WO2020088644A1 - 定位方法及装置 - Google Patents

定位方法及装置 Download PDF

Info

Publication number
WO2020088644A1
WO2020088644A1 PCT/CN2019/114990 CN2019114990W WO2020088644A1 WO 2020088644 A1 WO2020088644 A1 WO 2020088644A1 CN 2019114990 W CN2019114990 W CN 2019114990W WO 2020088644 A1 WO2020088644 A1 WO 2020088644A1
Authority
WO
WIPO (PCT)
Prior art keywords
target terminal
wireless access
access points
terminal
multiple wireless
Prior art date
Application number
PCT/CN2019/114990
Other languages
English (en)
French (fr)
Inventor
廖学文
郑德舜
胡莹娟
田馨元
Original Assignee
华为技术有限公司
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
Priority claimed from CN201910114921.3A external-priority patent/CN111561921B/zh
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2020088644A1 publication Critical patent/WO2020088644A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • 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
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information

Definitions

  • Embodiments of the present application relate to the field of electronic technology, and in particular, to a positioning method and device.
  • pervasive computing has realized the fusion of the physical world and the information space, providing people with a wide range of computing and information services. Since most services are location-based services (LBS), location awareness in pervasive computing has become particularly important. Therefore, as people continue to increase the demand for pervasive computing, services based on location-aware computing It has also become diverse, and indoor positioning technology has been widely developed.
  • LBS location-based services
  • WiFi wireless fidelity
  • WiFi wireless fidelity
  • the indoor positioning technology based on WiFi signals mainly uses the collected WiFi signals as location fingerprints to locate through the fingerprint method.
  • the indoor positioning technology of WiFi signals is mainly stored in the database by using the signal offline. Since the signal is greatly affected by changes in the environment, the database is easily affected by the environment, which in turn affects the positioning accuracy.
  • the embodiments of the present application provide a positioning method and device. To improve positioning stability and positioning accuracy.
  • a terminal positioning method Receiving pedometer information sent by the target terminal and signal strengths of multiple wireless access points where the target terminal is located; based on the pedometer information and signals of multiple wireless access points where the target terminal is located Intensity to determine the current location of the target terminal.
  • the sensor signal and the WiFi signal can be combined as a location fingerprint to increase the characteristics of the location fingerprint, the positioning result is smoother, to reduce the impact of the environment on the positioning accuracy, and to improve the stability of the positioning technology, thereby improving the positioning Precision.
  • the method further includes: the foregoing step counting information includes one or more of the following: a walking direction, a step length, and an offset angle between two adjacent walking directions.
  • the foregoing determining the current location of the target terminal according to the step counting information and the signal strength of multiple wireless access points where the target terminal is located includes:
  • Is the emission probability of O 1 , O 2 , ..., O i , ..., O n to S 1 , S 2 , ..., S i , ..., S n , O i includes the step counting information of step i and step i The signal strength of multiple wireless access points where the target terminal is located;
  • S i ) is the transition probability from point S i + 1 to point S i ;
  • Pr (S 1 ) is the probability of the initial position S 1 .
  • the initial position may also be predefined, for example, the first hidden state may be defined as the entrance of the specified area. Alternatively, when there are multiple entrances in the designated area, the first hidden state may be determined in combination with the fingerprint positioning method.
  • l i, l j respectively represent coordinates of the position S i, S j is, d [(l j -l i ), step_length] shows a state S i, S j between the Euclidean distance and the step length difference, d (S j , S i ) represents the Euclidean distance between the states S i , S j , and D max is the distance threshold between two adjacent steps determined according to the pedestrian step size.
  • dis_state_wf i is the distance from S i to the positioning result determined by the signal strengths of multiple wireless access points where the target terminal is located at the i-th step and the signal strengths of multiple wireless access points determined in advance at the reference point
  • ⁇ i is the offset angle of the row direction between the adjacent i-th step and i-1 step
  • ⁇ 0 is the error threshold, ⁇ 0 ⁇ 20 ° ⁇ 45 °.
  • the update frequency of the signal strength information of the wireless access point is lower than the update frequency of the sensor information; the method further includes: performing pedestrian dead reckoning based on the step counting information, and determining the corresponding a position; the first position and the same S n, S n is determined that the current location of the target terminal;
  • the PDR is used to estimate the updated position status, which improves the continuity of positioning and the positioning accuracy.
  • it further includes: sending the position of the target terminal after the Nth step of user movement to the target terminal. Or, provide the target terminal with a service based on the position of the target terminal after the Nth step of the user's movement. Based on this, it is possible to provide terminals with high stability and high accuracy positioning, or positioning-based services.
  • a positioning method includes: when the detected user movement is at step N, step counting information of the user movement at step N and the signal strength of multiple wireless access points where the target terminal is located are sent to the server, so that the server can Step counting information and signal strengths of multiple wireless access points where the target terminal is located determine the position of the Nth step of the movement of the target terminal; the receiving server sends the position of the Nth step of the movement of the target terminal.
  • the sensor signal and the WiFi signal can be combined as a location fingerprint to increase the characteristics of the location fingerprint, the positioning result is smoother, to reduce the impact of the environment on the positioning accuracy, and to improve the stability of the positioning technology, thereby improving the positioning Precision.
  • the terminal further includes: when the position of the target terminal after the received user movement step N is the same as the position of the target terminal after the received user movement step N-1, then The step counting information after the Nth step of the user's movement obtains the current position of the target terminal after the Nth step of the user's movement through the pedestrian dead reckoning.
  • the terminal can combine the fingerprint positioning result provided by the server and its own PDR result, so as to increase the update frequency of the positioning result and improve the positioning accuracy.
  • a terminal positioning device receiving unit for receiving step counting information sent by a target terminal and signal strengths of multiple wireless access points where the target terminal is located;
  • the positioning unit is configured to determine the current location of the target terminal according to the step counting information and signal strengths of multiple wireless access points where the target terminal is located.
  • the step counting information includes one or more of the following:
  • the positioning unit is specifically used for:
  • Is the emission probability of O 1 , O 2 , ..., O i , ..., O n to S 1 , S 2 , ..., S i , ..., S n , O i includes the step counting information of step i and step i The signal strength of multiple wireless access points where the target terminal is located;
  • S i ) is the transition probability from point S i + 1 to point S i ;
  • Pr (S 1 ) is the probability of the initial position S 1 .
  • l i, l j respectively represent coordinates of the position S i, S j is, d [(l j -l i ), step_length] shows a state S i, S j between the Euclidean distance and the step length difference, d (S j , S i ) represents the Euclidean distance between the states S i , S j , and D max is the distance threshold between two adjacent steps determined according to the pedestrian step size.
  • dis_state_wf i is the distance from S i to the positioning result determined by the signal strengths of multiple wireless access points where the target terminal is located at the i-th step and the signal strengths of multiple wireless access points determined in advance at the reference point ;
  • ⁇ i is the offset angle of the row direction between the adjacent i-th step and i-1 step;
  • ⁇ 0 is the error threshold, ⁇ 0 ⁇ 20 ° ⁇ 45 °.
  • the update frequency of the signal strength information of the wireless access point is lower than the update frequency of the sensor information
  • the device also includes:
  • the calculation unit is used to calculate the pedestrian dead reckoning according to the step counting information and determine the first position corresponding to the target terminal;
  • the sending unit is configured to send the current position of the target terminal to the target terminal.
  • a terminal positioning device in a fourth aspect, includes:
  • the sending unit is configured to send the step counting information of the user movement step N and the signal strength of the multiple wireless access points where the target terminal is located when the detected user movement is step N, so that the server can The step counting information and the signal strengths of the plurality of wireless access points where the target terminal is located determine the position of the target terminal movement step N;
  • the receiving unit is configured to receive the server sends the position of the target terminal motion step N.
  • the estimation unit is configured to: when the position of the target terminal after the received user movement step N is the same as the position of the target terminal after the received user movement step N-1, based on the user movement step N After the step counting information is obtained, the current position of the target terminal after the Nth step of the user's movement is calculated through pedestrian dead reckoning. .
  • an embodiment of the present invention provides a device.
  • the device includes a transceiver, a processor, and a memory; the transceiver is used to communicate with other devices, for example, the device can be a server, and the transceiver of the server is used to communicate with a terminal, and the device can also be a terminal, which transmits and receives
  • the processor is used to communicate with the server, and the memory is used to store the program; the processor is used to execute the program stored in the memory to control the device to execute the method described in any one of the first aspect or the second aspect.
  • a computer-readable storage medium is provided, and a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to implement any one of the first aspect or the second aspect method.
  • a computer program product containing instructions is provided.
  • the instructions of the computer program product run on a computer, the computer is caused to perform the method described in any one of the first aspect or the second aspect.
  • the sensor signal and the WiFi signal can be combined as a location fingerprint to increase the characteristics of the location fingerprint, the positioning result is smoother, to reduce the impact of the environment on the positioning accuracy, and to improve the stability of the positioning technology, thereby improving the positioning Precision.
  • FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a positioning method provided by an embodiment of the present application.
  • Figure 3 is an example of an application scenario
  • FIG. 4 is a schematic flowchart of a positioning method provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a terminal positioning device according to an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a terminal positioning device according to an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a server provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
  • this application proposes a positioning method and device.
  • the sensor signal and the WiFi signal can be combined as a location fingerprint to increase the characteristics of the location fingerprint to reduce the impact of the environment on the positioning accuracy and improve the stability of the positioning technology, thereby improving the positioning accuracy.
  • the positioning result obtained by WiFi signal positioning technology and the positioning result obtained by sensor positioning technology can also be integrated to obtain the final positioning result, which can reduce the cumulative error of sensor positioning and reduce the positioning result caused by WiFi signal fluctuations. Stability issues, etc.
  • This application is applicable to indoor scenes such as offices, shopping malls, airports, and railway stations.
  • a certain number of WAPs are set in this scene, and the WiFi signal density transmitted by the WAP is sufficient.
  • the number of WAPs that a terminal can detect in any indoor space location is greater than 5.
  • the terminal may send the acquired WiFi signal and sensor information to the server, and the server performs positioning determination, and returns the determined positioning result to the terminal.
  • FIG. 1 is a schematic diagram of an operation scenario provided by an embodiment of the present invention.
  • this scenario includes WAP, terminal, and server 130.
  • WAP Wireless Fidelity
  • terminal terminal
  • server 130 There may be multiple WAPs, and any one of the multiple WAPs sends a WiFi signal from the designated area 140 to the designated area 140, such as WAP111, or may send a WiFi signal to the designated area 140 within the designated area 140, such as WAP112.
  • the server 130 may provide positioning services for terminals in the designated area 140, for example, the server 130 provides location-based services or positioning services for the terminal 121 at the location 141 or the terminal 122 at the location 142.
  • the designated area 140 may be an indoor scene such as an office, a shopping mall, an airport, and a train station.
  • the designated area may include obstacles, such as walls, office supplies, or green plants.
  • FIG. 2 is a schematic flowchart of a positioning method according to an embodiment of the present application. This method can be applied in the scenario shown in FIG. 1. As shown in FIG. 2, the method may specifically include:
  • M hidden states in a specified area may be determined in advance based on the step size, where M is an integer greater than zero.
  • the size of the designated area is the designated area shown in FIG. 1, and the position of the designated area except for obstacles is divided into grids of the same size according to a step length of 0.8 meters, and the intersections of the grids are in different hidden states. Location point.
  • the signal strength of multiple wireless access points where the terminal of the reference point is located can also be collected in advance, so as to determine the location of the terminal during positioning according to the signal strength of multiple wireless access points where the terminal of the reference point is located
  • the transmission probability between the signal strength and hidden state of multiple wireless access points at a location is calculated.
  • the interval of the reference point may be an integer multiple of the step size.
