Training methods for terminal positioning models, methods and devices for terminal positioning.
By acquiring uplink signal measurement data from the terminal and combining it with line-of-sight and non-line-of-sight environment judgments, the final position of the terminal is calculated using fingerprint database matching and iterative filtering algorithms. This solves the positioning accuracy problem in mixed line-of-sight and non-line-of-sight environments, achieving higher positioning reliability and accuracy.
Patent Information
- Application Number
- CN202211072997.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-09-02
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2042-09-02
AI Technical Summary
Existing positioning technologies cannot achieve optimal positioning results in mixed line-of-sight and non-line-of-sight environments, especially in places such as airports, train stations, large shopping malls, supermarkets, exhibition halls, and museums.
By acquiring the target uplink signal measurement data from the positioning request sent by the terminal, it is determined whether the terminal's coverage environment is line-of-sight or non-line-of-sight. The fingerprint database of wireless signal communication equipment is used for matching, and the final positioning location is calculated by combining iterative filtering algorithm.
It improves positioning accuracy in mixed line-of-sight and non-line-of-sight environments, ensures the effective application of positioning algorithms in different environments, and achieves higher positioning reliability and accuracy.
Smart Images

Figure CN117692857B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of core network technology, and in particular to a training method for a terminal positioning model, a terminal positioning method, and an apparatus. Background Technology
[0002] When deploying terminal devices, the priority is to provide users with excellent communication networks, and line-of-sight environments are not deliberately selected. Therefore, when deploying 5G equipment in airports, train stations, large shopping malls, supermarkets, exhibition halls and museums to support positioning services, the environment is mostly a mixture of line-of-sight and non-line-of-sight environments, and existing positioning technologies cannot achieve the best positioning effect. Summary of the Invention
[0003] This invention provides a method for training a terminal positioning model, a method for terminal positioning, and an apparatus for terminal positioning, in order to solve the problem of inaccurate positioning in existing mixed environments of line-of-sight and non-line-of-sight.
[0004] To solve the above-mentioned technical problems, the present invention is implemented as follows:
[0005] In a first aspect, the present invention provides a method for training a terminal positioning model, comprising:
[0006] The system acquires a location request sent by the terminal to be located, the location request including target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, relative arrival time, and signal reception power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located.
[0007] Based on the target uplink signal measurement data, the coverage environment of the terminal is determined; the coverage environment includes: line-of-sight environment and non-line-of-sight environment;
[0008] The relative arrival time and signal receiving power in the target uplink signal measurement data of the terminal are matched with the relative arrival time and signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device to obtain the uplink signal measurement data with the highest similarity, and the location information corresponding to the uplink signal measurement data with the highest similarity is used as the initial position; the fingerprint database includes: the correspondence between uplink signal measurement data and location information;
[0009] Based on the initial position, the final location of the terminal is calculated using an iterative filtering algorithm;
[0010] If the result points calculated based on the initial position do not converge, the initial position is re-determined based on the coverage environment, and the final positioning position of the terminal is calculated using an iterative filtering algorithm based on the initial position until the result points calculated based on the initial position converge, thus obtaining the final positioning position and completing the training of the terminal positioning model.
[0011] Optionally, the fingerprint database for wireless signal communication devices further includes: device information of the wireless signal communication devices; wherein the device information includes at least one of the following: the identification of the wireless signal communication device, the coordinates of the wireless signal communication device, the mounting height of the wireless signal communication device, and the coverage type of the wireless signal communication device; the coverage type includes: line-of-sight and non-line-of-sight.
[0012] Optionally, the fingerprint database for wireless signal communication devices further includes: device information of the wireless signal communication devices; wherein the device information includes at least one of the following: the identification of the wireless signal communication device, the coordinates of the wireless signal communication device, the mounting height of the wireless signal communication device, and the coverage type of the wireless signal communication device; the coverage type includes: line-of-sight and non-line-of-sight.
[0013] Optionally, determining the coverage environment of the terminal includes:
[0014] The information of the target wireless signal communication device contained in the target uplink signal measurement data of the terminal is obtained; the information includes the uplink signal measurement data of the target wireless signal communication device contained in the target uplink signal measurement data of the terminal.
[0015] If the target wireless signal communication device has a coverage environment of line-of-sight, and the uplink signal measurement data corresponding to the wireless signal communication device with a coverage environment of line-of-sight meets the preset requirements, then the coverage type of the terminal is determined to be line-of-sight.
