WO2019085337A1 - 基于信号数据筛选的定位方法、电子装置及存储介质 - Google Patents
基于信号数据筛选的定位方法、电子装置及存储介质 Download PDFInfo
- Publication number
- WO2019085337A1 WO2019085337A1 PCT/CN2018/076176 CN2018076176W WO2019085337A1 WO 2019085337 A1 WO2019085337 A1 WO 2019085337A1 CN 2018076176 W CN2018076176 W CN 2018076176W WO 2019085337 A1 WO2019085337 A1 WO 2019085337A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- signal strength
- data
- signal
- wireless device
- array
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0278—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves involving statistical or probabilistic considerations
Definitions
- the present application relates to the field of wireless positioning technologies, and in particular, to a positioning method based on signal data screening, an electronic device, and a computer readable storage medium.
- a wireless signal transmitting device such as a wireless router
- the signals of the devices detected by the mobile terminal and the known location information of the devices are used to calculate the mobile terminal. s position.
- the server and the mobile terminal continuously interact to continuously locate the location of the mobile terminal.
- the signal detected by the mobile terminal may fluctuate due to object occlusion, signal interference, or failure of the wireless signal transmitting device, causing the signal to deviate, but for the server, the signal is not automatically determined. Whether it is reasonable, just use the signal data to estimate the position and return to the display of the mobile terminal, resulting in unreasonable positioning points also displayed on the mobile, resulting in low positioning accuracy.
- the present application provides a positioning method, an electronic device and a computer readable storage medium based on signal data screening, the main purpose of which is to filter the signal data, use reasonable signal data to locate the mobile terminal, and improve the mobile terminal. Positioning accuracy.
- the present application provides a positioning method based on signal data screening, the method comprising:
- S3. Determine whether the number of the feature values in the signal strength array is less than a preset threshold. When the threshold is greater than or equal to the preset threshold, the signal strength array is retained. When the threshold is less than the preset threshold, the signal strength array is filtered out, and the returning step is performed. S1;
- the location coordinates of the mobile terminal are calculated according to the device signal data corresponding to the signal strength array according to a preset positioning algorithm.
- the present application further provides an electronic device, including: a memory, a processor, where the memory stores a positioning program based on signal data filtering, and the positioning program is implemented by the processor. The following steps:
- A2 extracting signal strength data of each wireless device from the device signal data as a feature value, and combining an eigenvalue of each wireless device to generate an array of signal strengths;
- A3. Determine whether the number of the feature values in the signal strength array is less than a preset threshold. When the threshold is greater than or equal to the preset threshold, the signal strength array is retained. When the threshold is less than the preset threshold, the signal strength array is filtered out, and the return step is performed. A1;
- A4 Input the reserved signal strength array into a predetermined signal data classifier, and determine whether the signal strength array is reasonable according to a result output by the signal data classifier;
- the position coordinates of the mobile terminal are calculated according to the device signal data corresponding to the signal strength array according to a preset positioning algorithm.
- the present application further provides a computer readable storage medium storing a positioning program based on signal data filtering, which is implemented by a processor to implement the above-described The steps of the positioning method for signal data screening.
- the positioning method, the electronic device and the computer readable storage medium based on the signal data screening receive the device signal data reported by the mobile terminal, and extract the signal strength of each wireless device as a feature value, and The feature value combination generates an array of signal strengths, performs preliminary screening on the array, and then uses a signal data classifier to judge the signal strength array rationally. If reasonable, the signal data of the signal strength array is used to calculate the position of the mobile terminal. Coordinates improve positioning accuracy.
- FIG. 1 is a schematic diagram of a preferred embodiment of an electronic device of the present application.
- FIG. 2 is a block diagram showing a preferred embodiment of a positioning procedure based on signal data screening in FIG. 1;
- FIG. 3 is a flowchart of a preferred embodiment of a positioning method based on signal data screening according to the present application
- FIG. 4 is a detailed flowchart of step S2 in the positioning method based on signal data screening according to the present application.
- the application provides an electronic device 1 .
- the electronic device 1 may be a PC (Personal Computer), or may be a terminal device having a computing function, such as a smart phone, a tablet computer, an e-book reader, a portable computer, or a server.
- the server may include: a rack server, a blade server, a tower server, a rack server, or the like.
- the electronic device includes a memory 11, a processor 12, a network interface 13, and a communication bus 14.
- the memory 11 includes at least one type of readable storage medium.
- the at least one type of readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card type memory, or the like.
- the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1.
- the readable storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC). , Secure Digital (SD) card, Flash Card, etc.
- SMC smart memory card
- SD Secure Digital
- the readable storage medium of the memory 11 is generally used to store application software and various types of data installed in the electronic device 1, for example, a positioning program 10 based on signal data filtering, and predetermined signal data classification. Model files, etc.
- the memory 11 can also be used to temporarily store data that has been output or is about to be output.
- the processor 12 in some embodiments, may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data processing chip for running program code or processing stored in the memory 11.
- the data for example, performs the positioning program 10 based on signal data filtering and the like.
- Network interface 13 may include a standard wired interface, a wireless interface (such as a Wi-Fi interface). Generally used to establish a communication connection between the electronic device 1 and other electronic devices.
- Communication bus 14 is used to implement connection communication between these components.
- Figure 1 shows only the electronic device 1 with components 11-14 and a signal data based locating program 10, but it should be understood that not all illustrated components may be implemented, alternative implementations may be more or less s component.
- the electronic device 1 may further include a user interface
- the user interface may include an input unit such as a keyboard
- the optional user interface may further include a standard wired interface and a wireless interface.
- the electronic device 1 may further include a display, which may also be referred to as a display screen or a display unit.
- a display may also be referred to as a display screen or a display unit.
- it may be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor, or the like.
- the display is used to display information processed in the electronic device 1 and a user interface for displaying visualizations.
- the memory 11 stores a positioning program 10 based on signal data filtering.
- the processor 12 executes the positioning program 10 based on signal data filtering stored in the memory 11, the following steps are implemented:
- A2 extracting signal strength data of each wireless device from the device signal data as a feature value, and combining an eigenvalue of each wireless device to generate an array of signal strengths;
- A3. Determine whether the number of the feature values in the signal strength array is less than a preset threshold. When the threshold is greater than or equal to the preset threshold, the signal strength array is retained. When the threshold is less than the preset threshold, the signal strength array is filtered out, and the return step is performed. A1;
- A4 Input the reserved signal strength array into a predetermined signal data classifier, and determine whether the signal strength array is reasonable according to a result output by the signal data classifier;
- the position coordinates of the mobile terminal are calculated according to the device signal data corresponding to the signal strength array according to a preset positioning algorithm.
- a plurality of wireless devices are disposed in the positioning area, such as a Wi-Fi device, a Bluetooth device, a radio frequency signal device, etc., and the mobile terminal (not shown) is located in the positioning area.
- the wireless signal transmitted by the wireless device is continuously detected within the coverage of the wireless device.
- the scheme of the present application will be described below by taking a Wi-Fi device as an example.
- each wireless device has a globally unique MAC (Media Access Control) address, and in general, the location of the device does not move, and the mobile terminal is enabled for Wi-Fi.
- MAC Media Access Control
- the surrounding Wi-Fi signals can be scanned and collected, and the MAC addresses broadcast by the wireless devices are obtained, and the mobile terminal transmits the detected signal strength and the MAC address of the corresponding device to the electronic device 1, as it can be moved according to the mobile device.
- the signal strength detected by the terminal determines the distance of the mobile terminal from the corresponding wireless device. Therefore, the electronic device 1 can calculate the current location of the mobile terminal according to the received signal data and the location coordinates of the stored device, and return to the mobile terminal for positioning. .
- the mobile terminal reports the device signal data at intervals of a preset time interval (1 second), wherein the device signal data includes the detected signal strength data of the plurality of wireless devices and the corresponding wireless device's MAC address or SSID (Service Set Identifier) , service set identifier, etc., which can uniquely identify the identification information of the device.
- MAC address Service Set Identifier
- SSID Service Set Identifier
- service set identifier etc.