  • the reference point interval can be 4-6 times the step size.
  • the collected signal strengths of the multiple wireless access points where the terminal is located are stored in the database.
  • the signal strengths of the multiple wireless access points where the terminal is located also need to be pre-processed, for example, in each
  • the signal strength of multiple wireless access points collected by the same wireless access point for multiple groups of terminals at the same reference point can be determined in advance The average value of the signal strength.
  • Each reference point can collect the signal strength of multiple wireless access points where the terminal is located in multiple directions, and the signal strength of multiple wireless access points where each group of terminals is located in each direction can be The signal strengths of multiple wireless access points where all terminals are located in all directions of the reference point are averaged, and the average value is stored in a database.
  • the average value of the signal strengths of multiple wireless access points where all WAP terminals of each reference point are located constitutes a set of vectors, and the set of vectors can be used as a location fingerprint of the reference point.
  • the terminal sends the sent pedometer information to the server and the signal strength of multiple wireless access points where the target terminal is located, so that the server can send the pedometer information and the target according to the sent pedometer information Locate the signal strength of multiple wireless access points where the terminal is located.
  • the pedometer information may be information obtained through sensor information, for example, the pedometer information may be collected data of sensors such as accelerometers, gyroscopes, or electronic compasses, or user motion information that may be determined based on sensor data
  • the motion information may include a walking direction, a step length, an offset angle of the walking directions of two adjacent steps, and so on.
  • the terminal can detect the user's movement through the sensor,
  • the terminal may perform gait detection through an accelerometer, and after determining that the user is taking a step, the information of the accelerometer, gyroscope, and electronic compass may be sent to the server.
  • the terminal may perform gait detection through an accelerometer. After determining that the user is taking a step, the terminal may calculate the movement direction based on the information of the accelerometer, gyroscope, and electronic compass, and send the movement direction to the server. In addition, the step direction can also be calculated from the accelerometer, and the estimated step length can be sent to the server.
  • the terminal when the terminal line is continuously positioned, the terminal quickly scans the surrounding WiFi signals, and uploads the signal strengths of the multiple wireless access points where the scanned terminal is located to the server.
  • the terminal can collect the sensor information of the terminal during the user's movement in real time, and determine the number of steps, the step length, and the direction according to the collected sensor information.
  • the sampling interval of the WiFi signal is usually 50 milliseconds
  • the sampling frequency of the accelerometer and compass is usually 50 Hz.
  • the acceleration sensor can be used to detect the number of walking steps. Whenever a walking step is detected, it can be counted as the Nth step.
  • the compass and gyroscope can be used to determine the movement direction of the Nth step.
  • the movement direction of the Nth walking and the signal strengths of the multiple wireless access points where the terminal is located are sent to the server.
  • the server receives the sensor information sent by the target terminal after the Nth step of user motion and the signal strength of multiple wireless access points where the terminal is located. After receiving the above information, the server can implement positioning through the following S220-S230.
  • S220 Determine the current location of the target terminal according to the step counting information and signal strengths of multiple wireless access points where the target terminal is located.
  • the server may determine the transmission probability of the M hidden states corresponding to each step in the first N steps according to the sensor information of the first N steps and the signal strength of multiple wireless access points where the terminal is located.
  • the positioning problem can be transformed into solving the best hidden state sequence corresponding to the first N steps according to the sensor information of the first N steps and the signal strength of multiple wireless access points where the terminal is located, for example, based on The hidden Markov model or a model based on the hidden Markov model evolves to estimate the best hidden state sequence.
  • each observation vector the observation vector includes sensor information and signal strengths of multiple wireless access points where the terminal is located
  • the possible The location point is the M hidden states
  • likelihood probability that is, the transmission probability
  • the transition probability between the hidden state states needs to be determined
  • the hidden state sequence corresponding to the maximum probability is solved by the transmission probability, the transition probability, and the initial probability , That is, the best position point sequence, for example, the optimal position point sequence corresponding to the probability maximization is solved by the Viterbi algorithm.
  • the hidden probability of transmission can be determined according to the sensor information and the signal strength of multiple wireless access points where the terminal is located, to improve the accuracy of the transmission probability.
  • the initial transmission probability of the hidden state can be determined according to the signal strengths of multiple wireless access points where the terminal is located, and whether the user's movement direction determined by the sensor information and the corresponding direction between the hidden states match to adjust The initial launch probability of the hidden state gives the final launch probability.
  • the first probability of the M hidden states corresponding to each step in the first N steps may be determined according to the signal strengths of multiple wireless access points where the terminal is located in each step in the previous N steps;
  • the first N step The second probability of the M hidden states corresponding to each step; where the first direction of the i-th step is the direction determined based on the sensor information of the i-th step, and the second direction of the k-th hidden state of the i-th step is the k-th.
  • step i is any one of the first N steps, and the kth hidden state is any one of the M hidden states;
  • the first probability and the second probability of the M hidden states corresponding to each of the first N steps are multiplied to determine the transmission probability of each of the M hidden states corresponding to the first N steps.
  • the hidden state corresponding to the initial position may be known or determined according to the signal strength of multiple wireless access points where the terminal is located.
  • the server may receive the signal strength of multiple wireless access points at the location of the initial location terminal sent by the target terminal; the server may determine the signal strength of the multiple wireless access points at the location of the initial location terminal,
  • the first hidden state is determined by the proximity algorithm KNN, and the first hidden state is the hidden state corresponding to the initial position.
  • the initial probability of the first hidden state corresponding to the initial position of the target terminal is 1, the initial position is the position corresponding to the number of steps N equal to 0, and among the aforementioned M hidden states The initial probability of the hidden state other than the first hidden state is 0.
  • the transition probability between hidden states can be determined according to the characteristics of the hidden states themselves. Specifically, the transition probability between hidden states is determined according to the difference between the distance between hidden states and the step size. Among them, for example, due to the limitation of their own ability, the distance of each pedestrian is usually not much different. If the distance between the hidden states is greater than the step size, the transition between the two states will not occur. That is, the probability is 0. Correspondingly, the closer the distance between the hidden states is to the step size, the greater the transition probability. Based on this, the method may include: determining the difference between the distance between the jth hidden state and the fth hidden state and the step size, and the relationship between the difference and the distance threshold Probability of state transition between f hidden states. Among them, the jth hidden state is any one of the M hidden states, and the fth hidden state is any one of the M hidden states.
  • the movement according to the movement of pedestrians in the room usually has a certain regularity, for example, the probability of movement before the office and the pantry is the largest. It can count the distribution of the movement law of multiple users moving indoors. According to the movement law, determine the directional probability between two hidden states. By multiplying the directional probability and the initial state transition probability determined according to the relationship with the step size, we can get The final state transition probability. Based on this, the embodiments of the present invention may further include:
  • the third probability is determined by the difference between the distance and step between the jth hidden state and the fth hidden state, and the relationship between the difference and the distance threshold;
  • the direction probability of the jth hidden state and the fth hidden state is determined according to the historical movement rules of users in the specified area, the jth hidden state is any of the M hidden states, and the fth hidden state is the M hidden states Any one of the states.
  • the server multiplies the transmission probability of the M hidden states corresponding to each of the first N steps, the transition probability between the M hidden states, and the initial probability of the M hidden states, and selects the highest probability A hidden state sequence, and determining the position of the target terminal after the Nth step of user movement according to the first hidden state sequence, wherein the transition probability between hidden states is based on the distance between the hidden states and the step size The difference is determined.
  • the transition probability between the M hidden states, and the initial overview of the M hidden states can be used to solve the corresponding The best hidden state sequence.
  • the optimal position sequence can be solved by Viterbi algorithm. After determining the best hidden state sequence corresponding to the first N steps, the position corresponding to the Nth step of the user movement may be determined according to the best hidden state sequence corresponding to the first N steps.
  • the position coordinates corresponding to the target terminal may be determined according to the hidden state corresponding to the Nth step in the best hidden state sequence corresponding to the first N steps.
  • PDR Pedestrian Dead Reckoning
  • the second hidden state sequence is a hidden state sequence determined after step N-1 of user movement
  • the position of the target terminal after the Nth step of user movement determined according to the first hidden state sequence is the same as the position of the target terminal after the N-1th step of user movement determined according to the second hidden state sequence, then according to the user
  • the sensor information after the Nth step of the movement obtains the target terminal position after the Nth step of the user's movement through the pedestrian dead reckoning PDR;
  • the position of the target terminal after the Nth step of user movement determined according to the first hidden state sequence is different from the position of the target terminal after the N-1th step of user movement determined according to the second hidden state sequence, then It is determined that the position of the hidden state corresponding to the Nth step in the first hidden state sequence is the position of the target terminal after the user moves the Nth step.
  • the server sends the location of the target terminal after the Nth step of the user's movement to the target terminal.
  • the server provides the target terminal with a service based on the location of the target terminal after the Nth step of the user's movement.
  • the target terminal after receiving the position sent by the server after the Nth step of the user movement, can provide a positioning service for the user or other applications according to the position. For example, users can be provided with navigation services within a specified area.
  • the service based on the location of the target terminal after the Nth step of the user's movement in S230b may include a variety of services, such as pushing nearby merchant information, waiting room information, and train number information corresponding to the waiting room for the terminal, or for the user.
  • Provide location services such as alarms (eg, fire alarms), complaints, etc.
  • the position of the target terminal sent by the server to the terminal after the Nth step of user movement may be obtained by combining the PDR technology, or may be obtained by not combining the PDR technology.
  • the target terminal may combine the PDR technology to obtain the final positioning location coordinates, or update the positioning location coordinates in real time according to the PDR technology.
  • the target terminal can determine whether the position of the target terminal after the received user movement step N is the same as the position of the target terminal after the received user movement step N-1; when the target terminal receives the user movement
  • the position of the target terminal after step N is the same as the position of the target terminal after step N-1 of the received user motion
  • the user information after step N of the user motion is obtained through line PDR according to the sensor information after step N of the user motion Target terminal location.
  • the hidden state adopts the virtual hidden state mode.
  • the distance between the positions of different hidden states is the step size.
  • the total number of hidden states depends on the pedestrian step size and the size of the designated area. This makes the hidden state more inconsistent with the characteristics of the user, and the positioning accuracy is higher.
  • the interval of the reference points for offline acquisition of WiFi signal strength is an integer multiple of pedestrian steps (the integer is greater than 1). In order to achieve a balance between positioning performance and acquisition workload, the multiple is recommended to be 4-6.
  • the signal strength of the wireless access point that can be collected at each reference point comes from an existing AP in the environment, excluding WAPs whose WiFi signal strength value is below a threshold (for example, -80 dBm).
  • a threshold for example, -80 dBm.
  • Each reference point is divided into 4 directions, and a signal strength sample of a wireless access point of 50 ms is collected in each direction at a sampling interval of 200 ms.
  • preprocessing is performed. Determine the average value of the signal strength (rssi 1 , rssi 2 , ..., rssi n ) of multiple groups of wireless access points collected by the same AP on each reference point
  • the calculation formula is: Store the average of each reference point in the database.