[0016] Otherwise, the coverage type of the terminal is determined to be a non-line-of-sight environment.
[0017] Optionally, if the result point calculated based on the initial position does not converge, then recalculating the initial position based on the coverage environment includes:
[0018] If the coverage type of the terminal to be located is a line-of-sight environment, then the location of the wireless signal communication device with a line-of-sight coverage environment among the target wireless signal communication devices shall be used as the initial location.
[0019] Optionally, if the result point calculated based on the initial position does not converge, then recalculating the initial position based on the coverage environment includes:
[0020] If the coverage type of the terminal to be located is a non-line-of-sight environment, the relative arrival time in the target uplink signal measurement data of the terminal is matched with the relative arrival time in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device to obtain the uplink signal measurement data with the highest similarity, and the location information corresponding to the uplink signal measurement data with the highest similarity is used as the initial location.
[0021] Optionally, if the result point obtained by matching the relative arrival time in the target uplink signal measurement data of the terminal with the relative arrival time in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device does not converge, then the signal receiving power in the target uplink signal measurement data of the terminal and the signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device are matched to obtain the uplink signal measurement data with the highest similarity, and the position information corresponding to the uplink signal measurement data with the highest similarity is used as the initial position;
[0022] The final location of the terminal is calculated based on the initial location.
[0023] Secondly, the present invention provides a method for terminal positioning, comprising:
[0024] The system acquires a location request sent by the terminal to be located, the location request including target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, relative arrival time, and signal reception power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located.
[0025] Input the location request into the terminal location model;
[0026] Obtain the final location output by the terminal positioning model.
[0027] Thirdly, the present invention provides a training apparatus for a terminal positioning model, comprising:
[0028] The first acquisition module is used to acquire a positioning request sent by the terminal to be located, wherein the positioning request includes target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, the relative arrival time and signal receiving power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located.
[0029] The processing module is used to determine the coverage environment of the terminal based on the uplink signal measurement data of the target; the coverage environment includes: line-of-sight environment and non-line-of-sight environment;
[0030] The first calculation module is used to match the relative arrival time and signal receiving power in the target uplink signal measurement data of the terminal with the relative arrival time and signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device, to obtain the uplink signal measurement data with the highest similarity, and to use the location information corresponding to the uplink signal measurement data with the highest similarity as the initial position; the fingerprint database includes: the correspondence between uplink signal measurement data and location information;
[0031] The second calculation module is used to calculate the final location of the terminal based on the initial location using an iterative filtering algorithm.
[0032] The third calculation module is used to redetermine the initial position based on the coverage environment if the result points calculated based on the initial position do not converge, and calculate the final positioning position of the terminal based on the initial position using an iterative filtering algorithm until the result points calculated based on the initial position converge, thereby obtaining the final positioning position and completing the training of the terminal positioning model.
[0033] Optionally, the fingerprint database for wireless signal communication devices further includes: device information of the wireless signal communication devices; wherein the device information includes at least one of the following: the identification of the wireless signal communication device, the coordinates of the wireless signal communication device, the mounting height of the wireless signal communication device, and the coverage type of the wireless signal communication device; the coverage type includes: line-of-sight and non-line-of-sight.
[0034] Optionally, the processing module includes:
[0035] The acquisition submodule is used to acquire information about the target wireless signal communication device contained in the target uplink signal measurement data of the terminal; the information includes the uplink signal measurement data of the target wireless signal communication device contained in the target uplink signal measurement data of the terminal.
[0036] The processing submodule is used to determine that the coverage type of the terminal is a line-of-sight environment if there is a wireless signal communication device with a coverage environment of line-of-sight, and the uplink signal measurement data corresponding to the wireless signal communication device with a coverage environment of line-of-sight meets the preset requirements.
[0037] Otherwise, the coverage type of the terminal is determined to be a non-line-of-sight environment.
[0038] Optionally, the third computing module includes:
[0039] The first calculation submodule is used to take the location of a wireless signal communication device with a line-of-sight coverage environment among the target wireless signal communication devices as the initial location if the coverage type of the terminal to be located is a line-of-sight environment.
[0040] Optionally, the third computing module includes:
[0041] The second calculation submodule is used to match the relative arrival time in the target uplink signal measurement data of the terminal with the relative arrival time in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device if the coverage type of the terminal to be located is a non-line-of-sight environment, to obtain the uplink signal measurement data with the highest similarity, and to use the location information corresponding to the uplink signal measurement data with the highest similarity as the initial location.