- Extracting signal strength data of multiple wireless devices from the device signal data as feature values, and combining feature values of multiple wireless devices according to a preset sorting manner to form an array of signal strengths for subsequent use of the signal strength array Predict the current position coordinates of the mobile terminal. It can be understood that it is impossible to detect the signals of all the wireless devices at the current location. For the feature values corresponding to the wireless devices in this part, the default is -110dbm (near no signal), thus ensuring the elements in each signal strength array. The number is the same.
- the number of feature values in the signal strength array is not counted, that is, the feature value in the statistical signal strength array is not - the number of -110dbm, and determine whether the number is greater than or equal to a preset threshold (for example, 3), and if so, retain the array of signal strength and perform subsequent steps, if not, filter out the signal strength of this type Array.
- a preset threshold for example, 3
- the signal strength array retained by the above filtering step is input into a predetermined signal data classifier to predict whether the signal strength array is reasonable.
- the training step of the signal data classifier includes: separately collecting device signal data of multiple wireless devices detected by the mobile terminal at multiple sampling points, and devices of different wireless devices that the mobile terminal detects at different sampling points.
- Signal data extracting signal strength data of each wireless device from each group of device signal data as a feature value; combining characteristic values of each wireless device collected at each sampling point to generate an array of signal strength corresponding to the sampling point Assigning a first flag to the array of signal strengths, for example, "1", indicating that the signal strength array is reasonable, the signal strength arrays and marks corresponding to the plurality of sampling points are used as positive sample data, and some signals are estimated according to the positive sample data.
- An array of strengths assigning a second flag to the array of signal strengths, such as "0", indicating that the array of signal strengths is unreasonable, as a negative sample data, composing a sample set; randomly extracting a first ratio (eg, 60%) from the sample set An array of signal strengths and a marker of the signal strength array of the first ratio (eg 60%) as training a set, from the remaining sample set, randomly extracting a second scale (eg, 50%) of the signal strength array and the second scale (eg, 50%) of the signal strength array of the mark as a verification set, that is, extracting the sample set 20% of the sample data is used as a verification set; the random forest model is trained by using the 50% sample data, and the model parameters of the signal data classifier are determined to determine whether the signal strength array and the signal strength array are reasonable; 20% of the sample data verifies the accuracy of the signal data classifier. If the accuracy rate is greater than or equal to the preset accuracy rate (for example, 90%), the training ends, or if the accuracy rate is less than the prese
- the position coordinates of the mobile terminal are calculated by using the position and signal strength of each wireless device in the signal strength array. If the output result of the signal data classifier is the second flag, for example, “0”, it indicates that the signal strength array is unreasonable, and is not suitable for calculating the position coordinates of the mobile terminal.
- the positional coordinates of the mobile terminal may be calculated by using a triangulation algorithm, when the position coordinates of three or more wireless devices are determined, and the signal strength of the wireless device detected according to the mobile terminal.
- the distances of the mobile terminals from the wireless devices can be determined, and the location coordinates of the mobile terminal can be calculated according to the above information.
- the location coordinates of the mobile terminal are calculated by a classification algorithm, for example, using a random forest model calculation, the position coordinates of all wireless devices are collected, and the classifier is trained by the signal strength data detected by the mobile terminal with known position coordinates, and the classifier is determined.
- the model parameters determine the relationship between the position coordinates of the mobile terminal and the detected signal strength and the position coordinates of the corresponding wireless device.
- the calculated average value of the signal strength data of each wireless device is input into the trained classifier, the current position coordinates of the mobile terminal are calculated, and the position coordinates are fed back to the mobile terminal for positioning.
- the electronic device 1 of the embodiment receives the device signal data reported by the mobile terminal, extracts the signal strength of each wireless device as a feature value, combines the feature values to generate an array of signal strengths, and performs preliminary screening on the array.
- the rationality judgment if reasonable, uses the signal data of the signal strength array to calculate the position coordinates of the mobile terminal, thereby improving the positioning accuracy.
- step A2 includes:
- each set of signal strength data includes signal strength data of a plurality of wireless devices, n>1;
- the signal strength of the wireless device is detected n times consecutively when the time interval of the last report reaches 1 second.
- n sets of signal strength data It should be noted that the time interval between the detection of the n times of the signal is very short and negligible, and the moving distance of the mobile terminal during this period is also very small and negligible.
- the electronic device 1 performs filtering processing on these signals, and filters out appropriate signal data for calculating the position coordinates of the mobile terminal.
- Each set of signal strength data includes detected signal strengths of multiple wireless devices and corresponding wireless signals. Identification information of the device, such as SSID.
- the step of calculating the amount of deviation of the signal strength data of the wireless device includes calculating an average value of the signal strength data of the wireless device, and using a difference between the signal strength data and the average value as a deviation amount of the signal strength data. It is assumed that each group of signal strength data includes signal strength data of six wireless devices, and the electronic device 1 separately counts 10 signal strength data corresponding to each signal device according to the above 10 sets of signal strength data. For each wireless device, filter the 10 signal strength data, first calculate the deviation of each wireless signal strength data, and assume that there are n signal strength data corresponding to each device, then the n signal strength data The calculation formula of the deviation amount ⁇ i of the i-th signal intensity data p i in the following is as follows:
- the signal strength data of the wireless device is filtered. Specifically, when filtering the signal strength data of a wireless device, calculating a deviation amount of the signal strength data of the wireless device; determining, according to the total number of the signal strength data of the wireless device and the preset weight, the deletion The number m of signal strength data is used to delete m signal strength data with the largest amount of deviation in the signal strength data of the wireless device, where m ⁇ n.
- the electronic device 1 proposed in this embodiment detects and reports the signal of the mobile terminal for multiple times, and filters the signal strength data to reduce the influence of the deviation or fluctuation of the signal strength on the positioning and improve the positioning accuracy.
- the positioning program 10 based on signal data filtering may also be divided into one or more modules, one or more modules being stored in the memory 11 and being processed by one or more processors. 12 implementations to complete this application.
- a module as referred to in this application refers to a series of computer program instructions that are capable of performing a particular function.
- FIG. 2 it is a block diagram of a preferred embodiment of the positioning program 10 based on signal data filtering in FIG.
- the positioning program 10 based on the signal data screening may be divided into: a receiving module 110, an extracting module 120, a first determining module 130, a second determining module 140, and a calculating module 150, and the functions implemented by the modules 110-150 or
- the operation steps are all similar to the above, and will not be described in detail here, exemplarily, for example, where:
- the receiving module 110 is configured to receive device signal data of multiple wireless devices reported by the mobile terminal, and the extracting module 120 is configured to extract signal strength data of each wireless device from the device signal data as a feature value, and combine each wireless The eigenvalue of the device generates an array of signal strengths;
- the first determining module 130 is configured to determine whether the number of the feature values in the signal strength array is less than a preset threshold, and when the threshold is greater than or equal to the preset threshold, retain the signal strength array, and when less than the preset threshold, filter the An array of signal strengths;
- the second determining module 140 is configured to input the reserved signal strength array into a predetermined signal data classifier, and determine whether the signal strength array is reasonable according to a result output by the signal data classifier;
- the calculation module 150 is configured to calculate a position coordinate of the mobile terminal according to the device signal data corresponding to the signal strength array according to a preset positioning algorithm when the output of the signal data classifier is reasonable.
- the present application also provides a positioning method based on signal data screening.
- FIG. 3 it is a flowchart of a first preferred embodiment of a positioning method based on signal data screening of the present application.
- the method can be performed by an electronic device, which can be implemented by software and/or hardware.
- the positioning method based on the signal data screening includes: Steps S1 to S5.
- S3. Determine whether the number of the feature values in the signal strength array is less than a preset threshold. When the threshold is greater than or equal to the preset threshold, the signal strength array is retained. When the threshold is less than the preset threshold, the signal strength array is filtered out, and the returning step is performed. S1;
- the location coordinates of the mobile terminal are calculated according to the device signal data corresponding to the signal strength array according to a preset positioning algorithm.
- the mobile terminal reports the device signal data once every preset time interval (1 second), wherein the device signal data includes the detected signal strength data of the plurality of wireless devices and the corresponding wireless device's MAC address or SSID, which can be uniquely identified. Identification information of the device. It should be noted that each wireless device is numbered in advance, and the MAC address, SSID, and sorting manner of each wireless device (in descending order of numbers) are stored in the electronic device 1. Extracting signal strength data of multiple wireless devices from the device signal data as feature values, and combining feature values of multiple wireless devices according to a preset sorting manner to form an array of signal strengths for subsequent use of the signal strength array Predict the current position coordinates of the mobile terminal.
