当加速度随时间的变化大于理论最大值时，即代表其加速度变化是不正常或非人为造成的，从而把所有超出加速随时间的理论最大值时的数据判定为无效数据。在第一次微分后继续进行对加速度第二次微分，第二次微分用以防止数据溢出，由于部分运动传感器设计上的问题，其输出数据中bytes数量不足以表达该数值，便会出现数据溢出的情况。例如1byte表达整数数字最大值是127，当需要以1byte去强行表达128时，会得出-128，这种情况则成为数据溢出。发生数据溢出的特点是数据由很大的正(负)值突然一下跳到很大的负(正)值。为了算法能够在有数据溢出问题的运动传感器下正常运行，因此需对溢出的数据进行过滤。
而由于三轴传感器等目前常用的传感器所采集到的运动数据为各个运动方向的数据(三轴传感器为xyz三轴上的运动数据)，而在计算时由于各方向的运动数据的方向性问题，导致计算的复杂化，因此本发明将各方向的运动数据进行转化，利用简单的公式acc x 2+acc y 2+acc z 2＝acc 2即可将具有方向的矢量转化为无方向的标量，使得后续的计算变得简单。
本发明通过运动数据的人类极限，设备的储存规律，对数据进行过滤，将运动传感器采集到的无效数据进行过滤从而得到有效数据，而后又通过简单的转化，将有效数据中各个方向的运动数据由矢量转化为标量，得到有效运动数 据，而有效运动数据可使后续的续计算与分析大幅度简化并且得到的结果准确率更高。
进一步地，参照图3，步骤S12之后还包括：
步骤S13，当检测到有效运动数据中加速度大于预设最大临界值时，则检测在大于预设最大值后加速度是否小于预设最小临界值：
步骤S14，若在大于预设最大值后加速度小于预设最小临界值，则判定终端的运动状态为突发事件状态。
具体地，在使用过程中，除了无效数据外，会有许多意外情况的发生，意外情况的运动数据并不是无效数据，但是对于最终的分析与计算却有干扰的效果，因此需要将突发事件的运动数据进行过滤。突发事件例如物件意外倒下、处于交通工具中时，交通工具的突然急刹车或急加速等等。突发事件在运动数据中体现的特点为：非常短时间之内加速度变化出现两次相反而非常大的变化，简单来说，就是检测到加速度突然增加，并且达到一个非常大的值(大于预设最大值)，然后加速度变成方向相反的一个非常大的值(小于预设最小值)。因此通过对有效运动数据中的加速度的变化量进行检查，当发现变化量大于预设临界值时，则进一步检测加速度在大于预设最大值后加速度是否小于预设最小临界值，若加速度在大于预设最大值后加速度小于预设最小临界值，则该有效运动数据的运动规律与突发运动的规律一致，因此判定终端此时的运动状态为突发运动。
在进行过对溢出以及错误数据的过滤后，本发明将过滤由意外情况引发的运动数据大幅度起伏的情况。突发情况所引起的终端运动，其运动数据的特征明显，并且对此类运动数据进行分析并不会为本发明对于终端防盗等目的带来益处，因此将此类突发运动运动的运动数据进行过滤，进一步简化后续的计算与分析的步骤。同时由于突发事件的运动特征与人为运动的特征有一定相似之处，然而意义却是不同(人为有可能是被盗前，突发运动无被盗窃风险)，因此在将突发运动的运动数据过滤可以提高判断终端运动状态的准确率。
进一步地，参照图4，为本发明第二实施例，所述获取有效运动效数据中终端的加速度标准差，并由加速度标准差计算得出终端的背噪值的步骤包括：
步骤S21，当前时刻背噪值由上一时刻的背噪值加上加速度与一减去过渡 系数的乘积标准差与过渡系数的乘积得到，其中过渡系数决定加速度标准差对当前时刻背噪值的影响，其中初始背噪值为预设值。
具体地，背噪值会随着动态环境的运动数据变化而变化，己达到实时更新当前动态环境背噪值的日的。在计算时，通过过渡系数决定加速度标准差对当前时刻背噪值的影响，其中加速度标准差指的是当前时刻的加速度标准差。
背噪值由有效运动数据中获取的加速度的标准差计算得出。背噪值是用以描述动态环境的运动状态的一个量，而背噪值也会实时进行更新，以适应动态环境的运动状态的变化，确保背噪值能够准确的对动态环境的运动状态进行描述。而在对有效运动数据进行运动状态的计算与分析时，背噪值则会成与初始的基线组成新的基线。