[0042] Optionally, if the result point obtained by matching the relative arrival time in the target uplink signal measurement data of the terminal with the relative arrival time in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device does not converge, then the signal receiving power in the target uplink signal measurement data of the terminal and the signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device are matched to obtain the uplink signal measurement data with the highest similarity, and the position information corresponding to the uplink signal measurement data with the highest similarity is used as the initial position;
[0043] The final location of the terminal is calculated based on the initial location.
[0044] Fourthly, the present invention provides a device for terminal positioning, comprising:
[0045] The second acquisition module is used to acquire a positioning request sent by the terminal to be located, wherein the positioning request includes target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, the relative arrival time and signal receiving power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located.
[0046] An input module is used to input the positioning request into the terminal positioning model;
[0047] The third acquisition module is used to acquire the final positioning location output by the terminal positioning model.
[0048] Fifthly, the present invention provides an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the training method of the terminal positioning model as described in any one of the first aspects, or implement the steps in the terminal positioning method as described in the second aspect.
[0049] In a sixth aspect, the present invention provides a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the training method for a terminal positioning model as described in any one of the first aspects, or implement the steps in the terminal positioning method as described in the second aspect.
[0050] In this embodiment of the invention, by determining the coverage environment of the terminal and combining the information in the fingerprint database established by the corresponding wireless signal communication device in the coverage environment, a suitable initial position is selected, and the initial position is calculated by an iterative filtering algorithm to obtain the final positioning position, thereby ensuring the overall positioning accuracy of the positioning algorithm. Attached Figure Description
[0051] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:
[0052] Figure 1 This is a flowchart of a training method for a terminal positioning model provided in an embodiment of the present invention;
[0053] Figure 2 This is a network architecture diagram of a training method for a terminal positioning model provided in an embodiment of the present invention;
[0054] Figure 3 This is a field layout diagram of a training method for a terminal positioning model provided in an embodiment of the present invention;
[0055] Figure 4 This is a flowchart of a terminal positioning method provided in an embodiment of the present invention;
[0056] Figure 5 This is a schematic diagram of the structure of a training device for a terminal positioning model provided in an embodiment of the present invention;
[0057] Figure 6 This is a schematic diagram of the structure of a terminal positioning device provided in an embodiment of the present invention;
[0058] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0060] Please refer to Figure 1 This invention provides a method for training a terminal positioning model, comprising:
[0061] Step 11: Obtain the positioning request sent by the terminal to be located, wherein the positioning request includes target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, the relative arrival time and signal receiving power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located.
[0062] In this embodiment of the invention, terminal positioning is performed based on the target uplink signal measurement data of the terminal, thereby improving positioning reliability.
[0063] Step 12: Determine the coverage environment of the terminal based on the target uplink signal measurement data; the coverage environment includes: line-of-sight environment and non-line-of-sight environment;
[0064] In this embodiment of the invention, the line-of-sight or non-line-of-sight condition of the current positioning scene is determined first, and then calculations are performed for the two different scenarios. This can ensure the overall positioning accuracy of the positioning algorithm while giving full play to the advantages of using parameters for positioning in a line-of-sight environment.
[0065] Step 13: Match the relative arrival time and signal receiving power in the target uplink signal measurement data of the terminal with the relative arrival time and signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device to obtain the uplink signal measurement data with the highest similarity, and use the location information corresponding to the uplink signal measurement data with the highest similarity as the initial location; the fingerprint database includes: the correspondence between uplink signal measurement data and location information;
[0066] Step 14: Based on the initial position, calculate the final location of the terminal using an iterative filtering algorithm;
[0067] Step 15: If the result points calculated based on the initial position do not converge, the initial position is re-determined based on the coverage environment, and the final positioning position of the terminal is calculated using an iterative filtering algorithm based on the initial position until the result points calculated based on the initial position converge, thus obtaining the final positioning position and completing the training of the terminal positioning model.
[0068] In this embodiment of the invention, by determining the coverage environment of the terminal and combining the information in the fingerprint database established by the corresponding wireless signal communication device in the coverage environment, a suitable initial position is selected, and the initial position is calculated by an iterative filtering algorithm to obtain the final positioning position, thereby ensuring the overall positioning accuracy of the positioning algorithm.