- the default is -110dbm (near no signal), thus ensuring the elements in each signal strength array.
- the number is the same.
- the number of feature values in the signal strength array is not counted, that is, the feature value in the statistical signal strength array is not - the number of -110dbm, and determine whether the number is greater than or equal to a preset threshold (for example, 3), and if so, retain the array of signal strength and perform subsequent steps, if not, filter out the signal strength of this type Array.
- a preset threshold for example, 3
- the signal strength array retained by the above filtering step is input into a predetermined signal data classifier to predict whether the signal strength array is reasonable.
- the training step of the signal data classifier includes: separately collecting device signal data of multiple wireless devices detected by the mobile terminal at multiple sampling points, and devices of different wireless devices that the mobile terminal detects at different sampling points.
- Signal data extracting signal strength data of each wireless device from each group of device signal data as a feature value; combining characteristic values of each wireless device collected at each sampling point to generate an array of signal strength corresponding to the sampling point Assigning a first flag to the array of signal strengths, for example, "1", indicating that the signal strength array is reasonable, the signal strength arrays and marks corresponding to the plurality of sampling points are used as positive sample data, and some signals are estimated according to the positive sample data.
- An array of strengths assigning a second flag to the array of signal strengths, such as "0", indicating that the array of signal strengths is unreasonable, as a negative sample data, composing a sample set; randomly extracting a first ratio (eg, 60%) from the sample set An array of signal strengths and a marker of the signal strength array of the first ratio (eg, 60%) as a training a set, from the remaining sample set, randomly extracting a second scale (eg, 50%) of the signal strength array and the second scale (eg, 50%) of the signal strength array of the mark as a verification set, that is, extracting the sample set 20% of the sample data is used as a verification set; the random forest model is trained by using the 50% sample data, and the model parameters of the signal data classifier are determined to determine whether the signal strength array and the signal strength array are reasonable; 20% of the sample data verifies the accuracy of the signal data classifier. If the accuracy rate is greater than or equal to the preset accuracy rate (for example, 90%), the training ends, or if the accuracy rate is less
- the position coordinates of the mobile terminal are calculated by using the position and signal strength of each wireless device in the signal strength array. If the output result of the signal data classifier is the second flag, for example, “0”, indicating that the signal strength array is unreasonable, it is not suitable for calculating the position coordinates of the mobile terminal.
- the positional coordinates of the mobile terminal may be calculated by using a triangulation algorithm, when the position coordinates of three or more wireless devices are determined, and the signal strength of the wireless device detected according to the mobile terminal.
- the distances of the mobile terminals from the wireless devices can be determined, and the location coordinates of the mobile terminal can be calculated according to the above information.
- the location coordinates of the mobile terminal are calculated by a classification algorithm, for example, using a random forest model calculation, the position coordinates of all wireless devices are collected, and the classifier is trained by the signal strength data detected by the mobile terminal with known position coordinates, and the classifier is determined.
- the model parameters determine the relationship between the position coordinates of the mobile terminal and the detected signal strength and the position coordinates of the corresponding wireless device.
- the calculated average value of the signal strength data of each wireless device is input into the trained classifier, the current position coordinates of the mobile terminal are calculated, and the position coordinates are fed back to the mobile terminal for positioning.
- the positioning method based on signal data screening proposed in this embodiment receives the device signal data reported by the mobile terminal, extracts the signal strength of each wireless device as a feature value, and combines the feature values to generate an array of signal strengths, and performs an array on the array. After the initial screening, the rationality judgment is made. If it is reasonable, the signal data of the signal strength array is used to calculate the position coordinates of the mobile terminal, and the positioning accuracy is improved.
- step S2 in the positioning method based on signal data screening of the present application.
- the step S2 includes:
- Step S21 obtaining n sets of signal strength data from the device signal data, wherein each set of signal strength data includes signal strength data of a plurality of wireless devices, n>1;
- Step S22 Statistically calculate signal strength data corresponding to each wireless device according to the n sets of signal strength data, and perform filtering processing: calculating a deviation amount of signal strength data of each wireless device, and deleting a signal whose offset amount satisfies a preset weight Intensity data; and
- Step S23 calculating an average value of the plurality of signal strength data remaining after filtering processing of each wireless device as a feature value of each wireless device, and combining feature values of each wireless device in each set of signal strength arrays into An array of signal strengths.
- the mobile terminal when the mobile terminal detects the signal strength data and reports it every preset time interval (1 second), the signal strength of the wireless device is detected n times consecutively when the time interval of the last report reaches 1 second. n sets of signal strength data. It should be noted that the time interval between the detection of the n times of the signal is very short and negligible, and the moving distance of the mobile terminal during this period is also very small and negligible.
- the signals are filtered and the appropriate signal data is filtered to calculate the position coordinates of the mobile terminal.
- the step of calculating the amount of deviation of the signal strength data of the wireless device includes calculating an average value of the signal strength data of the wireless device, and using a difference between the signal strength data and the average value as a deviation amount of the signal strength data. It is assumed that each group of signal strength data includes signal strength data of six wireless devices, and according to the above 10 sets of signal strength data, 10 signal strength data corresponding to each signal device are separately counted. For each wireless device, filter the 10 signal strength data, first calculate the deviation of each wireless signal strength data, and assume that there are n signal strength data corresponding to each device, then the n signal strength data The calculation formula of the deviation amount ⁇ i of the i-th signal intensity data p i in the following is as follows:
- the signal strength data of the wireless device is filtered. Specifically, when filtering the signal strength data of a wireless device, calculating a deviation amount of the signal strength data of the wireless device; determining, according to the total number of the signal strength data of the wireless device and the preset weight, the deletion The number m of signal strength data is used to delete m signal strength data with the largest amount of deviation in the signal strength data of the wireless device, where m ⁇ n.
- the positioning method based on the signal data screening proposed in this embodiment uses the signal detection and reporting of the mobile terminal multiple times to filter the signal strength data, thereby reducing the deviation of the signal strength or the influence of the fluctuation on the positioning. Improve positioning accuracy.
- the embodiment of the present application further provides a computer readable storage medium, where the positioning program based on signal data filtering is stored, and the positioning program based on signal data filtering is implemented by the processor as follows: operating:
- A2 extracting signal strength data of each wireless device from the device signal data as a feature value, and combining an eigenvalue of each wireless device to generate an array of signal strengths;
- A3. Determine whether the number of the feature values in the signal strength array is less than a preset threshold. When the threshold is greater than or equal to the preset threshold, the signal strength array is retained. When the threshold is less than the preset threshold, the signal strength array is filtered out, and the return step is performed. A1;
- A4 Input the reserved signal strength array into a predetermined signal data classifier, and determine whether the signal strength array is reasonable according to a result output by the signal data classifier;
- the position coordinates of the mobile terminal are calculated according to the device signal data corresponding to the signal strength array according to a preset positioning algorithm.
- the specific implementation manner of the computer readable storage medium of the present application is substantially the same as the specific implementation method of the above-mentioned positioning method based on signal data screening, and details are not described herein again.
- a disk including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the various embodiments of the present application.
- a terminal device which may be a mobile phone, a computer, a server, or a network device, etc.