基线是在计算中的一个尺度参数或者标记，而在本发明中判断终端的运动状态的初始基线是静止状态，即处于基线是为静止状态，然而实际计算中在处于动态环境中时，动态环境的运动数据会被终端的运动传感器所采集，对计算造成干扰。而将背噪值加入到基线中，即可解决此问题，即将动态环境的运动数据加入到基线中，视动态环境为静止状态。通过计算动态环境的背噪值，解决了在动态环境中检测到的运动数据的误差问题，提高了对于终端运动状态分析的准确率。
进一步，步骤S21包括：
步骤S211，根据以下公式，计算得出终端的背噪值，其中公式为：
BackgroundNoise new＝BackgroundNoise old*(1-k)+StdDev(acc)*k
其中BackgroundNoise old为未更新的背噪值，初始值为0.1；StdDev(acc)为加速度的标准差，k为背噪值的过渡系数，初始值为0.05，取值范围为[O,l],BackgroundNoise new为更新后的背噪值。
具体地，背噪值的计算公式如上述所示，其中BackgroundNoise old为未更新的背噪值，初始值为0.05(即环境为静止状态)。StdDev(acc)为加速度标准差，加速度由有效运动数据中获取。过渡系数k用以判断当前时刻动态环境与过去时刻的动态环境的过渡关系，k取最小值时，当前环境背噪值与过去时刻时刻背噪值相同；而当k取最大值时，当前时刻背噪值对于过去时刻背噪值的依赖程度最小，可以理解为当前时刻背噪值为一个新的背噪值。k的取值与背噪值和有效运动数据的比较关系有关，过渡系数k使得背噪值能够在环 境变化时，更加平稳的由旧环境过渡到新环境。
进一步地，参照图5，为本发明第三实施例，所述根据加速度标准差和背噪值的比较状态以及比较状态对应的持续时间，确定终端的运动状态的步骤包括：
步骤S31，当检测到加速度标准差与背噪值的比较状态满足预设的移动临界值时，判定终端当前处于移动状态；
步骤S311当判定终端处于移动状态后，若加速度标准差与背噪值的比较状态满足预设的结束临界值，且满足结束临界值的持续时间大于预设的结束临界时间，则判定终端移动状态结束。
具体地，在获取到背噪值后，在加速度标准差与背噪值的比较关系大于预设移动临界值时，判定终端是否处于移动状态，移动状态表明终端当前有明显位移。在判定终端处于移动状态后，继续对移动状态进行监测，当加速度标准差与背噪值的比较关系小于预设结束临界值时，即满足结束条件，则判定终端的移动状态结束。
在判断终端的运动状态时，首先判断终端是否处于移动状态。在判断终端处于移动终端之后再具体判断当前运动是否为人为带走的运动。因此满足一定的加速度或者速度条件，则判定终端处于移动状态。然而若是移动状态的终端在移动状态时持续时间极短(小于预设的时间)或者加速度等运动数据迅速减小(加速度标准差与背噪值的比较关系小于预设的结束临界值)，那么表明终端做了一次短暂、微小的位移，而微小的位移与人为带走运动的特征并不符合，因此持续时间小于运动临界时间的运动并非人为带走的运动。本发明中通过加速度标准差与背噪值的比较关系对终端的运动状态进行判断，并且可以将不满足人为运动条件的微小运动进行排除，运算简单，并且结果准确率高。进一步地，参照图5,步骤S31之后还包括：
步骤S312，在判定当前处于移动状态后，若加速度标准差与背噪值的比较状态满足预设的人为运动临界值，且满足人为运动临界值的持续时间大于预设人为运动临界时间，则判定终端当前的运动状态为人为带走运动。
具体地，在终端保持移动状态后，则判定是否为人为运动造成终端的运动。通过对人类运动规律的观察和研究，在走路或者跑步等运动时，运动均有较为明显的规律(例如走路时，脚在抬起跨步时加速度较大，而脚在落下踏步时加 速度较小，因此加速度也是均匀变化的)，并且是持续进行。根据人为运动的特点，通过加速度标准差与背噪值的比较关系判断终端是否处于人为运动的运动状态。并且在终端满足处于人为运动的运动状态时，对处于人为运动的状态的持续时间进行检测，若是持续时间也满足预设的条件(大于运动临界时间)，则判定终端当前运动状态为人为运动的状态。
本发明的主要目的为用于终端的防盗，所以对于终端运动状态的检测也是基于盗窃的特点，判断是否被移动(被人盗取)→判断是否为人运动(盗取后不法分子携带终端逃离)。因此在处于移动状态后，需要检测是否进行人为运动。依旧通过加速度的标准差与背噪值的比较关系进行判断，在两者比较关系大于人为运动临界值时并且满足人为运动临界值的持续时间大于预设人为运动临界时间，则终端运动状态为人为运动状态。通过加速度的标准差即可对终端的运动状态进行判断，原理简单并且工作效率高。