  • the designated area is divided into k grids, and the intersection of each grid is regarded as the possible real position state of the user's movement, that is, the hidden state, denoted as S i , i ⁇ ⁇ 1,2,..., k ⁇ ;
  • S i the possible real position state of the user's movement
  • i the hidden state
  • k the relevant information corresponding to the grid
  • the hidden state of the user moving track corresponding measurement vectors ⁇ O 1, O 2, ... , O it, ..., O n> can be expressed as a transmission probability Pr (O 1, O 2 , ..., O i , ..., O n
  • the trajectory of the mobile user can be determined according to the observation value information of the location point, that is, finding the hidden state sequence such that the probability Pr (S 1 , S 2 , ..., S i , ..., S n
  • Pr (O 1, O 2 , ..., O i, ..., O n) represents the probability of the observation sequence.
  • Pr (O 1, O 2 , ..., O i, ..., O n) represents the probability of the observation sequence.
  • the Bayesian criterion there are:
  • the hidden state sequence of the mobile user's trajectory can be expressed as follows:
  • the hidden state of the mobile user at the current moment is only related to the hidden state at the previous moment, not related to the hidden state at other moments, and the transition probability between different hidden states is predetermined.
  • the determination of the trajectory of the mobile user is to solve the hidden state sequence corresponding to the maximum probability of the following formula:
  • l i , l j represent the position coordinates of the hidden states S i , S j respectively, and d [(l j -l i ), step_length] represents the Euclidean distance and the step size between the states S i , S j The difference, d (S j , S i ) represents the Euclidean distance between states S i , S j .
  • D max 4.8 meters.
  • the emission probability refers to the probability that the observed value behaves as a hidden state.
  • the emission probability is determined by the positioning result of each step of the WiFi fingerprint method and the data from the sensor when pedestrians walk online.
  • the specific implementation is as follows: the observation value is the WiFi positioning result, and the distance between the location result of the WiFi location fingerprint method at time t and the hidden state i is dis_state_wf i .
  • the sensor heading angle at the current time t be ⁇ t and the hidden state i position coordinates (x i , y i ) to the location result at the last time (location_x t-1 , location_y t-1 )
  • the included angle is ⁇ i ;
  • ⁇ i is the offset angle between the measured heading angle ⁇ t and ⁇ i ; after experiments, the offset angle ⁇ i will have a certain range under different experimental environments and different terminal types.
  • the range becomes the error threshold, which is expressed by ⁇ 0.
  • ⁇ 0 ⁇ 20 ° ⁇ 45 ° the value of ⁇ 0 is a constant under the conditions of a given experimental environment and given terminal;
  • the designated area is shown in Figure 3.
  • the size of the designated area is 41.26m ⁇ 26.10m.
  • the designated area includes obstacles such as offices and workstations.
  • the signal strength of the wireless access point is collected.
  • the interval of the reference points collected is four times (3.2 meters) the step length (0.8 meters). Due to space constraints, the interval between the reference points of the two wings in the designated area is three times (2.4 meters ) Or twice (1.6 meters), there are a total of 73 reference points in the designated area, the signal strength of the wireless access point collected at each reference point comes from the existing WAP in the environment, excluding the wifi signal strength below -80dBm WAP.
  • Each reference point is divided into 4 directions, and a 50-second signal strength sample of the wireless access point is collected in each direction at a sampling interval of 200 ms.
  • the collected information is preprocessed. For each set of RSSI information collected by the same WAP, rssi 1 , rssi 2 , ..., rssi n at each reference point, determine their average value
  • the calculation formula is: In this way, the average value of samples in all directions of each reference point is determined and stored in the database. Among them, the average information of all WAPs of each reference point constitutes a set of vectors, which are used as location fingerprints.
  • the terminal quickly scans the signal strength of multiple wireless access points in the surrounding WAP.
  • the sampling interval of the signal strength of the multiple wireless access points where the terminal is located is 50 ms
  • the sampling frequency of the sensor data is 50 Hz.
  • the terminal sends the collected sensor information and the signal strength of multiple wireless access points where the terminal is located to the server.
  • the server After receiving the above information, the server performs real-time positioning calculation.
  • the details are as follows:
  • the server determines the positioning result according to the sensor information and the signal strength of multiple wireless access points where the terminal is located in combination with the fingerprint method
  • the server determines the positioning result based on the sensor information and the signal strength of multiple wireless access points where the terminal is located in combination with the fingerprint method, the following steps are specifically included:
  • the designated area is divided into grids of the same size according to the step length of 0.8 meters, and the intersection points of the grids are the positions of different hidden states.
  • a total of 638 hidden states are divided, and the positioning problem is equivalent to 638 hidden states To find the best hidden state sequence.
  • the initial probability of the hidden state can be determined according to the known initial position
  • the transition probability between the hidden states can be determined by the formula (6)
  • the transmission probability can be determined by the formula (10).
  • the Viterbi algorithm is combined with formula (5) to determine the hidden state sequence with the highest probability.
  • the position coordinates of the hidden state corresponding to the current moment is the positioning result obtained by the fingerprint positioning method.
  • S440 Determine whether the positioning result by the fingerprint method at the current moment is the same as the positioning result by the fingerprint method at the previous moment. If the current fingerprint positioning result is the same as the previous fingerprint positioning result, the PDR positioning result in S420 is taken as the user's current location; if the current positioning method using the fingerprint method is different from the previous positioning method, The positioning result in S430 is used as the current location of the user.
  • the embodiment of the present application considers the indoor positioning problem from the perspective of a hidden Markov model (HMM), and converts the problem of finding the optimal position point sequence into a Viterbi algorithm to solve the optimization problem.
  • HMM hidden Markov model
  • the present invention adds information such as sensor direction to the In the algorithm, in addition, for the problem that the signal strength update frequency of multiple wireless access points where the terminal is located in the actual engineering scenario is lower than the motion sensor update frequency, improvements are considered while adding direction information.
  • the embodiment of the present application combines the pedestrian motion information and improves the state transition probability and emission probability of the hidden Markov model by merging terminal sensor data, which is more realistic, makes the positioning trajectory closer to the real trajectory, and the positioning accuracy is higher;
  • the idea of virtual hidden state quantification reduces the workload of offline database sampling.
  • FIG. 5 is a schematic structural diagram of a terminal positioning device according to an embodiment of the present application.
  • the device may be used to execute the method executed by the server in the embodiment shown in FIG. 2 or FIG. 4.
  • the M hidden states in the designated area are determined in advance based on the step size, and the M is an integer greater than zero.
  • the device includes:
  • the receiving unit 501 is configured to receive step counting information sent by the target terminal and signal strengths of multiple wireless access points where the target terminal is located;
  • the positioning unit 502 is configured to determine the current location of the target terminal according to the step counting information and signal strengths of multiple wireless access points where the target terminal is located.
  • the step counting information includes one or more of the following:
  • the positioning unit is specifically used for:
  • Is the emission probability of O 1 , O 2 , ..., O i , ..., O n to S 1 , S 2 , ..., S i , ..., S n , O i includes the step counting information of step i and step i The signal strength of multiple wireless access points where the target terminal is located;
  • S i ) is the transition probability from point S i + 1 to point S i ;
  • Pr (S 1 ) is the probability of the initial position S 1 .
  • l i, l j respectively represent coordinates of the position S i, S j is, d [(l j -l i ), step_length] shows a state S i, S j between the Euclidean distance and the step length difference, d (S j , S i ) represents the Euclidean distance between the states S i , S j , and D max is the distance threshold between two adjacent steps determined according to the pedestrian step size.
  • dis_state_wf i is the distance from S i to the positioning result determined by the signal strengths of multiple wireless access points where the target terminal is located at the i-th step and the signal strengths of multiple wireless access points determined in advance at the reference point ;
  • ⁇ i is the offset angle of the row direction between the adjacent i-th step and i-1 step;
  • ⁇ 0 is the error threshold, ⁇ 0 ⁇ 20 ° ⁇ 45 °.
  • the update frequency of the signal strength information of the wireless access point is lower than the update frequency of the sensor information
  • the device also includes:
  • the calculation unit is used to calculate the pedestrian dead reckoning according to the step counting information and determine the first position corresponding to the target terminal;
  • it also includes:
  • the sending unit is configured to send the current position of the target terminal to the target terminal.
  • FIG. 6 is a schematic structural diagram of a terminal positioning device according to an embodiment of the present application.
  • the apparatus may be used to execute the method executed by the terminal in the embodiment shown in FIG. 2 or FIG. 4.
  • the device includes:
  • the sending unit 601 is configured to send the step counting information of the user movement step N and the signal strength of multiple wireless access points where the target terminal is located to the server when the detected user movement is step N, so that the server Determine the position of the Nth step of the movement of the target terminal according to the step counting information and the signal strengths of multiple wireless access points where the target terminal is located;
  • the receiving unit 602 is configured to receive the server sends the position of the target terminal motion step N.
  • it also includes:
  • the estimation unit 603 is configured to, when the position of the target terminal after the received user movement step N is the same as the position of the target terminal after the received user movement step N-1, based on the user movement
  • the step counting information after the step obtains the current position of the target terminal after the Nth step of the user movement through the pedestrian dead reckoning.
  • the server 700 specifically includes: a transceiver 701, a processor 702, and a memory 703.
  • the transceiver 701, the processor 702, and the memory 703 may be connected through a bus.
  • the server can be used to implement the functions of the server in the embodiment shown in FIG. 2 or FIG. 4.
  • the transceiver 701 is used to support the server to send and receive information between the terminal or other servers in the foregoing embodiments.
  • the data and signaling messages are processed by the processor 702 and sent to the terminal by the transceiver 701.
  • the data and signaling from the terminal are received via the transceiver 701 and processed by the processor 702 to obtain the data and signaling sent by the terminal.
  • the processor 702 may control the sending device 700 to perform the processing procedures related to the sending end and / or other procedures used in the technology described in this application in the embodiment shown in FIG. 2 or FIG. 4.
  • the processor 702 is used to perform one or more steps in steps S220, S230, or S410-S440 in the embodiments shown in FIGS. 2 and 4, and the transceiver 701 is used to perform the steps shown in FIGS. 2 and 4.
  • the memory 703 is used to store program codes and data of the terminal.
  • FIG. 8 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
  • the terminal 800 specifically includes: a transceiver 801, a processor 802, a memory 803, a WiFi module 804, and a sensor 805.
  • the transceiver 801, the processor 802, the memory 803, the WiFi module 804, and the sensor 805 may be connected through a bus.
  • the network device may be used to implement the functions of the sending end in the embodiment shown in FIG. 2 or FIG. 4. For example, but not limited to mobile phones, computers, wearable devices, etc.
  • the transceiver 801 is used to support sending and receiving information between the terminal and the server in the foregoing embodiment.
  • the data and signaling messages are processed by the processor 802 and sent to the server by the transceiver 801.
  • the data and signaling from the server are received via the transceiver 801 and processed by the processor 802 to obtain the data and signaling sent by the server.
  • the WiFi module 804 is used to determine the signal strength of multiple wireless access points where the terminal is located, and the sensor 805 is used to determine sensor information.
  • the sensor 805 includes one or more of an accelerometer, a gyroscope, an electronic compass, or the like.
  • the processor 802 may control the terminal 800 to execute the processing procedures related to the terminal in the embodiments shown in FIG. 2 or FIG. 4 and / or other procedures for the technology described in this application.
  • the transceiver 801 is used to perform steps such as S210 in the embodiments shown in FIGS. 2 and 4.
  • the memory 803 is used to store program codes and data of the terminal.
  • An embodiment of the present application provides a chip.
  • the chip includes a processor and a memory; the memory is used to store a program; and the processor is used to execute the program stored in the memory to perform the method described in the foregoing method embodiments.
  • the present invention may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it can be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, all or part of the processes or functions according to the embodiments of the present invention are generated.
  • the computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable medium to another computer-readable medium, for example, the computer instructions may be from a website site, computer, server, or data center via wired (For example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) to another website, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device including a server, a data center, and the like integrated with one or more available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state drive), or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Automation & Control Theory (AREA)
  • Navigation (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