Abstract
本申请提出一种基于信号数据筛选的定位方法，该方法包括：接收移动终端上报的多台无线设备的设备信号数据；从所述设备信号数据中提取每台无线设备的信号强度作为特征值，组合特征值生成一个信号强度数组；判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组；将保留的该信号强度数组输入信号数据分类器，判断该信号强度数组是否合理；及，当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。本申请还提出一种电子装置及存储介质。利用本申请，可以提高移动终端的定位精准度。
Description
优先权申明
本申请基于巴黎公约申明享有2017年11月3日递交的申请号为CN201711071306.6、名称为“基于信号数据筛选的定位方法、装置及存储介质”的中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合本申请中。
本申请涉及无线定位技术领域，尤其涉及一种基于信号数据筛选的定位方法、电子装置及计算机可读存储介质。
在室内环境中对移动终端进行定位时，可以在室内环境部署无线信号发射设备(如无线路由器)，通过移动终端检测到的这些设备的信号以及已知的这些设备的位置信息，推算出移动终端的位置。
随着移动终端的移动，服务端与移动终端的不断交互，不断地定位出移动终端的位置。在实际应用中，可能会由于物体遮挡、信号干扰或者无线信号发射设备故障等原因，造成移动终端检测到的信号发生波动，导致信号发生偏离，但是对于服务器来说，不会自动的去判断信号是否合理，只是直接利用信号数据推算位置并返回至移动终端显示，导致不合理的定位点也在移动上显示，导致定位精准度低。
发明内容
本申请提供一种基于信号数据筛选的定位方法、电子装置及计算机可读存储介质，其主要目的在于，通过对信号数据进行筛选，利用合理的信号数据对移动终端进行定位，提高对移动终端的定位精准度。
为实现上述目的，本申请提供一种基于信号数据筛选的定位方法，该方法包括：
S1、接收移动终端上报的多台无线设备的设备信号数据；
S2、从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；
S3、判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组、返回步骤S1；
S4、将保留的该信号强度数组输入预先确定的信号数据分类器，根据信号数据分类器输出的结果判断所述信号强度数组是否合理；及
S5、当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
此外，为实现上述目的，本申请还提供一种电子装置，该电子装置包括：存储器、处理器，所述存储器存储有基于信号数据筛选的定位程序，该定位程序被所述处理器执行时实现如下步骤：
A1、接收移动终端上报的多台无线设备的设备信号数据；
A2、从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；
A3、判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组、返回步骤A1；
A4、将保留的该信号强度数组输入预先确定的信号数据分类器，根据信号数据分类器输出的结果判断所述信号强度数组是否合理；及
A5、当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
此外，为实现上述目的，本申请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存储有基于信号数据筛选的定位程序，该定位程序被处理器执行时实现如上所述的基于信号数据筛选的定位方法的步骤。
相较于现有技术，本申请提出的基于信号数据筛选的定位方法、电子装置及计算机可读存储介质，接收移动终端上报的设备信号数据，提取每台无线设备的信号强度作为特征值，将所述特征值组合生成一个信号强度数组，对该数组进行初步筛选，然后利用信号数据分类器对信号强度数组进行合理性判断，若合理，则利用该信号强度数组的信号数据计算移动终端的位置坐 标，提高了定位准确性。
图1为本申请电子装置较佳实施例的示意图；
图2为图1中基于信号数据筛选的定位程序较佳实施例的模块示意图；
图3为本申请基于信号数据筛选的定位方法较佳实施例的流程图；
图4为本申请基于信号数据筛选的定位方法中步骤S2的细化流程图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供一种电子装置1。参照图1所示，为本申请电子装置1较佳实施例的示意图。在本实施例中，电子装置1可以是PC(Personal Computer，个人电脑)，也可以是智能手机、平板电脑、电子书阅读器、便携计算机、服务器等具有计算功能的终端设备。在一个实施例中，当电子装置1为服务器时，该服务器可以包括：机架式服务器、刀片式服务器、塔式服务器或机柜式服务器等。
该电子装置包括存储器11、处理器12、网络接口13及通信总线14。
其中，存储器11包括至少一种类型的可读存储介质。所述至少一种类型的可读存储介质可为如闪存、硬盘、多媒体卡、卡型存储器等的非易失性存储介质。在一些实施例中，所述可读存储介质可以是所述电子装置1的内部存储单元，例如该电子装置1的硬盘。在另一些实施例中，所述可读存储介质也可以是所述电子装置1的外部存储设备，例如所述电子装置1上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。
在本实施例中，所述存储器11的可读存储介质通常用于存储安装于所述电子装置1的应用软件及各类数据，例如基于信号数据筛选的定位程序10、预先确定的信号数据分类器的模型文件等。所述存储器11还可以用于暂时地 存储已经输出或者将要输出的数据。
处理器12在一些实施例中可以是一中央处理器(Central Processing Unit,CPU)、控制器、微控制器、微处理器或其他数据处理芯片，用于运行存储器11中存储的程序代码或处理数据，例如执行所述基于信号数据筛选的定位程序10等。
网络接口13可以包括标准的有线接口、无线接口(如Wi-Fi接口)。通常用于在该电子装置1与其他电子设备之间建立通信连接。
通信总线14用于实现这些组件之间的连接通信。
图1仅示出了具有组件11-14以及基于信号数据筛选的定位程序10的电子装置1，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
可选的，该电子装置器1还可以包括用户接口，用户接口可以包括输入单元比如键盘(Keyboard)，可选的用户接口还可以包括标准的有线接口、无线接口。
可选的，该电子装置1还可以包括显示器，也可以称为显示屏或显示单元。在一些实施例中可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode，有机发光二极管)触摸器等。所述显示器用于显示在服电子装置1中处理的信息以及用于显示可视化的用户界面。
在图1所示的装置实施例中，存储器11中存储有基于信号数据筛选的定位程序10，处理器12执行存储器11中存储的基于信号数据筛选的定位程序10时实现以下步骤：
A1、接收移动终端上报的多台无线设备的设备信号数据；
A2、从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；
A3、判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组、返回步骤A1；
A4、将保留的该信号强度数组输入预先确定的信号数据分类器，根据信 号数据分类器输出的结果判断所述信号强度数组是否合理；及
A5、当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
本申请实施例中，在定位区域设置有多个无线设备(图中未示出)，例如Wi-Fi设备、蓝牙设备、无线射频信号设备等，移动终端(图中未示出)在定位区域中移动时，在无线设备的覆盖范围内，会不断地检测到无线设备发射的无线信号。以下以Wi-Fi设备为例对本申请的方案进行说明。对于无线设备来说，每一台无线设备都有一个全球唯一的MAC(Media Access Control，媒体访问控制)地址，并且一般情况下，该设备的位置不会移动，移动终端在开启Wi-Fi的情况下，可以扫描并收集周围的Wi-Fi信号，并获取这些无线设备广播出来的MAC地址，移动终端将检测到的信号强度与对应的设备的MAC地址发送给电子装置1，由于可以根据移动终端检测到的信号强度确定移动终端距离对应的无线设备的距离，因此电子装置1可以根据接收到的信号数据以及存储的设备的位置坐标计算出移动终端当前的位置，并返回给移动终端进行定位。
移动终端每间隔预设时间间隔(1秒)上报一次设备信号数据，其中，设备信号数据包含有检测到的多台无线设备的信号强度数据和对应的无线设备的MAC地址或者SSID(Service Set Identifier，服务集标识)等能够唯一标识该设备的标识信息。需要说明的是，事先为每台无线设备进行编号排序，并将每台无线设备的MAC地址、SSID及排序方式(按照编号从小到大的顺序)储存在电子装置1中。从上述设备信号数据中提取出多台无线设备的信号强度数据作为特征值，按照预设的排序方式对多台无线设备的特征值进行组合，形成一个信号强度数组，以便后续利用该信号强度数组预测移动终端当前的位置坐标。可以理解的是，在当前位置不可能检测到所有无线设备的信号，对于这部分的无线设备对应的特征值，默认为-110dbm(接近无信号)，这样保证每个信号强度数组中的元素的个数一致。