进一步地，所述加速度标准差与背噪值的比较状态满足预设的移动临界值为：
StdDev(acc)＞n1*BackgroundNoise∧StdDev(acc)＞BackgroundNoise+min.threshold movement
所述加速度标准差与背噪值的比较状态满足预设的结束临界值为：
StdDev(acc)＜n2*BackgroundNoise∨StdDev(acc)＜BackgroundNoise+min.threshold movement
所述加速度标准差与背噪值的比较状态满足预设的人为运动临界值，且满足人为运动临界值的持续时间大于预设人为运动临界时间为：
StdDev(acc)＞n3*BackgroundNoise∧Time movement＞3
其中StdDev(acc)为加速度标准差，BackgroundNoise为计算所得背噪值，n1,n2,n3为比较系数，并且大小关系为n3＞n2＞n1,min.threshold movement为预设的最低移动阔值，Time movement为持续时间。
具体地，在判断终端是否处于移动的公式中，加速度标准差大于移动临界值(由比较系数n1与背噪值的乘积组成)并且大于最低的移动阙值则判定移动，其中比较系数n1预设初始值为3；在判断移动状态是否结束时，加速度标准差小于结束临界值(由比较系数n2与背噪值的乘积组成)并且大于最低的移动阔值则判定移动，其中比较系数n2预设初始值为1.5；在判断终端是 否处于人为运动状态时，加速度标准差大于的人为运动临界值(由比较系数n3与背噪值的乘积组成)并且同时满足比较关系的持续时间大于3秒，其中比较系数n3预设初始值为4。n1,n2,n3可根据终端与环境的实际情况进行调整，以适应各种不同的情况。通过加速度标准差与背噪值的比较状态，对于得出结论所需的条件非常简单(仅需要获取运动数据)，运算快(公式简沽，无复杂运算)。因此可快速的检测出终端的运动状态，对于防盗等用途具有很大的意义。
此外，本发明实施例还提出一种计算机可读存储介质，所述计算机可读存储介质上存储有终端运动状态分析程序，所述终端运动状态分析程序被处理器执行时实现如下操作：
本发明还提供一种终端运动状态分析的移动终端。
本发明基终端运动状态分析的移动终端包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的终端运动状态分析程序，所述终端运动状态分析程序被所述处理器执行时实现如上所述的终端运动状态分析方法步骤。
其中，在所述处理器上运行的提示信息的终端运动状态分析程序被执行时所实现的方法可参照本发明终端运动状态分析的方法各个实施例，在此不再赘述。
此外本发明实施例还提出一种计算机可读存储介质。
本发明计算机可读存储介质上存储有终端运动状态分析程序，所述终端运动状态分析程序被处理器执行时实现如上所述的终端运动状态分析方法的步骤。
其中，在所述处理器上运行的提示信息的显示程序被执行时所实现的方法可参照本发明终端运动状态分析方法各个实施例，在此不再赘述。
需要说明的是，在本文中，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、物品或者***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、物品或者***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，并不排除在包括该要素的过程、方法、物品或者***中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的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如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本发明各个实施例所述的方法。
以上实施例仅用以说明本发明的技术方案，而非对本发明保护范围的限制，尽管参照较佳实施例对本发明作了详细地说明，本领域的普通技术人员应当理解，对本发明的技术方案进行修改或者等同替换，均属本发明的保护范围。