一种定位方法及装置，该方法包括：向服务器发送计步信息和目标终端所处位置的多个无线接入点的信号强度（S210）；根据计步信息和目标终端所处位置的多个无线接入点的信号强度，确定目标终端的当前位置（S220）。该方法可以结合计步信息以及无线接入点的信号强度进行定位，以此增加位置指纹的特征，定位结果更平滑，降低环境对定位精度的影响并提高定位技术的稳定性，从而提高定位精度。

Description

定位方法及装置
本申请要求于2018年11月1日提交中国国家知识产权局，申请号为CN 201811293931.X、发明名称为“佩戴检测设备”的中国专利申请，并要求于2019年2月14日提交中国国家知识产权局，申请号为CN 201910114921.3、发明名称为“定位方法及装置”的中国专利申请，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及电子技术领域，尤其涉及一种定位方法及装置。
背景技术
随着无线通信、计算机与感知技术的发展，普适计算实现了物理世界和信息空间的融合，为人们提供广泛的计算和信息服务。由于大多数服务都是基于位置的服务(location based services，LBS)，普适计算中的位置感知变得尤为重要，因此，随着人们对普适计算需求的不断增加，基于位置感知计算的服务也变得多种多样，室内定位技术得到广泛的发展。
由于无线局域网分布广泛，与其它室内定位技术相比，基于无线保真(wireless-fidelity，WiFi)信号的定位即使具有建设成本低的优势，因此基于WiFi信号的室内定位技术的应用与服务成为近来来室内定位的研究热点。基于WiFi信号的室内定位技术主要是将采集的WiFi信号作为位置指纹，通过指纹法进行定位，但是，由于室内复杂环境的影响使得WiFi信号的衰减难以预测，从而造成定位性能不够稳定，另外，基于WiFi信号的室内定位技术主要通过离线采用信号存储到数据库中，由于信号受环境的变化影响较大，所以数据库易受环境的影响，进而影响定位精度。
发明内容
本申请实施例提供了一种定位方法及装置。以提高定位稳定性以及定位精度。
第一方面，提供了一种终端定位方法。接收目标终端发送的计步信息和所述目标终端所处位置的多个无线接入点的信号强度；根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度，确定所述目标终端的当前位置。通过本申请实施例，可以结合传感器信号以及WiFi信号作为位置指纹，以此增加位置指纹的特征，定位结果更平滑，以降低环境对定位精度的影响，以及提高定位技术的稳定性，从而提高定位精度。
在一个可能的设计中，该方法还包括：前述计步信息包括下述一项或多项：步行方向、步长以及相邻两步步行方向偏移角。
在另一个可能的设计中，前述根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度，确定所述目标终端的当前位置包括：
求解如下公式概率最大的位置序列S 1,S 2,…,S i,…,S n，其中S n为所述目标终端的当前位置：
Figure PCTCN2019114990-appb-000001
其中，
Figure PCTCN2019114990-appb-000002
为O 1,O 2,…,O i,…,O n到S 1,S 2,…,S i,…,S n的发射概率，O i包括第i步的计步信息和第i步时目标终端所处位置的多个无线接入点的信号强度；
Pr(S i+1|S i)为点S i+1到点S i的转移概率；
Pr(S 1)为初始位置S 1的概率。通过本申请实施例可以实现，依据目标终端提供的无线接入点的信号强度信息以及计步信息，通过位置指纹法进行定位，使得定位更灵活。另外，初始位置还可以预定义，例如，该第一隐状态可以定义为该指定区域的入口。或者，该指定区域有多个入口时，可以结合指纹定位法，确定第一隐状态。
在另一个可能的设计中，
Figure PCTCN2019114990-appb-000003
其中，l i,l j分别表示S i,S j的位置坐标，d[(l j-l i),step_length]表示状态S i,S j间欧式距离与步长的差值，d(S j,S i)表示状态S i,S j间欧式距离，D max为根据行人步长确定的相邻两步之间的距离阈值。通过本申请实施例，利用传感器方向信息与行人运动规律，对可能的隐状态做出限制，从而使得对可能的隐状态的确定更合理，定位精度更高。
在另一个可能的设计中，
Figure PCTCN2019114990-appb-000004
其中，dis_state_wf i为根据第i步时目标终端所处位置的多个无线接入点的信号强度以及预先在基准点确定的多个无线接入点的信号强度确定的定位结果到S i的距离；Δθ i为相邻第i步与第i-1步的行方向偏移角；θ 0为误差门限，θ 0∈20°～45°。通过本申请实施例可以实现，对隐状态之间的转移概率，依据行人运动规律进行限制，使得在进行定位时，定位结果更符合实际，定位结果更准确，精度更高。
在另一个可能的设计中，无线接入点的信号强度信息的更新频率低于传感器信息的更新频率；所述方法，还包括：根据计步信息进行行人航位推算，确定目标终端对应的第一位置；所述第一位置与S n相同时，则确定所述S n为所述目标终端的当前位置；
当所述第一位置与S n不同时，则确定所述第一位置为所述目标终端的当前位置。通过本申请实施例，可以实现行人航位推算定位技术和位置指纹定位技术的融合，在位置指纹法定位更新频率较低时利用PDR估计更新位置状态，提高定位的连续性，定位精度更高。
在另一个可能的设计中，还包括：向目标终端发送用户运动第N步后的目标终端的位置。或者，向目标终端提供基于用户运动第N步后的目标终端的位置的服务。基于此，可以为终端提供高稳定性、高精度的定位，或基于定位的服务。
第二方面，提供了一种定位方法。该方法包括：当检测的用户运动第N步时，向服务器发送的用户运动第N步的计步信息和所述目标终端所处位置的多个无线接入点的信号强度，以便服务器根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度确定目标终端运动第N步的位置；接收服务器发送所述目标终端运动第N步的位置。通过本申请实施例，可以结合传感器信号以及WiFi信号作为位置指纹，以此增加位置指纹的特征，定位结果更平滑，以降低环境对定位精度的影响，以及提高定位技术的稳定性，从而提高定位精度。
在一个可能的设计中，还包括：当当接收到的用户运动第N步后所述目标终端的位置与接收到的用户运动第N-1步后的所述目标终端的位置相同时，则根据用户运动第N步后的计步信息通过行人航位推算得到用户运动第N步后所述目标终端的当前位置。通过本申请实施例，终端可以结合服务器提供的指纹定位结果和自身的PDR结果，以此可以提高定位结果更新频率，提高定位精度。
第三方面，提供了一种终端定位装置接收单元，用于接收目标终端发送的计步信息和所述目标终端所处位置的多个无线接入点的信号强度；
定位单元，用于根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强 度，确定所述目标终端的当前位置。
在一个可能的设计中，所述计步信息包括下述一项或多项：
步行方向、步长以及相邻两步步行方向偏移角。
在一个可能的设计中，所述定位单元具体用于：
求解如下公式概率最大的位置序列S 1,S 2,…,S i,…,S n，其中S n为所述目标终端的当前位置：
Figure PCTCN2019114990-appb-000005
其中，
Figure PCTCN2019114990-appb-000006
为O 1,O 2,…,O i,…,O n到S 1,S 2,…,S i,…,S n的发射概率，O i包括第i步的计步信息和第i步时目标终端所处位置的多个无线接入点的信号强度；
Pr(S i+1|S i)为点S i+1到点S i的转移概率；
Pr(S 1)为初始位置S 1的概率。
进一步地，
Figure PCTCN2019114990-appb-000007
其中，l i,l j分别表示S i,S j的位置坐标，d[(l j-l i),step_length]表示状态S i,S j间欧式距离与步长的差值，d(S j,S i)表示状态S i,S j间欧式距离，D max为根据行人步长确定的相邻两步之间的距离阈值。
进一步地，
Figure PCTCN2019114990-appb-000008
其中，dis_state_wf i为根据第i步时目标终端所处位置的多个无线接入点的信号强度以及预先在基准点确定的多个无线接入点的信号强度确定的定位结果 到S i的距离；
Δθ i为相邻第i步与第i-1步的行方向偏移角；
θ 0为误差门限，θ 0∈20°～45°。
在一个可能的设计中，，无线接入点的信号强度信息的更新频率低于传感器信息的更新频率；
所述装置，还包括：
推算单元，用于根据计步信息进行行人航位推算，确定目标终端对应的第一位置；
当所述第一位置与S n相同时，则确定所述S n为所述目标终端的当前位置；
当所述第一位置与S n不同时，则确定所述第一位置为所述目标终端的当前位置。
在一个可能的设计中，还包括：
发送单元，用于向目标终端发送所述目标终端的当前位置。
第四方面，提供了一种终端定位装置。所述装置包括：
发送单元，用于当检测的用户运动第N步时，向服务器发送的用户运动第N步的计步信息和所述目标终端所处位置的多个无线接入点的信号强度，以便服务器根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度确定目标终端运动第N步的位置；
接收单元，用于接收服务器发送所述目标终端运动第N步的位置。
在一个可能的设计中，，还包括：
推算单元，用于当接收到的用户运动第N步后所述目标终端的位置与接收到的用户运动第N-1步后的所述目标终端的位置相同时，则根据用户运动第N步后的计步信息通过行人航位推算得到用户运动第N步后所述目标终端的当前位置。。
第五方面，本发明实施例提供了一种设备。该设备包括收发器、处理器和存储器；收发器用于与其他设备进行通信，例如，该设备可以为服务器，该服务器的收发器用于与终端进行通信，该设备还可以为终端，该终端的收发器用于与服务器进行通信，存储器用于存放程序；处理器用于执行存储器存储的程序，以控制设备执行上述第一方面或第二方面中任意一方面所述的方法。