[0069] In this embodiment of the invention, taking a 5G network as an example, please refer to the network structure for building a 5G positioning system. Figure 2 In step 11, the LMF (Location Management Function) module in the 5G positioning system interacts with the AMF (Access and Mobility Management Function) of the core network to obtain uplink signal measurement data of the UE (User Equipment) being located. The coverage environment of the UE being located includes multiple TRP (Transmit / Receive Point) wireless signal communication devices. The TRP communicates with the gNB (the next generation Node B). The identification, relative time of arrival, and signal reception power of the target wireless signal communication device are mainly used.
[0070] In this embodiment of the invention, step 12, determining the coverage environment of the terminal, includes: acquiring information about the target wireless signal communication device contained in the target uplink signal measurement data of the terminal; wherein, the specific device information of the wireless signal communication device is obtained through a fingerprint database of wireless signal communication devices, the fingerprint database of wireless signal communication devices includes: device information of the wireless signal communication device; the device information includes at least one of the following: the identification of the wireless signal communication device, the coordinates of the wireless signal communication device, the mounting height of the wireless signal communication device, and the coverage type of the wireless signal communication device; the coverage type includes: line-of-sight and non-line-of-sight;
[0071] If the target wireless signal communication device has a coverage environment of line-of-sight, and the uplink signal measurement data corresponding to the target wireless signal communication device meets the preset requirements, then the coverage type of the terminal is determined to be line-of-sight.
[0072] Otherwise, the coverage type of the terminal is determined to be a non-line-of-sight environment;
[0073] The preset requirements are that the relative arrival time is less than or equal to 20 ns and the signal receiving power is greater than or equal to -90 dB. The preset conditions can also be set freely according to experience and actual conditions.
[0074] In this embodiment of the invention, due to the propagation characteristics of wireless signals, the transmission path becomes longer and the transmission time increases due to signal refraction, reflection, and blockage during signal propagation. Therefore, the relative arrival time combined with the location of the wireless signal communication device is used as the primary basis for determining whether the terminal is currently in a line-of-sight environment, while the signal receiving power is used as a secondary basis.
[0075] In this embodiment of the invention, in step 13, the relative arrival time and signal receiving power in the target uplink signal measurement data of the terminal are matched with the relative arrival time and signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device to obtain the uplink signal measurement data with the highest similarity, and the location information corresponding to the uplink signal measurement data with the highest similarity is used as the initial position; the fingerprint database includes: the correspondence between uplink signal measurement data and location information;
[0076] For example: taking fingerprints as having 3 relative arrival times and 3 signal reception powers, let the user's fingerprint be... Let the fingerprint database match the fingerprint as ;
[0077] , and For the three relative arrival times of the user's fingerprint; , and The three signal receiving powers for the user's fingerprint; , and Match fingerprints to the fingerprint database using three relative arrival times; , and The three signal reception powers of fingerprints are matched to the fingerprint database; the relative arrival time and signal reception power in the target uplink signal measurement data of the terminal are matched with the relative arrival time and signal reception power in the uplink signal measurement data of the fingerprint database of the wireless signal communication device to obtain the similarity. The formula for calculating the similarity d is:
[0078]
[0079] The smaller the value of d, the higher the similarity. The location information of the fingerprint with the smallest calculated d value is selected as the initial location (x0, y0).
[0080] In this embodiment of the invention, the establishment of the fingerprint database before step 11 includes:
[0081] The basic data collection for wireless signal communication equipment includes: In the indoor environment where 5G indoor distributed base stations are set up, data collection personnel collect and record the physical information of the wireless signal communication equipment according to the actual situation, and store it in the database to form a basic data table for the wireless signal communication equipment, as shown in Table 1.
[0082] Table 1
[0083] serial number TRP_ID, the identifier of wireless signal communication devices latitude longitude Hanging height (meters) Coverage type 1 trp1 x1 y1 2.8 Sight distance 2 trp2 x2 y2 2.7 Sight distance 3 trp3 x3 y3 2.7 Sight distance … … … … … Non-line-of-sight n (where n is an integer greater than 3) trpn xn yn 3.1 Non-line-of-sight
[0084] Wherein, TRP_ID is the identification identifier of the wireless signal communication device, used to identify a unique device within the same cell; latitude and longitude correspond to the indoor map coordinate system, used to indicate the location of the wireless signal communication device; relative coordinates can also be used; mounting height is the height of the wireless signal communication device above the ground, not altitude; coverage type indicates whether the surrounding environment where the wireless signal communication device is deployed is line-of-sight or non-line-of-sight; for mixed line-of-sight and non-line-of-sight environments, the presence of indoor obstacles that obstruct the effective propagation of wireless signals around the deployment location of the wireless signal communication device is used as the basis for determining line-of-sight / non-line-of-sight. Please refer to [reference needed]. Figure 3 If there are no obstructions within a certain distance around TRP1 and TRP2, then the coverage environment of TRP1 and TRP2 is recorded as line-of-sight. If TRP3 is close to a wall and the wall obstructs the signal propagated by TRP3 to the outside, such signals do not form an effective wireless signal propagation for indoor personnel and are not considered as obstructions, but are also recorded as line-of-sight. All other TRPs are recorded as non-line-of-sight.