Claims (10)

  1. 一种终端运动状态分析方法，其特征在于，所述终端运动状态分析方法包括以下步骤：
    获取终端的运动传感器采集到的运动数据，对所述运动数据进行预处理以得到有效运动数据；
    获取有效运动效数据中终端的加速度标准差，并由加速度标准差计算得出终端的背噪值；
    根据加速度标准差和背噪值的比较状态以及比较状态对应的持续时间，确定终端的运动状态。
  2. 如权利要求1所述的终端运动状态分析方法，其特征在于，所述对所述运动数据进行预处理以得到有效运动数据的步骤包括：
    对采集到的运动数据分别进行一次和两次微分，若微分结果的绝对值大于预设最大有效值，则判定采集的运动数据为无效数据：若微分结果的绝对值小于或等于预设的最大有效值，则判定采集的运动数据为有效数据；
    将所述有效数据中各矢量数据通过预设转换方法转换成标量数据，将该标量数据作为有效运动数据。
  3. 如权利要求2所述的终端运动状态分析方法，其特征在于，所述将所述有效数据中各矢量数据通过预设转换方法转换成标量数据，将该标量数据作为有效运动数据的步骤之后还包括：
    当检测到有效运动数据中加速度大于预设最大临界值时，则检测加速度在大于预设最大值后加速度是否小于预设最小临界值；
    若加速度在大于预设最大值后加速度小于预设最小临界值，则判定终端的运动状态为突发事件状态。
  4. 如权利要求1所述的终端运动状态分析方法，其特征在于，所述获取有效运动效数据中终端的加速度标准差，并由加速度标准差计算得出终端的背噪值的步骤包括：
    当前时刻背噪值由上一时刻的背噪值与一减去过渡系数的乘积加上加速度标准差与过渡系数的乘积得到，其中过渡系数决定加速度标准差对当前时刻背噪值的影响。
  5. 如权利要求4所述的终端运动状态分析方法，其特征在于，所述当前 时刻背噪值由上一时刻的背噪值与一减去过渡系数的乘积加上加速度标准差与过渡系数的乘积得到的步骤包括：
    根据以下公式，计算得出终端的背噪值，其中公式为：
    BackgroundNoise new＝BackgroundNoise old*(1-k)+StdDev(acc)*k
    其中BackgroundNoise old为未更新的背噪值，初始值为0.1；StdDev(acc)为加速度的标准差，k为背噪值的过渡系数，初始值为0.05，取值范围为[O,l],BackgroundNoise new为更新后的背噪值。
  6. 如权利要求1所述的终端运动状态分析方法，其特征在于，所述根据加速度标准差和背噪值的比较状态以及比较状态对应的持续时间，确定终端的运动状态的步骤包括：
    当检测到加速度标准差与背噪值的比较状态满足预设的移动临界值时，判定终端当前处于移动状态；
    当判定终端处于移动状态后，若加速度标准差与背噪值的比较状态满足预设的结束临界值，且满足结束临界值的持续时间大于预设的结束临界时间，则判定终端移动状态结束。
  7. 如权利要求6所述的终端运动状态分析方法，其特征在于，所述当判定终端处于移动状态后的步骤之后还包括：
    在判定当前处于移动状态后，若加速度标准差与背噪值的比较状态满足预设的人为运动临界值，且满足人为运动临界值的持续时间大于预设人为运动临界时间，则判定终端当前的运动状态为人为带走运动。
  8. 如权利要求6或7所述的终端运动状态分析方法，其特征在于，所述加速度标准差与背噪值的比较状态满足预设的移动临界值为：
    StdDev(acc)＞n1*BackgroundNoise∧StdDev(acc)＞BackgroundNoise+min.threshold movement
    所述加速度标准差与背噪值的比较状态满足预设的结束临界值为：
    StdDev(acc)＜n2*BackgroundNoise∨StdDev(acc)＜BackgroundNoise+min.threshold movement
    所述加速度标准差与背噪值的比较状态满足预设的人为运动临界值，且满足人为运动
    临界值的持续时间大于预设人为运动临界时间为：
    StdDev(acc)＞n3*BackgroundNoise∧Time movement＞3
    其中StdDev(acc)为加速度标准差，BackgroundNoise为计算所得背噪值，n1,n2,n3为比较系数，并且大小关为n3＞n2＞n1,min.threshold movement为预设的最低移动阔值，Time movement为持续时间。
  9. 一种移动终端，其特征在于，所述移动终端包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的终端运动状态分析程序，所述终端运动状态分析程序被所述处理器执行时实现如权利要求1至8中任一项所述的终端运动状态分析方法的步骤。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有终端运动状态分析程序，所述终端运动状态分析程序被处理器执行时实现如权利要求1至8中任一项所述的终端运动状态分析方法的步骤。
PCT/CN2018/095858 2017-07-18 2018-07-16 终端运动状态分析方法、移动终端及可读存储介质 WO2019015556A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710587497.5A CN107358051B (zh) 2017-07-18 2017-07-18 终端运动状态分析方法、移动终端及可读存储介质
CN201710587497.5 2017-07-18