第六方面，提供了一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器执行时实现上述第一方面或第二方面中任意一方面所述的方法。
第七方面，提供了一种包含指令的计算机程序产品，当计算机程序产品的指令在计算机上运行时，使得计算机执行上述第一方面或第二方面中任意一方面所述的方法。
通过本申请实施例，可以结合传感器信号以及WiFi信号作为位置指纹，以此增加位置指 纹的特征，定位结果更平滑，以降低环境对定位精度的影响，以及提高定位技术的稳定性，从而提高定位精度。
附图说明
图1为本申请实施例提供的一种应用场景示意图；
图2为本申请实施例提供的一种定位方法流程示意图；
图3为一个应用场景示例；
图4为本申请实施例提供的一种定位方法流程示意图；
图5为本申请实施例提供的一种终端定位装置结构示意图；
图6为本申请实施例提供的一种终端定位装置结构示意图；
图7为本申请实施例提供的一种服务器结构示意图；
图8为本发明实施例提供的一种终端结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例进行描述。
本申请的发明人通过分析发现，随着信息技术的快速发展，定位技术的种类越来越多，但是，不同定位技术的都具有各自的优缺点，可以将WiFi信号定位技术与传感器定位技术进行融合，以达到取长补短的效果。基于此，本申请提出了一种定位方法及装置。通过该定位方法，可以结合传感器信号以及WiFi信号作为位置指纹，以此增加位置指纹的特征，以降低环境对定位精度的影响，以及提高定位技术的稳定性，从而提高定位精度。进一步地，还可以综合通过WiFi信号定位技术得到的定位结果以及通过传感器定位技术得到的定位结果，得到最终的定位结果，以此可以降低传感器定位累计误差以及降低由于WiFi信号波动引起的定位结果不稳定的问题等。
本申请适用于办公室、商场、机场以及火车站等室内场景，在该场景中设置有一定数量的WAP，且该WAP发射的WiFi信号密度足够。例如，在任一室内空间位置中终端可以探测WAP数量都大于5个。终端可以将获取的WiFi信号以及传感器信息等发送至服务器，由服务器进行定位确定，并将确定的定位结果返回至终端。
图1为本发明实施例提供的一种运算场景示意图。如图1所示，在该场景中包括WAP、终端以及服务器130。其中，WAP可以包括多个，该多个WAP中的任意一个由指定区域140外向指定区域140发送WiFi信号，例如WAP111，也可以是在指定区域140内向指定区域140发送WiFi信号，例如WAP112。服务器130可以为处于指定区域140的终端提供定位服务， 例如，服务器130为处于位置141的终端121或处于位置142的终端122提供基于位置的服务或者定位服务。
其中，指定区域140可以为办公室、商场、机场以及火车站等室内场景，该指定区域内可以包括障碍物，例如墙体、办公用品或者绿植等等。
下面将结合本申请实施例中的附图，对本申请实施例进行进一步地描述。
图2为本申请实施例提供的一种定位方法流程示意图。该方法可以应用在图1所示的场景中。如图2所示，该方法具体可以包括：
在定位之前，需要预先进行隐状态量化，例如，可以预先以步长为基准确定指定区域中的M个隐状态，该M为大于零的整数。在一个示例中，指定区域大小为图1所示的指定区域，将该指定区域除障碍物以外的位置按照步长0.8米划分成大小相同的网格，网格的交点为不同隐含状态的位置点。
另外，还可以预先采集参考点的终端所处位置的多个无线接入点的信号强度，以便根据参考点的终端所处位置的多个无线接入点的信号强度对定位过程中终端所处位置的多个无线接入点的信号强度与隐状态之间的发射概率进行计算。其中，参考点的间隔可以为步长的整数倍。例如，参考点的间隔可以为步长的4-6倍。
在完成了参考点的终端所处位置的多个无线接入点的信号强度采集后，将采集到的终端所处位置的多个无线接入点的信号强度存入数据库中。其中，再将采集到的终端所处位置的多个无线接入点的信号强度放入数据库之前还需要对终端所处位置的多个无线接入点的信号强度进行预处理，例如，在每个参考点上对同一个无线接入点采集到的多组终端所处位置的多个无线接入点的信号强度，可以预先确定采集到的多组终端所处位置的多个无线接入点的信号强度的均值。其中，每个参考点可以采集多个方向的终端所处位置的多个无线接入点的信号强度，每个方向对应的多组终端所处位置的多个无线接入点的信号强度，可以将该参考点的全部方向的全部终端所处位置的多个无线接入点的信号强度进行平均，并将均值存入数据库。其中，每个参考点的所有WAP的终端所处位置的多个无线接入点的信号强度的均值构成一组向量，该组向量可以作为该参考点的位置指纹。
S210，当目标终端检测的用户运动第N步时，终端向服务器发送发送的计步信息和目标终端所处位置的多个无线接入点的信号强度，以便服务器根据发送的计步信息和目标终端所处位置的多个无线接入点的信号强度进行定位。其中，该计步信息可以为通过传感器信息获取的信息，例如该计步信息可以为采集的加速度计、陀螺仪或电子罗盘等传感器的数据，也是可以根据传感器数据确定的用户运动信息，该用户运动信息可以包括步行方向、步长以及相邻两步步行方向偏移角等等。
终端可以通过传感器检测用户的运动，
在一个示例中，终端可以通过加速度计进行步态检测，在确定用户迈步后，可以将加速度计、陀螺仪以及电子罗盘的信息发送至服务器。
在另一示例中，终端可以通过加速度计进行步态检测，在确定用户迈步后，可以根据加速度计、陀螺仪以及电子罗盘的信息推算出运动方向，并将运动方向发送至服务器。另外，还可以根据加速度计推算出步长方向，并将推算的步长发送至服务器。
例如，在终端线连续定位时，终端快速的对周围WiFi信号进行扫描，并将扫描到的终端所处位置的多个无线接入点的信号强度上传服务器。另外，终端可以实时采集用户运动过程中的终端的传感器信息，并根据采集到的传感器信息确定步数、步长以及方向。具体来讲，WiFi信号的采样间隔通常是50毫秒，加速计和罗盘的采样频率通常是50Hz。利用加速度传感器可以检测行走的步数，每当检测到行走一步时，可以计为第N步，利用罗盘和陀螺仪可以确定该第N步行进的运动方向，同时终端采集到该第N步相对应终端所处位置的多个无线接入点的信号强度，将该第N步行进的运动方向和终端所处位置的多个无线接入点的信号强度发送至服务器。服务器接收目标终端发送的用户运动第N步后的传感器信息以及终端所处位置的多个无线接入点的信号强度。当服务器在接收上述信息后，可以通过下述S220-S230实现定位。
S220，根据所述计步信息和目标终端所处位置的多个无线接入点的信号强度，确定所述目标终端的当前位置。
服务器可以根据前N步的传感器信息以及终端所处位置的多个无线接入点的信号强度，确定前N步中每一步的对应M个隐状态的发射概率。
在本申请实施例中，定位问题可以转化为根据前N步的传感器信息以及终端所处位置的多个无线接入点的信号强度求解该前N步对应的最佳隐状态序列，例如，基于隐马尔可夫模型或基于隐马尔可夫模型演变而来的模型，来进行最佳隐状态序列的估计。在具体确定过程中，需要确定在用户运动过程中每一个观测向量(该观测向量包括传感器信息以及终端所处位置的多个无线接入点的信号强度)在每个可能位置点(该可能的位置点即为M个隐状态)的似然概率，即发射概率；还需要确定可能的隐状态状态之间转移概率；通过发射概率、转移概率以及初始概率来求解最大化概率对应的隐状态序列，即最佳位置点序列，例如通过维特比算法求解概率最大化对应的最佳位置点序列。
其中，隐状态的发射概率可以根据传感器信息和终端所处位置的多个无线接入点的信号强度来确定，以提高发射概率的准确性。
在一个示例中，可以根据终端所处位置的多个无线接入点的信号强度确定隐状态的初始 发射概率，根据传感器信息确定的用户运动方向以及隐状态之间对应的方向是否吻合，来调整隐状态的初始发射概率得到最终发射概率。另外，通过传感器检测到的用户运动方向与用户运动对应的隐状态之间方向存在一定的误差，该误差通常在误差门限范围内。基于此，该方法可以包括如下步骤：
可以根据前N步中每一步的终端所处位置的多个无线接入点的信号强度确定前N步中每一步对应的M个隐状态的第一概率；
根据前N步中每一步对应的第一方向与前N步中每一步对应的M个隐状态的第二方向与之间的差值与门限(即误差门限)的关系，确定前N步中每一步对应的M个隐状态的第二概率；其中，第i步的第一方向为根据第i步的传感器信息确定的方向，第i步的第k个隐状态的第二方向为第k个隐状态到第i-1步目标终端的位置对应的隐状态的方向，第i步为前N步中任意一步，第k个隐状态为M个隐状态中任意一个；
将前N步中每一步对应的M个隐状态的第一概率和第二概率相乘，确定前N步中每一步对应M个隐状态的发射概率。
接下来，初始位置对应的隐状态可以为已知，或者根据终端所处位置的多个无线接入点的信号强度确定。
在一个示例中，服务器可以接收目标终端发送的初始位置终端所处位置的多个无线接入点的信号强度；该服务器可以根据初始位置终端所处位置的多个无线接入点的信号强度，通过临近算法KNN确定第一隐状态，该第一隐状态即为初始位置对应的隐状态。
在隐状态的初始概率的具体计算过程中，可以确定目标终端初始位置位置对应的第一隐状态的初始概率为1，该初始位置为步数N等于0对应的位置，前述M个隐状态中除第一隐状态以外的隐状态的初始概率为0。
接下来，隐状态之间的转移概率可以根据隐状态本身的特征确定。具体地，隐状态之间的转移概率根据隐状态之间的距离与步长的差值确定。其中，例如，行人由于其自身能力的限制，每步行走的距离通常是相差不大的，如果隐状态之间的距离大于步长过多，则两个状态之间的转移则不会出现，也就是概率为0，相应的，隐状态之间的距离越接近步长，则转移概率越大。基于此，该方法可以包括：将第j个隐状态与第f个隐状态之间的距离与步长之间的差值，以及该差值与距离门限的关系确定第j个隐状态与第f个隐状态之间的状态转移概率。其中，第j个隐状态为M个隐状态中任意一个，第f个隐状态为M个隐状态中任意一个。
另外，根据行人在室内的运动的运动通常具有一定的规律性，例如，在办公室和茶水间之前运动的概率最大。可以统计多个用户在室内移动的运动规律分布，根据该移动规律，确定两个隐状态之间的方向概率，通过将方向概率与根据与步长的关系确定的初始状态转移概 率相乘，得到最终的状态转移概率。基于此，本发明实施例还可以包括：