可以理解的是，后续根据信号强度数组计算移动终端的位置坐标时，至少需要3个无线设备的信号数据方能确定移动终端的具体位置，因此，需要对信号强度数组中特征值的个数进行筛选。在本实施例中，对于上述未检测到的无线设备信号，并将其默认为-110dbm的元素，不计入信号强度数组中特 征值的数量，也就是说，统计信号强度数组中特征值不是-110dbm的个数，并判断该个数是否大于或等于预设阈值(例如，3个)，若是，则保留该信号强度数组并进行后续步骤，若不是，则过滤掉这一类的信号强度数组。
将上述过滤步骤保留下来的信号强度数组输入预先确定的信号数据分类器中，以预测出该信号强度数组是否合理。其中，所述信号数据分类器的训练步骤包括：分别收集移动终端在多个采样点检测到的多台无线设备的设备信号数据，移动终端在不同的采样点会检测到的不同无线设备的设备信号数据，从每组设备信号数据中提取每台无线设备的信号强度数据作为特征值；将在每个采样点收集的每台无线设备的特征值进行组合，生成该采样点对应的信号强度数组，给这些信号强度数组分配第一标记，例如“1”，表示该信号强度数组合理，所述多个采样点分别对应的信号强度数组及标记作为正样本数据，并根据正样本数据推算一些信号强度数组，给这些信号强度数组分配第二标记，例如“0”，表示该信号强度数组不合理，作为负样本数据，组成样本集；从样本集中的随机抽取第一比例(例如60％)的信号强度数组及该第一比例(例如60％)的信号强度数组的标记作为训练集，从剩下的样本集中的随机抽取第二比例(例如50％)的信号强度数组及该第二比例(例如50％)的信号强度数组的标记作为验证集，也就是说，抽取样本集的20％的样本数据作为验证集；利用所述50％的样本数据对随机森林模型进行训练，确定信号数据分类器的模型参数，确定出信号强度数组与该信号强度数组是否合理的关系；利用20％的样本数据对所述信号数据分类器的准确性进行验证，若准确率大于或者等于预设准确率(例如90％)，则训练结束，或者，若准确率小于预设准确率(例如90％)，则增加样本数量并重新执行训练步骤。
若信号数据分类器的输出结果为所述第一标记，例如“1”，表示该信号强度数组合理，则利用该信号强度数组中各无线设备的位置及信号强度计算出移动终端的位置坐标。若信号数据分类器的输出结果为所述第二标记，例如“0”，表示该信号强度数组不合理，不适合用于计算移动终端的位置坐标。其中，在一些实施例中，可以采用三角定位算法计算移动终端的位置坐标，当三台或者三台以上的无线设备的位置坐标是确定的，并且根据移动终端检测到的这无线设备的信号强度，能够确定出移动终端分别距离这些无线设备的距离，根据上述信息可以计算出移动终端的位置坐标。
或者，通过分类算法计算出移动终端的位置坐标，例如使用随机森林模型计算，采集所有无线设备的位置坐标，并通过已知位置坐标的移动终端检测的信号强度数据训练上述分类器，确定分类器的模型参数，确定出移动终端的位置坐标与检测到得信号强度和对应的无线设备的位置坐标之间的关系。将计算得到的各台无线设备的信号强度数据的平均值输入上述训练好的分类器中，计算出所述移动终端当前的位置坐标，并将所述位置坐标反馈至移动终端进行定位。
本实施例提出的电子装置1，接收移动终端上报的设备信号数据，提取每台无线设备的信号强度作为特征值，将所述特征值组合生成一个信号强度数组，对该数组进行初步筛选后进行合理性判断，若合理，则利用该信号强度数组的信号数据计算移动终端的位置坐标，提高了定位准确性。
基于上述实施例提出本申请电子装置第二个较佳实施例。在本实施例中，所述步骤A2包括：
从所述设备信号数据中获取n组信号强度数据，其中，每组信号强度数据中包含有多个无线设备的信号强度数据，n＞1；
根据所述n组信号强度数据，分别统计每台无线设备对应的信号强度数据并进行过滤处理：计算每台无线设备的信号强度数据的偏离量，删除偏离量满足预设权重的信号强度数据；及
计算每台无线设备经过滤处理后剩余的多个信号强度数据的平均值作为每台无线设备的特征值，将所述每组信号强度数组中的每台无线设备的特征值组合成一个信号强度数组。
在本实施例中，移动终端每隔预设时间间隔(1秒)检测一次信号强度数据并上报，则在距离上一次上报的时间间隔达到1秒时，连续n次检测无线设备的信号强度生成n组信号强度数据。需要说明的是，这n次信号检测之间的时间间隔非常短，可以忽略不计，并且在这期间移动终端的移动距离也非常小，也可以忽略不计。电子装置1对这些信号进行过滤处理，筛选出合适的信号数据，用来计算移动终端的位置坐标。其中，n为大于1的正整数，优选地，n＝8～12。假设n＝10，则移动终端每间隔1秒，重复检测10次信号，生成10组信号强度数据，每一组信号强度数据中都包含有检测到的多个无线 设备的信号强度以及对应的无线设备的标识信息，如SSID。
计算该无线设备的信号强度数据的偏离量的步骤包括：计算该无线设备的信号强度数据的平均值，将信号强度数据与所述平均值之间的差值作为该信号强度数据的偏离量。假设每一组信号强度数据中都包含有6台无线设备的信号强度数据，电子装置1根据上述10组信号强度数据，分别统计每一个信号设备对应的10个信号强度数据。针对每一台无线设备，对这10个信号强度数据进行过滤处理，首先计算每一个无线信号强度数据的偏离量，假设每台设备对应的信号强度数据有n个，则这n个信号强度数据中的第i个信号强度数据p
i的偏离量δ
i的计算公式如下：
计算得到每个信号强度数据的偏离量之后，对无线设备的信号强度数据做过滤处理。具体地，在对一台无线设备的信号强度数据进行过滤处理时，计算该无线设备的信号强度数据的偏离量；根据该无线设备的信号强度数据的总数和所述预设权重确定要删除的信号强度数据的数量m，删除该无线设备的信号强度数据中偏离量最大的m个信号强度数据，其中，m＜n。
在该实施方式中，预设权重为需要保留的信号强度数据在信号强度数据总量中的占比，每台无线设备的n个信号强度数据中需要删除的数据量m＝n*预设权重(例如80％)，若采集到的一台无线设备的信号强度数据总量为10个，则删除其中偏离量最大的2个信号强度数据，即m＝8，需要保留其中偏离量较小的8个信号强度数据。在对信号强度数据过滤处理后，计算剩余的信号强度数据的平均值，提取出多台无线设备的信号强度数据作为特征值，按照预设的排序方式对多台无线设备的特征值进行组合，形成一个信号强度数组，将该特征向量输入上述实施例中训练好的信号数据分类器，判断该信号强度数组的合理性，计算移动终端当前的位置坐标，后续移动终端位置坐标的计算步骤参见上述两个实施例，这里不再赘述。
本实施例提出的电子装置1，通过移动终端连续多次的信号检测并上报，对这多次的信号强度数据进行过滤处理，降低信号强度存在的偏差或者波动对定位的影响，提高定位精度。
可选地，在其他的实施例中，基于信号数据筛选的定位程序10还可以被 分割为一个或者多个模块，一个或者多个模块被存储于存储器11中，并由一个或多个处理器12所执行，以完成本申请。本申请所称的模块是指能够完成特定功能的一系列计算机程序指令段。参照图2所示，是图1中基于信号数据筛选的定位程序10较佳实施例的模块示意图。
所述基于信号数据筛选的定位程序10可以被分割为：接收模块110、提取模块120、第一判断模块130、第二判断模块140及计算模块150，所述模块110-150所实现的功能或操作步骤均与上文类似，此处不再详述，示例性地，例如其中：
接收模块110，用于接收移动终端上报的多台无线设备的设备信号数据；提取模块120，用于从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；
第一判断模块130，用于判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组；
第二判断模块140，用于将保留的该信号强度数组输入预先确定的信号数据分类器，根据信号数据分类器输出的结果判断所述信号强度数组是否合理；及
计算模块150，用于当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
此外，本申请还提供一种基于信号数据筛选的定位方法。参照图3所示，为本申请基于信号数据筛选的定位方法第一个较佳实施例的流程图。该方法可以由一个电子装置执行，该装置可以由软件和/或硬件实现。
在本实施例中，基于信号数据筛选的定位方法包括：步骤S1～步骤S5。
S1、接收移动终端上报的多台无线设备的设备信号数据；
S2、从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；
S3、判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信 号强度数组、返回步骤S1；
S4、将保留的该信号强度数组输入预先确定的信号数据分类器，根据信号数据分类器输出的结果判断所述信号强度数组是否合理；及
S5、当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
移动终端每间隔预设时间间隔(1秒)上报一次设备信号数据，其中，设备信号数据包含有检测到的多台无线设备的信号强度数据和对应的无线设备的MAC地址或者SSID等能够唯一标识该设备的标识信息。需要说明的是，事先为每台无线设备进行编号排序，并将每台无线设备的MAC地址、SSID及排序方式(按照编号从小到大的顺序)储存在电子装置1中。从上述设备信号数据中提取出多台无线设备的信号强度数据作为特征值，按照预设的排序方式对多台无线设备的特征值进行组合，形成一个信号强度数组，以便后续利用该信号强度数组预测移动终端当前的位置坐标。可以理解的是，在当前位置不可能检测到所有无线设备的信号，对于这部分的无线设备对应的特征值，默认为-110dbm(接近无信号)，这样保证每个信号强度数组中的元素的个数一致。