Publications (1)

Publication Number Publication Date
WO2019015556A1 true WO2019015556A1 (zh) 2019-01-24

Family

ID=60285727

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/095858 WO2019015556A1 (zh) 2017-07-18 2018-07-16 终端运动状态分析方法、移动终端及可读存储介质

Country Status (2)

Country Link
CN (1) CN107358051B (zh)
WO (1) WO2019015556A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107358051B (zh) * 2017-07-18 2018-07-10 前海随身宝（深圳）科技有限公司 终端运动状态分析方法、移动终端及可读存储介质
CN109141465B (zh) * 2018-07-19 2021-06-22 歌尔科技有限公司 一种计步方法、可穿戴设备及计算机可读存储介质
CN111643887B (zh) * 2020-06-08 2023-07-14 歌尔科技有限公司 头戴设备及其数据处理方法、计算机可读存储介质
CN112082796B (zh) * 2020-09-14 2022-11-15 六盘水师范学院 一种工程机械设备工作状态判断方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101853380A (zh) * 2010-06-18 2010-10-06 华南理工大学 一种基于加速度传感器的手势识别的旋转特征提取方法
US20130102324A1 (en) * 2011-10-21 2013-04-25 Microsoft Corporation Device-to-device relative localization
CN103455170A (zh) * 2013-08-22 2013-12-18 西安电子科技大学 一种基于传感器的移动终端运动识别装置及方法
CN107358051A (zh) * 2017-07-18 2017-11-17 前海随身宝（深圳）科技有限公司 终端运动状态分析方法、移动终端及可读存储介质