将第j个隐状态与第f个隐状态之间的距离与步长之间的差值，以及该差值与距离门限的关系确定第三概率；
将第j个隐状态与第f个隐状态对应的第三概率与第j个隐状态与第f个隐状态的方向概率相乘，确定第j个隐状态与第f个隐状态之间的转移概率；
其中，第j个隐状态与第f个隐状态的的方向概率根据指定区域内用户历史移动规律确定，第j个隐状态为M个隐状态中任意一个，第f个隐状态为M个隐状态中任意一个。
服务器将所述前N步中每一步对应的M个隐状态的发射概率、所述M个隐状态之间的转移概率、以及所述M个隐状态的初始概率相乘，选择概率最大的第一隐状态序列，并根据所述第一隐状态序列确定用户运动第N步后的所述目标终端的位置，其中，隐状态之间的转移概率根据隐状态之间的距离与所述步长的差值确定。
在确定将前N步中每一步对应的M个隐状态的发射概率、M个隐状态之间的转移概率、以及M个隐状态的初始概后，可以结合上述概率求解该前N步对应的最佳隐状态序列。例如，可以通过维特比算法来求解最佳位置点序列。其中，在确定的前N步对应的最佳隐状态序列后，可以根据该前N步对应的最佳隐状态序列确定用户运动第N步对应的位置。
在一个示例中，可以根据前N步对应的最佳隐状态序列中第N步对应的隐状态，确定目标终端对应的位置坐标。
在另一个示例中，可以结合行人航位推算(Pedestrian Dead Reckoning，PDR)技术，得到最终的目标终端对应的位置坐标。基于此，本申请实施例在根据第一隐状态序列确定用户运动第N步后的目标终端的位置之后还可以包括：
判断第一隐状态序列确定的用户运动第N步后的所述目标终端的位置与根据第二隐状态序列确定的用户运动第N-1步后的所述目标终端的位置是否相同；其中，所述第二隐状态序列为用户运动第N-1步后确定的隐状态序列；
当根据第一隐状态序列确定的用户运动第N步后的所述目标终端的位置与根据第二隐状态序列确定的用户运动第N-1步后的目标终端的位置相同时，则根据用户运动第N步后的传感器信息通过行人航位推算PDR得到用户运动第N步后的所述目标终端位置；
当根据第一隐状态序列确定的用户运动第N步后的所述目标终端的位置与根据第二隐状态序列确定的用户运动第N-1步后的所述目标终端的位置不同时，则确定所述第一隐状态序列中第N步对应的隐状态的位置为用户运动第N步后的所述目标终端的位置。
S230a，服务器向目标终端发送用户运动第N步后的目标终端的位置。或者，S240b，服务器向目标终端提供基于用户运动第N步后的目标终端的位置的服务。
其中，目标终端在接收到服务器发送的用户运动第N步后的位置后，可以根据该位置为用户或其他应用提供定位服务。例如，可以为用户提供在指定区域内的导航服务。
在S230b中的基于用户运动第N步后的目标终端的位置的服务可以包括多种，例如，为终端推送附近商家信息、候车室信息、候车室对应的车次信息等等，还可以是为用户提供报警(例如，火警)、投诉等位置定位服务等等。
另外，服务器向终端发送的用户运动第N步后的目标终端的位置可以为结合PDR技术得到，也可以是未结合PDR技术得到。在从服务器接收到的定位信息未结合PDR技术时，目标终端可以结合PDR技术，得到最终的定位位置坐标，或者，根据PDR技术实时更新定位位置坐标。基于此，目标终端可以判断接收到的用户运动第N步后的目标终端的位置与接收到的用户运动第N-1步后的目标终端的位置是否相同；当目标终端接收到的用户运动第N步后的目标终端的位置与接收到的用户运动第N-1步后的目标终端的位置相同时，则根据用户运动第N步后的传感器信息通过行PDR得到用户运动第N步后的目标终端位置。
在本申请实施例中，隐含状态采用了虚拟隐含状态方式，不同隐状态位置的间距取值为步长，总的隐状态的数目取决于行人步长大小与指定区域的大小。使得隐状态更不符合用户的特点，定位精度更高。
另外，WiFi信号强度的离线采集参考点的间距取值为行人步长的整数倍(该整数大于1)，为了取得定位性能与采集工作量的平衡，该倍数取值建议为4～6。
下面，对本申请实施例中，PDR定位，隐状态量化，发射概率、转移概率以及初始概率的确定，结合具体示例进行进一步地介绍。
关于参考点离线采集：
可以在每个参考点采集的无线接入点的信号强度来自环境中已有的AP，剔除WiFi信号强度值低于阈值(例如，-80dBm)的WAP。每个参考点分4个方向，以200毫秒的采样间隔在每个方向采集50毫秒的无线接入点的信号强度样本。
在完成信号采集工作之后，进行预处理。确定每个参考点上对同一个AP采集到的多组无线接入点的信号强度(rssi 1,rssi 2,...,rssi n)的均值
Figure PCTCN2019114990-appb-000009
计算公式为：
Figure PCTCN2019114990-appb-000010
将每个参考点的均值存入数据库。
关于隐状态量化，以及：
设将指定区域划分为k个网格，每一个网格的交点看作用户运动可能的真实位置状态，即为隐状态，记为S i,i∈{1,2,…,k}；在每个网格交点处测量得到该网格对应的相关信息(即 为传感器信息以及无线接入点的信号强度)，记为O i,i∈{1,2,…,k}。用户在该区域内的运动轨迹为L＝{S 1,S 2,…,S i,…,S n},i∈{1,2,…,k}，表示用户从位置S 1，依次经过S 2,S 3,…,S n-1到达S n，则用户运动过程中所有测量值可以表示为向量<O 1,O 2,…,O i,…,O n>,i∈{1,2,…,k}，其中O i表示隐状态S i的观测值。在已知用户运动轨迹的情况下，用户移动轨迹对应的隐状态对应的测量值向量<O 1,O 2,…,O i,…,O n>的发送概率可以表示为Pr(O 1,O 2,…,O i,…,O n|S 1,S 2,…,S i,…,S n)。
可以根据位置点观测值信息对移动用户的轨迹进行确定，也即，寻找隐状态序列使得概率Pr(S 1,S 2,…,S i,…,S n|O 1,O 2,…,O i,…,O n)最大。这里，Pr(O 1,O 2,…,O i,…,O n)表示观测序列概率。根据贝叶斯准则，有：
Figure PCTCN2019114990-appb-000011
基于以上分析，移动用户的轨迹的隐状态序列可以表示为下式：
Figure PCTCN2019114990-appb-000012
其中，移动用户当前时刻的隐状态仅与前面时刻的隐状态有关，与其他时刻的隐状态无关，且不同隐状态之间的转移概率为预先确定。则有：
Figure PCTCN2019114990-appb-000013
另外不同隐状态的观测值相互独立，则有：
Figure PCTCN2019114990-appb-000014
所以，移动用户的轨迹的确定，即为求解下式概率最大值对应的隐状态序列：
Figure PCTCN2019114990-appb-000015
关于隐状态之间的转移概率的确定：
不同隐状态之间的转移概率与距离有关且服从高斯分布；根据行人运动的实际情况，当隐状态之间的距离接近步长(0.8米)时，状态转移的概率最大，即假设μ＝0.8；由于人在自然条件下的运动速度是有限的，即在固定的时间内运动的距离是有限的，因此设定距离阈值D max，当两个隐状态之间的距离超过阈值时，隐状态之间不会转移，即转移概率为0。因此，隐状态之间的转移概率确定公式如下：
Figure PCTCN2019114990-appb-000016
其中，式6中，l i,l j分别表示隐状态S i,S j的位置坐标，d[(l j-l i),step_length]表示状态S i,S j间欧式距离与步长的差值，d(S j,S i)表示状态S i,S j间欧式距离。根据人在室内行走的运动规律，位置不可能发生较大的跳变，因此取D max＝4.8米。
因为用户在室内移动具有一定的统计规律分布，如果具有大量的用户在地图中的移动方向统计数据，可以将统计得到的统计方向概率信息与(6)式中得到的状态转移概率相乘，得到最终的状态转移概率
Figure PCTCN2019114990-appb-000017
Pr D(S i→S j)为状态S i→S j的方向转移概率。如果没有状态转移的方向信息，则Pr D(S i→S j)＝1。
发射概率是指观测值表现为某种隐状态的概率。本专利中，通过行人在线行走时每一步WiFi指纹法定位结果与来自传感器的数据确定发射概率。具体实现如下：观测值是WiFi定位结果，设t时刻WiFi位置指纹法定位结果到隐含状态i的距离为dis_state_wf i，则t时刻隐状态i处发射概率确定公式如下：
Figure PCTCN2019114990-appb-000018
考虑传感器方向与步长信息，设当前时刻t采集到传感器航向角为θ t，隐状态i位置坐标(x i,y i)到上一时刻定位结果(location_x t-1,location_y t-1)的夹角为θ i；Δθ i为航向角测量值θ t与θ i的偏移角；经实验，偏移角Δθ i在不同实验环境、不同终端类型下会有一定的范围，将这个误差范围成为误差门限，用θ 0表示，一般情况下θ 0∈20°～45°，在给定实验环境、给定终端的条件下θ 0值是一个常数；通过利用传感器方向信息与行人运动规律，对可能的隐状态做出限制：
Figure PCTCN2019114990-appb-000019
Δθ i＝|θ i-θ t|       (9)
Figure PCTCN2019114990-appb-000020
因此，最终发射概率确定公式如下：
Figure PCTCN2019114990-appb-000021
关于PDR定位：
其中，该PDR定位过程可以在终端中实现也可以在服务器端实现。当行人脚步被探测之后，令t＝t+1。假定用户第t步的PDR的定位结果为
Figure PCTCN2019114990-appb-000022
第t步估计步长为d t，第t步运动方向为θ t。则根据PDR定位结果的计算公式，如式(1)，可得t时刻PDR的定位结果。
Figure PCTCN2019114990-appb-000023
Figure PCTCN2019114990-appb-000024
下面结合具体示例，对本申请实施例进行进一步地介绍。
指定区域如图3所示，该指定区域的大小为41.26m×26.10m，该指定区域包括办公室、工位等障碍物。