可以理解的是，后续根据信号强度数组计算移动终端的位置坐标时，至少需要3个无线设备的信号数据方能确定移动终端的具体位置，因此，需要对信号强度数组中特征值的个数进行筛选。在本实施例中，对于上述未检测到的无线设备信号，并将其默认为-110dbm的元素，不计入信号强度数组中特征值的数量，也就是说，统计信号强度数组中特征值不是-110dbm的个数，并判断该个数是否大于或等于预设阈值(例如，3个)，若是，则保留该信号强度数组并进行后续步骤，若不是，则过滤掉这一类的信号强度数组。
将上述过滤步骤保留下来的信号强度数组输入预先确定的信号数据分类器中，以预测出该信号强度数组是否合理。其中，所述信号数据分类器的训练步骤包括：分别收集移动终端在多个采样点检测到的多台无线设备的设备信号数据，移动终端在不同的采样点会检测到的不同无线设备的设备信号数据，从每组设备信号数据中提取每台无线设备的信号强度数据作为特征值；将在每个采样点收集的每台无线设备的特征值进行组合，生成该采样点对应的信号强度数组，给这些信号强度数组分配第一标记，例如“1”，表示该信号 强度数组合理，所述多个采样点分别对应的信号强度数组及标记作为正样本数据，并根据正样本数据推算一些信号强度数组，给这些信号强度数组分配第二标记，例如“0”，表示该信号强度数组不合理，作为负样本数据，组成样本集；从样本集中的随机抽取第一比例(例如60％)的信号强度数组及该第一比例(例如60％)的信号强度数组的标记作为训练集，从剩下的样本集中的随机抽取第二比例(例如50％)的信号强度数组及该第二比例(例如50％)的信号强度数组的标记作为验证集，也就是说，抽取样本集的20％的样本数据作为验证集；利用所述50％的样本数据对随机森林模型进行训练，确定信号数据分类器的模型参数，确定出信号强度数组与该信号强度数组是否合理的关系；利用20％的样本数据对所述信号数据分类器的准确性进行验证，若准确率大于或者等于预设准确率(例如90％)，则训练结束，或者，若准确率小于预设准确率(例如90％)，则增加样本数量并重新执行训练步骤。
若信号数据分类器的输出结果为所述第一标记，例如“1”，表示该信号强度数组合理，则利用该信号强度数组中各无线设备的位置及信号强度计算出移动终端的位置坐标。若信号数据分类器的输出结果为所述第二标记，例如“0”，表示该信号强度数组不合理，则不适合用于计算移动终端的位置坐标。其中，在一些实施例中，可以采用三角定位算法计算移动终端的位置坐标，当三台或者三台以上的无线设备的位置坐标是确定的，并且根据移动终端检测到的这无线设备的信号强度，能够确定出移动终端分别距离这些无线设备的距离，根据上述信息可以计算出移动终端的位置坐标。
或者，通过分类算法计算出移动终端的位置坐标，例如使用随机森林模型计算，采集所有无线设备的位置坐标，并通过已知位置坐标的移动终端检测的信号强度数据训练上述分类器，确定分类器的模型参数，确定出移动终端的位置坐标与检测到得信号强度和对应的无线设备的位置坐标之间的关系。将计算得到的各台无线设备的信号强度数据的平均值输入上述训练好的分类器中，计算出所述移动终端当前的位置坐标，并将所述位置坐标反馈至移动终端进行定位。
本实施例提出的基于信号数据筛选的定位方法，接收移动终端上报的设备信号数据，提取每台无线设备的信号强度作为特征值，将所述特征值组合生成一个信号强度数组，对该数组进行初步筛选后进行合理性判断，若合理， 则利用该信号强度数组的信号数据计算移动终端的位置坐标，提高了定位准确性。
基于上述第一个较佳实施例提出本申请基于信号数据筛选的定位第二个较佳实施例。参照图4所示，为本申请基于信号数据筛选的定位方法中步骤S2的细化流程图。在本实施例中，所述步骤S2包括：
步骤S21，从所述设备信号数据中获取n组信号强度数据，其中，每组信号强度数据中包含有多个无线设备的信号强度数据，n＞1；
步骤S22，根据所述n组信号强度数据，分别统计每台无线设备对应的信号强度数据并进行过滤处理：计算每台无线设备的信号强度数据的偏离量，删除偏离量满足预设权重的信号强度数据；及
步骤S23，计算每台无线设备经过滤处理后剩余的多个信号强度数据的平均值作为每台无线设备的特征值，将所述每组信号强度数组中的每台无线设备的特征值组合成一个信号强度数组。
在本实施例中，移动终端每隔预设时间间隔(1秒)检测一次信号强度数据并上报，则在距离上一次上报的时间间隔达到1秒时，连续n次检测无线设备的信号强度生成n组信号强度数据。需要说明的是，这n次信号检测之间的时间间隔非常短，可以忽略不计，并且在这期间移动终端的移动距离也非常小，也可以忽略不计。对这些信号进行过滤处理，筛选出合适的信号数据，用来计算移动终端的位置坐标。其中，n为大于1的正整数，优选地，n＝8～12。假设n＝10，则移动终端每间隔1秒，重复检测10次信号，生成10组信号强度数据，每一组信号强度数据中都包含有检测到的多个无线设备的信号强度以及对应的无线设备的标识信息，如SSID。
计算该无线设备的信号强度数据的偏离量的步骤包括：计算该无线设备的信号强度数据的平均值，将信号强度数据与所述平均值之间的差值作为该信号强度数据的偏离量。假设每一组信号强度数据中都包含有6台无线设备的信号强度数据，根据上述10组信号强度数据，分别统计每一个信号设备对应的10个信号强度数据。针对每一台无线设备，对这10个信号强度数据进行过滤处理，首先计算每一个无线信号强度数据的偏离量，假设每台设备对应的信号强度数据有n个，则这n个信号强度数据中的第i个信号强度数据 p
i的偏离量δ
i的计算公式如下：
计算得到每个信号强度数据的偏离量之后，对无线设备的信号强度数据做过滤处理。具体地，在对一台无线设备的信号强度数据进行过滤处理时，计算该无线设备的信号强度数据的偏离量；根据该无线设备的信号强度数据的总数和所述预设权重确定要删除的信号强度数据的数量m，删除该无线设备的信号强度数据中偏离量最大的m个信号强度数据，其中，m＜n。
在该实施方式中，预设权重为需要保留的信号强度数据在信号强度数据总量中的占比，每台无线设备的n个信号强度数据中需要删除的数据量m＝n*预设权重(例如80％)，若采集到的一台无线设备的信号强度数据总量为10个，则删除其中偏离量最大的2个信号强度数据，即m＝8，需要保留其中偏离量较小的8个信号强度数据。在对信号强度数据过滤处理后，计算剩余的信号强度数据的平均值，提取出多台无线设备的信号强度数据作为特征值，按照预设的排序方式对多台无线设备的特征值进行组合，形成一个信号强度数组，将该特征向量输入上述实施例中训练好的信号数据分类器，判断该信号强度数组的合理性，计算移动终端当前的位置坐标，后续移动终端位置坐标的计算步骤参见上述两个实施例，这里不再赘述。
本实施例提出的基于信号数据筛选的定位方法，通过移动终端连续多次的信号检测并上报，对这多次的信号强度数据进行过滤处理，降低信号强度存在的偏差或者波动对定位的影响，提高定位精度。
此外，本申请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基于信号数据筛选的定位程序，所述基于信号数据筛选的定位程序被处理器执行时实现如下操作：
A1、接收移动终端上报的多台无线设备的设备信号数据；
A2、从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；
A3、判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组、返回步骤A1；
A4、将保留的该信号强度数组输入预先确定的信号数据分类器，根据信号数据分类器输出的结果判断所述信号强度数组是否合理；及
A5、当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
本申请之计算机可读存储介质的具体实施方式与上述基于信号数据筛选的定位方法的具体实施方式大致相同，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、装置、物品或者方法不仅包括那些要素，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、装置、物品或者方法所固有的要素。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、装置、物品或者方法中还存在另外的相同要素。
上述本申请实施例先后仅仅为了描述，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，本申请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，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。
Claims (20)
- 一种基于信号数据筛选的定位方法，应用于电子装置，其特征在于，该方法包括：S1、接收移动终端上报的多台无线设备的设备信号数据；S2、从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；S3、判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组、返回步骤S1；S4、将保留的该信号强度数组输入预先确定的信号数据分类器，根据信号数据分类器输出的结果判断所述信号强度数组是否合理；及S5、当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
- 如权利要求1所述的基于信号数据筛选的定位方法，其特征在于，所述步骤S2包括：从所述设备信号数据中获取n组信号强度数据，其中，每组信号强度数据中包含有多个无线设备的信号强度数据，n＞1；根据所述n组信号强度数据，分别统计每台无线设备对应的信号强度数据并进行过滤处理：计算每台无线设备的信号强度数据的偏离量，删除偏离量满足预设权重的信号强度数据；及计算每台无线设备经过滤处理后剩余的多个信号强度数据的平均值作为每台无线设备的特征值，将所述每组信号强度数组中的每台无线设备的特征值组合成一个信号强度数组。