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102010062016A1 (de) * 2010-11-26 2012-05-31 Siemens Aktiengesellschaft Verfahren und Vorrichtung zur Ermittlung von Bewegungsparametern bewegter Objekte
WO2014046204A1 (ja) * 2012-09-19 2014-03-27 株式会社ニコン 電子機器、及びプログラム
CN103340634B (zh) * 2013-06-17 2015-11-18 无锡市中安捷联科技有限公司 一种基于加速度变化检测人运动状态的方法
CN103701991A (zh) * 2013-12-20 2014-04-02 百度在线网络技术（北京）有限公司 移动终端状态识别方法和移动终端
CN105094305B (zh) * 2014-05-22 2018-05-18 华为技术有限公司 识别用户行为的方法、用户设备及行为识别服务器
CN104490401B (zh) * 2015-01-15 2017-05-24 张�杰 基于加速度数据的智能终端进行人体行为自动识别的方法
CN105571609B (zh) * 2015-04-28 2018-11-06 宇龙计算机通信科技(深圳)有限公司 一种运动参数处理方法及移动终端
CN106131792B (zh) * 2016-08-26 2019-11-01 北京小米移动软件有限公司 用户运动状态监测方法和装置
CN106441350A (zh) * 2016-10-09 2017-02-22 深圳市金立通信设备有限公司 一种计步方法及终端

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101853380A (zh) * 2010-06-18 2010-10-06 华南理工大学 一种基于加速度传感器的手势识别的旋转特征提取方法
US20130102324A1 (en) * 2011-10-21 2013-04-25 Microsoft Corporation Device-to-device relative localization
CN103455170A (zh) * 2013-08-22 2013-12-18 西安电子科技大学 一种基于传感器的移动终端运动识别装置及方法
CN107358051A (zh) * 2017-07-18 2017-11-17 前海随身宝（深圳）科技有限公司 终端运动状态分析方法、移动终端及可读存储介质

Also Published As

Publication number Publication date
CN107358051A (zh) 2017-11-17
CN107358051B (zh) 2018-07-10

Similar Documents

Publication Publication Date Title
WO2019015556A1 (zh) 终端运动状态分析方法、移动终端及可读存储介质
US8781991B2 (en) Emotion recognition apparatus and method
US20160296144A1 (en) Time and frequency domain based activity tracking system
US20140278208A1 (en) Feature extraction and classification to determine one or more activities from sensed motion signals
EP2967445A1 (en) Dynamic control of sampling rate of motion to modify power consumption
KR102143499B1 (ko) 휴대 단말 장치를 이용한 수면 품질 측정 방법 및 장치
US20140288875A1 (en) Methods and architecture for determining activity and activity types from sensed motion signals
CN108377422B (zh) 一种多媒体内容的播放控制方法、装置及存储介质
CN111698601B (zh) 蓝牙耳机及其按键灵敏度调整方法、装置、可读存储介质
KR20140083209A (ko) 사용자 동작 인식 장치 및 그 방법
EP2972930A2 (en) Inline calibration of motion sensor
US10799169B2 (en) Apparatus, system and method for detecting onset Autism Spectrum Disorder via a portable device
US20150241243A1 (en) Method for counting steps and electronic apparatus using the same
CN107784298B (zh) 一种识别方法及装置
US9665180B2 (en) Method for continuous recognition of gestures of a user of a handheld mobile terminal fitted with a motion sensor assembly, and related device
CN108038412B (zh) 终端及其基于自训练手势的控制方法、存储装置
US11602295B2 (en) Electronic device and method for providing personalized biometric information based on biometric signal using same
WO2018014432A1 (zh) 语音应用触发控制方法、装置及终端
CN114532992B (zh) 小睡状态检测方法、装置、***及计算机可读存储介质
WO2022198991A1 (zh) 运动时间计算方法、装置、设备及计算机可读存储介质
CN111797873A (zh) 场景识别方法、装置、存储介质及电子设备
CN111796663B (zh) 场景识别模型更新方法、装置、存储介质及电子设备
CN112790752B (zh) 心率值修正方法、装置及电子设备
JP2012063208A (ja) 状態判定装置および状態判定プログラム
CN114732377A (zh) 基于ai的健康管理方法、装置、设备及可读存储介质

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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 1205A DATED 19.05.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18834617

Country of ref document: EP

Kind code of ref document: A1