在离线阶段进行无线接入点的信号强度采集，采集的参考点间隔是步长(0.8米)的四倍(3.2米)，由于空间限制，指定区域两翼参考点的间隔是三倍(2.4米)或两倍(1.6米)，在指定区域中一共有73个参考点，在每个参考点采集的无线接入点的信号强度来自环境中已有的WAP，剔除wifi信号强度低于-80dBm的WAP。每个参考点分4个方向，以200毫秒的采样间隔在每个方向采集50秒的无线接入点的信号强度样本。
在前述采集工作完成之后，将采集到的信息进行预处理。在每个参考点上对同一个WAP采集到的多组RSSI信息，rssi 1,rssi 2,...,rssi n，确定出他们的均值
Figure PCTCN2019114990-appb-000025
计算公式为：
Figure PCTCN2019114990-appb-000026
以此确定出每个参考点的所有方向的样本平均值存入数据库。其中，每个参考点的所有WAP的均值信息构成一组向量，作为位置指纹。
在线定位时，终端快速的进行周围WAP的多个无线接入点的信号强度进行扫描。其中，终端所处位置的多个无线接入点的信号强度的采样间隔是50毫秒，传感器数据的采样频率是50Hz。
终端将采集到的传感器信息和终端所处位置的多个无线接入点的信号强度发送至服务器。
服务器接收到以上信息之后，进行实时定位计算。具体如下所述：
S410，服务器确定用户初始位置。其中，用户初始位置已知，l 0＝(x 0,y 0)；
S420，服务器根据传感器信息确定用户走一步时，根据传感器信息确定当前时刻PDR的定位结果
Figure PCTCN2019114990-appb-000027
S430，服务器根据传感器信息和终端所处位置的多个无线接入点的信号强度结合指纹法确定定位结果
Figure PCTCN2019114990-appb-000028
在服务器根据传感器信息和终端所处位置的多个无线接入点的信号强度结合指纹法确定定位结果过程中，具体包括如下步骤：
预先进行隐状态量化。其中，将指定区域按照步长0.8米划分成大小相同的网格，网格的交点为不同隐状态的位置点，一共划分为638个隐状态，则定位问题就等效于在638个隐状态中寻找最佳隐状态序列。
确定隐状态的初始概率、发射概率以及隐状态之间的转移概率。其中，隐状态的初始概率可以根据已知的初始位置确定，隐状态之间的转移概率结合公式(6)确定，发射概率可以结合公式(10)确定。
在获得初始概率、状态转移概率与发射概率之后，利用维特比算法结合公式(5)确定概率最大的隐状态序列。其中，该在该隐状态序列中，当前时刻对应的隐状态的位置坐标，即为通过指纹定位法得到定位结果。
S440，判断当前时刻通过指纹法的定位结果与前一时刻通过指纹法定位结果是否相同。若当前时刻指纹法定位结果等于前一时刻指纹法定位结果相同，则将S420中PDR的定位结果作为用户的当前位置；若当前时刻通过指纹法定位结果与前一时刻通过指纹法定位结果不同，则将S430中的定位结果作为用户的当前位置。
本申请实施例从隐马尔科夫模型(hidden markov model，HMM)角度考虑室内定位问题，将寻找最佳位置点序列的问题转化为维特比算法求解最优化问题。针对仅采用终端所处位置的多个无线接入点的信号强度带来的观测信息不足而导致的基于隐马尔可夫模型的定位算法性能较差的问题，本发明将传感器方向等信息加入到算法中，此外，针对实际工程场景中终端所处位置的多个无线接入点的信号强度更新频率低于运动传感器更新频率的问题，在考虑加入方向信息的同时做出改进，具体提出基于隐马尔科夫模型终端所处位置的多个无线接入点的信号强度与传感器信息分段融合定位算法。
本申请实施例结合行人运动行为信息，通过融合终端传感器数据提高了隐马尔可夫模型下状态转移概率以及发射概率更符合实际情况，使得定位轨迹更接近真实轨迹，定位精度更高；同时提出了虚拟隐状态量化的思想，减小了离线数据库采样工作量。
图5为本申请实施例提供的一种终端定位装置结构示意图。该装置可以用于执行图2或图4所示实施例中服务器所执行的方法。预先以步长为基准确定指定区域中的M个隐状态，所述M为大于零的整数，如图5所示，该装置包括：
接收单元501，用于接收目标终端发送的计步信息和所述目标终端所处位置的多个无线接入点的信号强度；
定位单元502，用于根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度，确定所述目标终端的当前位置。
在一个实施例中，所述计步信息包括下述一项或多项：
步行方向、步长以及相邻两步步行方向偏移角。
在另一个实施例中，所述定位单元具体用于：
求解如下公式概率最大的位置序列S 1,S 2,…,S i,…,S n，其中S n为所述目标终端的当前位置：
Figure PCTCN2019114990-appb-000029
其中，
Figure PCTCN2019114990-appb-000030
为O 1,O 2,…,O i,…,O n到S 1,S 2,…,S i,…,S n的发射概率，O i包括第i步的计步信息和第i步时目标终端所处位置的多个无线接入点的信号强度；
Pr(S i+1|S i)为点S i+1到点S i的转移概率；
Pr(S 1)为初始位置S 1的概率。
在另一个实施例中，
Figure PCTCN2019114990-appb-000031
其中，l i,l j分别表示S i,S j的位置坐标，d[(l j-l i),step_length]表示状态S i,S j间 欧式距离与步长的差值，d(S j,S i)表示状态S i,S j间欧式距离，D max为根据行人步长确定的相邻两步之间的距离阈值。
在另一个实施例中，
Figure PCTCN2019114990-appb-000032
其中，dis_state_wf i为根据第i步时目标终端所处位置的多个无线接入点的信号强度以及预先在基准点确定的多个无线接入点的信号强度确定的定位结果到S i的距离；
Δθ i为相邻第i步与第i-1步的行方向偏移角；
θ 0为误差门限，θ 0∈20°～45°。
在另一个实施例中，无线接入点的信号强度信息的更新频率低于传感器信息的更新频率；
所述装置，还包括：
推算单元，用于根据计步信息进行行人航位推算，确定目标终端对应的第一位置；
当所述第一位置与S n相同时，则确定所述S n为所述目标终端的当前位置；
当所述第一位置与S n不同时，则确定所述第一位置为所述目标终端的当前位置。
在另一个实施例中，还包括：
发送单元，用于向目标终端发送所述目标终端的当前位置。
图6为本申请实施例提供的一种终端定位装置结构示意图。该装置可以用于执行图2或图4所示实施例中终端所执行的方法。如图6所示，该装置包括：
发送单元601，用于当检测的用户运动第N步时，向服务器发送的用户运动第N步的计步信息和所述目标终端所处位置的多个无线接入点的信号强度，以便服务器根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度确定目标终端运动第N步的位置；
接收单元602，用于接收服务器发送所述目标终端运动第N步的位置。
在一个实施例中，还包括：
推算单元603，用于当接收到的用户运动第N步后所述目标终端的位置与接收到的用户运动第N-1步后的所述目标终端的位置相同时，则根据用户运动第N步后的计步信息通过行人航位推算得到用户运动第N步后所述目标终端的当前位置。
图7为本申请实施例提供的一种服务器结构示意图。该服务器700具体包括：包括收发器701，处理器702，存储器703。收发器701、处理器702和存储器703可以通过总线连接。该服务器可以用于实现图2或图4所示实施例中服务器的功能。
其中，收发器701用于支持服务器与上述实施例中的终端或其他服务器之间收发信息。在服务器与终端之间通信过程中，数据和信令消息由处理器702进行处理，并由收发器701发送给终端。来自终端的数据和信令的经由收发器701接收，由处理器702进行处理得到终端发送的数据和信令。处理器702可以控制发送设备700执行图2或图4所示实施例中涉及发送端的处理过程和/或用于本申请所描述的技术的其他过程。例如，处理器702用于执行图2和图4所示的实施例中的S220、S230或S410-S440等步骤中的一步或多步，收发器701用于执行图2和图4所示的实施例中的S240a或S240b等步骤中的一步或多步。存储器703用于存储终端的程序代码和数据。
图8为本发明实施例提供的一种终端结构示意图。该终端800具体包括：包括收发器801，处理器802，存储器803，WiFi模块804和传感器805。收发器801、处理器802、存储器803、WiFi模块804和传感器805可以通过总线连接。该网络设备可以用于实现图2或图4所示实施例中发送端的功能。例如但不限于手机、电脑、可穿戴设备等。
其中，收发器801用于支持终端与上述实施例中服务器之间收发信息。在终端与服务器之间通信过程中，数据和信令消息由处理器802进行处理，并由收发器801发送给服务器。来自服务器的数据和信令的经由收发器801接收，由处理器802进行处理得到服务器发送的数据和信令。WiFi模块804用于确定终端所处位置的多个无线接入点的信号强度，传感器805用于确定传感器信息。该传感器805包括加速度计、陀螺仪或电子罗盘等中的一项或多项。处理器802可以控制终端800执行图2或图4所示实施例中涉及终端的处理过程和/或用于本申请所描述的技术的其他过程。例如，收发器801用于执行图2和图4所示的实施例中的S210等步骤。存储器803用于存储终端的程序代码和数据。
本申请实施例提供了一种芯片。该芯片包括处理器和存储器；存储器用于存放程序；所述处理器用于执行所述存储器存储的所述程序，以执行上述方法实施例中所述的方法。
在上述各个本发明实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本发明实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读介质向另一个计算机可读介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任 何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如，固态硬盘)等。
以上所述，仅为本申请较佳的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应该以权利要求的保护范围为准。