- 如权利要求2所述的基于信号数据筛选的定位方法，其特征在于，所述“计算每台无线设备的信号强度数据的偏离量”的步骤包括：计算该无线设备的信号强度数据的平均值，将信号强度数据与所述平均值之间的差值作为该信号强度数据的偏离量。
- 如权利要求3所述的基于信号数据筛选的定位方法，其特征在于，所述“计算每台无线设备的信号强度数据的偏离量，删除偏离量满足预设权重的 信号强度数据”的步骤包括：在对一台无线设备的信号强度数据进行过滤处理时，计算该无线设备的信号强度数据的偏离量；及根据该无线设备的信号强度数据的总数和所述预设权重确定要删除的信号强度数据的数量m，删除该无线设备的信号强度数据中偏离量最大的m个信号强度数据，其中，m＜n。
- 如权利要求1所述的基于信号数据筛选的定位方法，其特征在于，所述“组合每台无线设备的特征值生成一个信号强度数组”的步骤包括：按照预设的排序方式对多台无线设备的特征值进行组合，形成一个信号强度数组。
- 如权利要求1所述的基于信号数据筛选的定位方法，其特征在于，所述预先确定的信号数据分类器的训练步骤包括：分别收集移动终端在多个采样点检测到的多台无线设备的设备信号数据，从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值；将在每个采样点收集的每台无线设备的特征值进行组合，生成该采样点对应的信号强度数组，并分配第一标记作为正样本数据；根据正样本数据推算一些不合理的信号强度数组，并分配第二标记作为负样本数据，组成样本集；将所述样本数据分成为第一比例的训练集及第二比例的验证集；利用所述训练集对随机森林模型进行训练，得到所述信号数据分类器；及利用所述验证集对所述信号数据分类器的准确性进行验证，若准确率大于或者等于预设准确率，则训练结束，或者，若准确率小于预设准确率，则增加样本数量并重新执行训练步骤。
- 一种电子装置，其特征在于，该电子装置包括：存储器、处理器，所述存储器存储有基于信号数据筛选的定位程序，该定位程序被所述处理器执行时实现如下步骤：A1、接收移动终端上报的多台无线设备的设备信号数据；A2、从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；A3、判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组、返回步骤A1；A4、将保留的该信号强度数组输入预先确定的信号数据分类器，根据信号数据分类器输出的结果判断所述信号强度数组是否合理；及A5、当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
- 如权利要求7所述的电子装置，其特征在于，所述步骤A2包括：从所述设备信号数据中获取n组信号强度数据，其中，每组信号强度数据中包含有多个无线设备的信号强度数据，n＞1；根据所述n组信号强度数据，分别统计每台无线设备对应的信号强度数据并进行过滤处理：计算每台无线设备的信号强度数据的偏离量，删除偏离量满足预设权重的信号强度数据；及计算每台无线设备经过滤处理后剩余的多个信号强度数据的平均值作为每台无线设备的特征值，将所述每组信号强度数组中的每台无线设备的特征值组合成一个信号强度数组。
- 如权利要求8所述的电子装置，其特征在于，所述“计算每台无线设备的信号强度数据的偏离量”的步骤包括：计算该无线设备的信号强度数据的平均值，将信号强度数据与所述平均值之间的差值作为该信号强度数据的偏离量。
- 如权利要求9所述的电子装置，其特征在于，所述“计算每台无线设备的信号强度数据的偏离量，删除偏离量满足预设权重的信号强度数据”的步骤包括：在对一台无线设备的信号强度数据进行过滤处理时，计算该无线设备的信号强度数据的偏离量；及根据该无线设备的信号强度数据的总数和所述预设权重确定要删除的信号强度数据的数量m，删除该无线设备的信号强度数据中偏离量最大的m个信号强度数据，其中，m＜n。
- 如权利要求7所述的电子装置，其特征在于，所述“组合每台无线设备的特征值生成一个信号强度数组”的步骤包括：按照预设的排序方式对多台无线设备的特征值进行组合，形成一个信号强度数组。
- 如权利要求7所述的电子装置，其特征在于，所述预先确定的信号数据分类器的训练步骤包括：分别收集移动终端在多个采样点检测到的多台无线设备的设备信号数据，从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值；将在每个采样点收集的每台无线设备的特征值进行组合，生成该采样点对应的信号强度数组，并分配第一标记作为正样本数据；根据正样本数据推算一些不合理的信号强度数组，并分配第二标记作为负样本数据，组成样本集；将所述样本数据分成为第一比例的训练集及第二比例的验证集；利用所述训练集对随机森林模型进行训练，得到所述信号数据分类器；及利用所述验证集对所述信号数据分类器的准确性进行验证，若准确率大于或者等于预设准确率，则训练结束，或者，若准确率小于预设准确率，则增加样本数量并重新执行训练步骤。
- 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存储有基于信号数据筛选的定位程序，该定位程序被处理器执行时实现如下步骤：A1、接收移动终端上报的多台无线设备的设备信号数据；A2、从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值，组合每台无线设备的特征值生成一个信号强度数组；A3、判断所述信号强度数组中特征值的数量是否小于预设阈值，当大于或等于预设阈值时，保留该信号强度数组，当小于预设阈值时，过滤掉该信号强度数组、返回步骤A1；A4、将保留的该信号强度数组输入预先确定的信号数据分类器，根据信号数据分类器输出的结果判断所述信号强度数组是否合理；及A5、当信号数据分类器输出的结果为合理，按照预设的定位算法，根据该信号强度数组对应的设备信号数据计算所述移动终端的位置坐标。
- 如权利要求13所述的计算机可读存储介质，其特征在于，所述步骤 A2包括：从所述设备信号数据中获取n组信号强度数据，其中，每组信号强度数据中包含有多个无线设备的信号强度数据，n＞1；根据所述n组信号强度数据，分别统计每台无线设备对应的信号强度数据并进行过滤处理：计算每台无线设备的信号强度数据的偏离量，删除偏离量满足预设权重的信号强度数据；及计算每台无线设备经过滤处理后剩余的多个信号强度数据的平均值作为每台无线设备的特征值，将所述每组信号强度数组中的每台无线设备的特征值组合成一个信号强度数组。
- 如权利要求14所述的计算机可读存储介质，其特征在于，所述“计算每台无线设备的信号强度数据的偏离量”的步骤包括：计算该无线设备的信号强度数据的平均值，将信号强度数据与所述平均值之间的差值作为该信号强度数据的偏离量。
- 如权利要求15所述的计算机可读存储介质，其特征在于，所述“计算每台无线设备的信号强度数据的偏离量，删除偏离量满足预设权重的信号强度数据”的步骤包括：在对一台无线设备的信号强度数据进行过滤处理时，计算该无线设备的信号强度数据的偏离量；及根据该无线设备的信号强度数据的总数和所述预设权重确定要删除的信号强度数据的数量m，删除该无线设备的信号强度数据中偏离量最大的m个信号强度数据，其中，m＜n。
- 如权利要求13所述的计算机可读存储介质，其特征在于，所述“组合每台无线设备的特征值生成一个信号强度数组”的步骤包括：按照预设的排序方式对多台无线设备的特征值进行组合，形成一个信号强度数组。
- 如权利要求13所述的计算机可读存储介质，其特征在于，所述预先确定的信号数据分类器的训练步骤包括：分别收集移动终端在多个采样点检测到的多台无线设备的设备信号数据，从所述设备信号数据中提取每台无线设备的信号强度数据作为特征值；将在每个采样点收集的每台无线设备的特征值进行组合，生成该采样点 对应的信号强度数组，并分配第一标记作为正样本数据；根据正样本数据推算一些不合理的信号强度数组，并分配第二标记作为负样本数据，组成样本集；将所述样本数据分成为第一比例的训练集及第二比例的验证集；利用所述训练集对随机森林模型进行训练，得到所述信号数据分类器；及利用所述验证集对所述信号数据分类器的准确性进行验证，若准确率大于或者等于预设准确率，则训练结束，或者，若准确率小于预设准确率，则增加样本数量并重新执行训练步骤。
- 一种基于信号数据筛选的定位程序，其特征在于，该程序包括：接收模块、提取模块、第一判断模块、第二判断模块及计算模块。
- 如权利要求19所述的基于信号数据筛选的定位程序，其特征在于，该定位程序被处理器执行时可实现如权利要求1至6中任意一项基于信号数据筛选的定位方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711071306.6 | 2017-11-03 | ||
| CN201711071306.6A CN107966678B (zh) | 2017-11-03 | 2017-11-03 | 基于信号数据筛选的定位方法、电子装置及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019085337A1 true WO2019085337A1 (zh) | 2019-05-09 |
Family
ID=62000873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/076176 WO2019085337A1 (zh) | 2017-11-03 | 2018-02-10 | 基于信号数据筛选的定位方法、电子装置及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107966678B (zh) |
| WO (1) | WO2019085337A1 (zh) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110035392B (zh) * | 2018-11-09 | 2020-05-12 | 阿里巴巴集团控股有限公司 | 设备是否位于目标区域的识别方法及装置和电子设备 |
| CN110868703B (zh) * | 2019-10-24 | 2022-07-12 | 深圳数位大数据科技有限公司 | 应用程序信号质量的保证方法及装置 |
| CN112184941A (zh) * | 2020-09-28 | 2021-01-05 | 深圳技术大学 | 一种基于WiFi信号强度数据的考勤的方法及系统 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015103863A1 (zh) * | 2014-01-13 | 2015-07-16 | 中兴通讯股份有限公司 | 基于信号强度的位置信息提示方法及装置 |
| CN105101406A (zh) * | 2015-06-26 | 2015-11-25 | 上海汇纳信息科技股份有限公司 | 一种基于无线强度的室内定位方法及系统 |
| CN105704815A (zh) * | 2016-04-20 | 2016-06-22 | 重庆重邮汇测通信技术有限公司 | 一种基于基站空口数据的移动终端定位方法 |
| CN105792356A (zh) * | 2016-04-22 | 2016-07-20 | 西安理工大学 | 一种基于wifi的位置指纹定位方法 |
| CN107277777A (zh) * | 2016-04-06 | 2017-10-20 | 大唐移动通信设备有限公司 | 一种室内定位方法和装置 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101183148B (zh) * | 2007-12-07 | 2011-02-16 | 中国移动通信集团广东有限公司 | 一种无线定位方法和无线定位装置 |
| CN103974410B (zh) * | 2013-01-31 | 2017-05-31 | 西门子公司 | 用于定位的方法和装置 |
| US20160192126A1 (en) * | 2014-12-31 | 2016-06-30 | Silver Spring Networks, Inc. | System and method for tracking a device |
| EP3067432A1 (en) * | 2015-03-11 | 2016-09-14 | Deutsches Krebsforschungszentrum Stiftung des Öffentlichen Rechts | DNA-methylation based method for classifying tumor species of the brain |
| CN105657824B (zh) * | 2015-12-23 | 2018-12-11 | 杭州贤芯科技有限公司 | iBeacon定位系统及将移动终端作为临时基站的方法 |
| CN105873211A (zh) * | 2016-04-29 | 2016-08-17 | 安徽华米信息科技有限公司 | 一种定位方法及装置 |
| CN106255201A (zh) * | 2016-08-19 | 2016-12-21 | 北京羲和科技有限公司 | 一种室内定位方法及装置 |
| CN106919956A (zh) * | 2017-03-09 | 2017-07-04 | 温州大学 | 基于随机森林的脑电波年龄预测系统 |
-
2017
- 2017-11-03 CN CN201711071306.6A patent/CN107966678B/zh active Active
-
2018
- 2018-02-10 WO PCT/CN2018/076176 patent/WO2019085337A1/zh active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015103863A1 (zh) * | 2014-01-13 | 2015-07-16 | 中兴通讯股份有限公司 | 基于信号强度的位置信息提示方法及装置 |
| CN105101406A (zh) * | 2015-06-26 | 2015-11-25 | 上海汇纳信息科技股份有限公司 | 一种基于无线强度的室内定位方法及系统 |
| CN107277777A (zh) * | 2016-04-06 | 2017-10-20 | 大唐移动通信设备有限公司 | 一种室内定位方法和装置 |
| CN105704815A (zh) * | 2016-04-20 | 2016-06-22 | 重庆重邮汇测通信技术有限公司 | 一种基于基站空口数据的移动终端定位方法 |
| CN105792356A (zh) * | 2016-04-22 | 2016-07-20 | 西安理工大学 | 一种基于wifi的位置指纹定位方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107966678A (zh) | 2018-04-27 |
| CN107966678B (zh) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019085336A1 (zh) | 基于随机森林模型的定位方法、装置及存储介质 | |
| CN109947793B (zh) | 伴随关系的分析方法、装置和存储介质 | |
| WO2019019255A1 (zh) | 建立预测模型的装置、方法、预测模型建立程序及计算机可读存储介质 | |
| WO2019061988A1 (zh) | 基于无线设备的定位装置、方法及计算机可读存储介质 | |
| CN102968338B (zh) | 用于电子设备的应用程序分类的方法、装置及电子设备 | |
| WO2019085337A1 (zh) | 基于信号数据筛选的定位方法、电子装置及存储介质 | |
| CN105956518A (zh) | 一种人脸识别方法、装置和系统 | |
| US10798670B2 (en) | Information processing device, portable device, and system | |
| WO2019153600A1 (zh) | 电子装置、楼层定位方法和计算机可读存储介质 | |
| CN106937251B (zh) | 一种室内定位方法及服务器 | |
| WO2019205375A1 (zh) | 牲畜识别方法、装置及存储介质 | |
| CN109685092B (zh) | 基于大数据的聚类方法、设备、存储介质及装置 | |
| US20180157682A1 (en) | Image information processing system | |
| CN107679559A (zh) | 图像处理方法、装置、计算机可读存储介质和移动终端 | |
| CN109522923B (zh) | 客户地址聚合方法、装置及计算机可读存储介质 | |
| CN109145926A (zh) | 相似图片识别方法及计算机设备 | |
| JP2013242706A5 (zh) | ||
| US20230418976A1 (en) | Identifying personally identifiable information within an unstructured data store | |
| CN110288755A (zh) | 基于文本识别的发票检验方法、服务器及存储介质 | |
| CN109218987A (zh) | 信息处理方法、装置、终端及存储介质 | |
| CN106911554B (zh) | 一种历史信息展示方法及装置 | |
| JP2004258914A (ja) | タググルーピングシステム、タググルーピング方法 | |
| CN110446256B (zh) | 一种基于超宽带的基站实现定位的方法及设备 | |
| JP5956035B1 (ja) | 待ち時間推定システムおよび待ち時間推定方法 | |
| CN109858363B (zh) | 一种狗鼻纹特征点的检测方法、装置、系统及存储介质 |
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: 18874024 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: 18874024 Country of ref document: EP Kind code of ref document: A1 |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16/10/2020) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 18874024 Country of ref document: EP Kind code of ref document: A1 |