Claims (22)

  1. 一种终端定位方法，其特征在于，所述方法包括：
    接收目标终端发送的计步信息和所述目标终端所处位置的多个无线接入点的信号强度；
    根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度，确定所述目标终端的当前位置。
  2. 根据权利要求1所述的方法，其特征在于，所述计步信息包括下述一项或多项：
    步行方向、步长以及相邻两步步行方向偏移角。
  3. 根据权利要求1或2所述的方法，其特征在于，所述根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度，确定所述目标终端的当前位置包括：
    求解如下公式概率最大的位置序列S 1,S 2,…,S i,…,S n，其中S n为所述目标终端的当前位置：
    Figure PCTCN2019114990-appb-100001
    其中，
    Figure PCTCN2019114990-appb-100002
    为O 1,O 2,…,O i,…,O n到S 1,S 2,…,S i,…,S n的发射概率，O i包括第i步的计步信息和第i步时目标终端所处位置的多个无线接入点的信号强度；
    Pr(S i+1|S i)为点S i+1到点S i的转移概率；
    Pr(S 1)为初始位置S 1的概率。
  4. 根据权利要求3所述的方法，其特征在于，
    Figure PCTCN2019114990-appb-100003
    其中，l i,l j分别表示S i,S j的位置坐标，d[(l j-l i),step_length]表示状态S i,S j间欧式距离与步长的差值，d(S j,S i)表示状态S i,S j间欧式距离，D max为根据行人步长确定的相邻两步之间的距离阈值。
  5. 根据权利要求3或4所述的方法，其特征在于，
    Figure PCTCN2019114990-appb-100004
    其中，dis_state_wf i为根据第i步时目标终端所处位置的多个无线接入点的信号强度以及预先在基准点确定的多个无线接入点的信号强度确定的定位结果到S i的距离；
    Δθ i为相邻第i步与第i-1步的行方向偏移角；
    θ 0为误差门限，θ 0∈20°～45°。
  6. 根据权利要求3-5任意一项所述的方法，其特征在于，无线接入点的信号强度信息的更新频率低于传感器信息的更新频率；
    所述方法，还包括：
    根据计步信息进行行人航位推算，确定目标终端对应的第一位置；
    当所述第一位置与S n相同时，则确定所述S n为所述目标终端的当前位置；
    当所述第一位置与S n不同时，则确定所述第一位置为所述目标终端的当前位置。
  7. 根据权利要求1-6任意一项所述的方法，其特征在于，还包括：
    向目标终端发送所述目标终端的当前位置。
  8. 一种终端定位方法，其特征在于，所述方法包括：
    当检测的用户运动第N步时，向服务器发送的用户运动第N步的计步信息和所述目标终端所处位置的多个无线接入点的信号强度，以便服务器根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度确定目标终端运动第N步的位置；
    接收服务器发送所述目标终端运动第N步的位置。
  9. 根据权利要求8所述的方法，其特征在于，还包括：
    当接收到的用户运动第N步后所述目标终端的位置与接收到的用户运动第N-1步后的所述目标终端的位置相同时，则根据用户运动第N步后的计步信息通过行人航位推算得到用户运动第N步后所述目标终端的当前位置。
  10. 一种终端定位装置，其特征在于，所述装置包括：
    接收单元，用于接收目标终端发送的计步信息和所述目标终端所处位置的多个无线接入点的信号强度；
    定位单元，用于根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度，确定所述目标终端的当前位置。
  11. 根据权利要求10所述的装置，其特征在于，所述计步信息包括下述一项或多项：
    步行方向、步长以及相邻两步步行方向偏移角。
  12. 根据权利要求10或11所述的装置，其特征在于，所述定位单元具体用于：
    求解如下公式概率最大的位置序列S 1,S 2,…,S i,…,S n，其中S n为所述目标终端的当前位置：
    Figure PCTCN2019114990-appb-100005
    其中，
    Figure PCTCN2019114990-appb-100006
    为O 1,O 2,…,O i,…,O n到S 1,S 2,…,S i,…,S n的发射概率，O i包括第i步的计步信息和第i步时目标终端所处位置的多个无线接入点的信号强度；
    Pr(S i+1|S i)为点S i+1到点S i的转移概率；
    Pr(S 1)为初始位置S 1的概率。
  13. 根据权利要求12所述的装置，其特征在于，
    Figure PCTCN2019114990-appb-100007
    其中，l i,l j分别表示S i,S j的位置坐标，d[(l j-l i),step_length]表示状态S i,S j间欧式距离与步长的差值，d(S j,S i)表示状态S i,S j间欧式距离，D max为根据行人步长确定的相邻两步之间的距离阈值。
  14. 根据权利要求12或13所述的装置，其特征在于，
    Figure PCTCN2019114990-appb-100008
    其中，dis_state_wf i为根据第i步时目标终端所处位置的多个无线接入点的信号强度以及预先在基准点确定的多个无线接入点的信号强度确定的定位结果到S i的距离；
    Δθ i为相邻第i步与第i-1步的行方向偏移角；
    θ 0为误差门限，θ 0∈20°～45°。
  15. 根据权利要求11-14任意一项所述的装置，其特征在于，无线接入点的信号强度信息的更新频率低于传感器信息的更新频率；
    所述装置，还包括：
    推算单元，用于根据计步信息进行行人航位推算，确定目标终端对应的第一位置；
    当所述第一位置与S n相同时，则确定所述S n为所述目标终端的当前位置；
    当所述第一位置与S n不同时，则确定所述第一位置为所述目标终端的当前位置。
  16. 根据权利要求10-15任意一项所述的装置，其特征在于，还包括：
    发送单元，用于向目标终端发送所述目标终端的当前位置。
  17. 一种终端定位装置，其特征在于，所述装置包括：
    发送单元，用于当检测的用户运动第N步时，向服务器发送的用户运动第N步的计步信息和所述目标终端所处位置的多个无线接入点的信号强度，以便服务器根据所述计步信息和所述目标终端所处位置的多个无线接入点的信号强度确定目标终端运动第N步的位置；
    接收单元，用于接收服务器发送所述目标终端运动第N步的位置。
  18. 根据权利要求17所述的装置，其特征在于，还包括：
    推算单元，用于当接收到的用户运动第N步后所述目标终端的位置与接收到的用户运动第N-1步后的所述目标终端的位置相同时，则根据用户运动第N步后的计步信息通过行人航位推算得到用户运动第N步后所述目标终端的当前位置。
  19. 一种服务器，其特征在于，包括收发器、处理器和存储器；所述收发器用于与终端进行通信，所述存储器用于存放程序；所述处理器用于执行所述存储器存储的所述程序，以控制所述计算机设备执行权利要求1-7任意一项所述的方法。
  20. 一种终端，其特征在于，包括WiFi模块、传感器、收发器、处理器和存储器，所述WiFi模块用于确定终端所处位置的多个无线接入点的信号强度，所述传感器用于确定传感器信息，所述收发器用于与服务器进行通信，所述存储器用于存放程序；所述处理器用于执行所述存储器存储的所述程序，以控制所述计算机设备执行权利要求8或9所述的方法。
  21. 一种计算机可读存储介质，包括计算机可读指令，当计算机读取并执行所述计算机可读指令时，使得计算机执行如权利要求1-9任意一项所述的方法。
  22. 一种计算机程序产品，包括计算机可读指令，当计算机读取并执行所述计算机可读指令，使得计算机执行如权利要求1-9任意一项所述的方法。
PCT/CN2019/114990 2018-11-01 2019-11-01 定位方法及装置 WO2020088644A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN201811293931.X 2018-11-01
CN201811293931 2018-11-01
CN201910114921.3 2019-02-14
CN201910114921.3A CN111561921B (zh) 2019-02-14 2019-02-14 定位方法及装置

Publications (1)

Publication Number Publication Date
WO2020088644A1 true WO2020088644A1 (zh) 2020-05-07

Family

ID=70464357

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/114990 WO2020088644A1 (zh) 2018-11-01 2019-11-01 定位方法及装置

Country Status (1)

Country Link
WO (1) WO2020088644A1 (zh)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103402256A (zh) * 2013-07-11 2013-11-20 武汉大学 一种基于WiFi指纹的室内定位方法
CN104581628A (zh) * 2014-12-11 2015-04-29 北京智慧图科技有限责任公司 一种建立位置与特征信号的对应关系列表的方法及装置
CN104655137A (zh) * 2015-03-05 2015-05-27 中国人民解放军国防科学技术大学 行人航迹推测辅助的Wi-Fi信号指纹定位算法
CN104869541A (zh) * 2015-06-11 2015-08-26 吉林大学 一种室内定位追踪方法
CN105682227A (zh) * 2016-04-05 2016-06-15 上海雅丰信息科技有限公司 一种基于iBeacon的室内定位方法
CN105704652A (zh) * 2016-02-16 2016-06-22 中国科学院光电研究院 一种wlan/蓝牙定位中的指纹库采集和优化方法
CN107302754A (zh) * 2017-05-10 2017-10-27 广东工业大学 一种基于WiFi与PDR的室内定位简易方法
CN107396321A (zh) * 2017-08-02 2017-11-24 江南大学 基于手机传感器和iBeacon的无监督式室内定位方法
CN107580294A (zh) * 2017-09-07 2018-01-12 深圳市易景空间智能科技有限公司 一种室内混合定位方法
CN107966151A (zh) * 2017-11-22 2018-04-27 合肥工业大学 一种基于多传感器融合技术的室内行人航位推算方法

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103402256A (zh) * 2013-07-11 2013-11-20 武汉大学 一种基于WiFi指纹的室内定位方法
CN104581628A (zh) * 2014-12-11 2015-04-29 北京智慧图科技有限责任公司 一种建立位置与特征信号的对应关系列表的方法及装置
CN104655137A (zh) * 2015-03-05 2015-05-27 中国人民解放军国防科学技术大学 行人航迹推测辅助的Wi-Fi信号指纹定位算法
CN104869541A (zh) * 2015-06-11 2015-08-26 吉林大学 一种室内定位追踪方法
CN105704652A (zh) * 2016-02-16 2016-06-22 中国科学院光电研究院 一种wlan/蓝牙定位中的指纹库采集和优化方法
CN105682227A (zh) * 2016-04-05 2016-06-15 上海雅丰信息科技有限公司 一种基于iBeacon的室内定位方法
CN107302754A (zh) * 2017-05-10 2017-10-27 广东工业大学 一种基于WiFi与PDR的室内定位简易方法
CN107396321A (zh) * 2017-08-02 2017-11-24 江南大学 基于手机传感器和iBeacon的无监督式室内定位方法
CN107580294A (zh) * 2017-09-07 2018-01-12 深圳市易景空间智能科技有限公司 一种室内混合定位方法
CN107966151A (zh) * 2017-11-22 2018-04-27 合肥工业大学 一种基于多传感器融合技术的室内行人航位推算方法

Similar Documents

Publication Publication Date Title
CN107426687B (zh) 面向WiFi/PDR室内融合定位的自适应卡尔曼滤波方法
Cengiz Comprehensive analysis on least-squares lateration for indoor positioning systems
JP5740537B2 (ja) デバイス位置のための位置表示制御
CN109275095B (zh) 一种基于蓝牙的室内定位系统、定位设备和定位方法
CN106412839B (zh) 基于二级分区与指纹梯度匹配的室内定位与跟踪方法
US9661473B1 (en) Methods and apparatus for determining locations of devices in confined spaces
JP2015531053A (ja) 無線マップを動的に作成するためのシステム、方法、及びコンピュータプログラム
CN104076327B (zh) 基于搜索空间缩减的连续定位方法
CN109379711B (zh) 一种定位方法
Huang et al. RSS-based indoor positioning based on multi-dimensional kernel modeling and weighted average tracking
Li et al. Fine-grained indoor tracking by fusing inertial sensor and physical layer information in WLANs
WO2022100272A1 (zh) 室内定位方法及相关装置
Tian et al. HiQuadLoc: A RSS fingerprinting based indoor localization system for quadrotors
Hoang et al. A hidden Markov model for indoor user tracking based on WiFi fingerprinting and step detection
Dashti et al. Rssi localization with gaussian processes and tracking
Shin et al. Received signal strength-based robust positioning system in corridor environment
Xingli et al. Indoor positioning technology based on deep neural networks
US20240159857A1 (en) Method for constructing indoor map and related apparatus
Ye et al. Local HMM for indoor positioning based on fingerprinting and displacement ranging
CN114760684A (zh) 无线定位方法、路径识别模型的训练方法和装置
US11864056B2 (en) Developing a fingerprint map for determining an indoor location of a wireless device
WO2020088644A1 (zh) 定位方法及装置
Kumar et al. H2LWRF-PDR: An efficient indoor positioning algorithm using a single Wi-Fi access point and Pedestrian Dead Reckoning
Tang et al. Fingerprint localization using WLAN RSS and magnetic field with landmark detection
CN111561921B (zh) 定位方法及装置

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: 19879069

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: 19879069

Country of ref document: EP

Kind code of ref document: A1