[0085] The fingerprint data collection process specifically includes: Data collectors, in the indoor environment where a 5G indoor distributed base station is set up, confirm their current location by referring to an indoor map based on the actual environment; the data collectors send the latitude and longitude of their current location to the server-side data collection system, stop moving, and begin data collection; the data collection system calls the 5G positioning system to obtain the uplink signal measurement data of the experimental terminal used by the data collectors at their current location; the GMLC (Gateway Mobile Location Center), LMF (Location Management Function), and UDM (Unified Data Management) and AMF (Access and Mobility Management Function) in the positioning system communicate with each other in the core network to complete multiple sets of uplink signal measurements and return them to the data collection system; after associating the experimental terminal's location with the data collection system, the uplink signal measurement data is stored in the database, and a completion response is returned; data collection continues at the next collection point; in practical applications, data collection is not limited to data collectors but can also be completed by robots or other automated collection equipment to improve data collection accuracy.
[0086] The data acquisition system includes at least one of the following: the coordinates of the wireless signal communication equipment, which correspond to the indoor map coordinate system and are used to indicate the location of the smart antenna; latitude and longitude coordinates or relative coordinates can be used; the mounting height of the experimental terminal, i.e., the height of the experimental terminal from the ground, not the altitude; and multiple sets of uplink signal measurement data of the wireless signal communication equipment and the experimental terminal, with the main parameters being the identification of the target wireless signal communication equipment, the relative arrival time, and the signal receiving power.
[0087] A fingerprint database as shown in Table 2 was established based on the collected data.
[0088] Table 2
[0089] serial number latitude longitude TRP_ID, the identifier of wireless signal communication devices relative arrival time Signal receiving power 1 x1 y1 trp1, trp2, trp3…trpn k1,k2,k3…kn r1,r2,r3…rn 2 x2 y2 trp1, trp2, trp3…trpn k1,k2,k3…kn r1,r2,r3…rn 3 x3 y3 trp1, trp2, trp3…trpn k1,k2,k3…kn r1,r2,r3…rn … … … … … … n (where n is an integer greater than 3) xn yn trp1, trp2, trp3…trpn k1,k2,k3…kn r1,r2,r3…rn
[0090] Among them, there will be multiple sets of different uplink signal measurement data under the same latitude and longitude.
[0091] In this embodiment of the invention, before step 14, if it is determined that the coverage environment of the terminal is a line-of-sight environment, then the horizontal distance between the location of the target wireless signal communication device with a line-of-sight coverage environment and the initial position is calculated. When the horizontal distance is less than or equal to the rated range, the original initial position is used as the initial point for calculation; otherwise, the location of the target wireless signal communication device with a line-of-sight coverage environment is used as the initial point for calculation.
[0092] In this embodiment of the invention, in step 14, the final location of the terminal is calculated using an iterative filtering algorithm based on the initial location. The specific calculation is as follows:
[0093] Calculate the signal propagation distance d based on the location of the wireless signal communication device. s = s * t; where s is the speed of light, t is time, and t is the relative arrival time value from the LMF (Location Management Function) measurement result; the signal propagation distance is the distance between the user terminal and the wireless signal communication equipment. Due to the height difference between the two, the horizontal distance d needs to be calculated using the Pythagorean theorem. d ;
[0094] Reuse the initial position The localization result is calculated using the iterative filtering algorithm, specifically as follows:
[0095] First, calculate the initial values for the first filter: ;
[0096] Where E is the expected value; for The covariance matrix; for The estimated value;
[0097] Second, calculate the Sigma point set at the previous time step (k-1):
[0098] The Sigma point set at time (k-1) is:
[0099] ;
[0100] in, Let be the covariance matrix at time k; n be the number of wireless communication devices; λ be the additive relaxation factor.
[0101] Third, predict the state vector and covariance matrix at the current time (k):
[0102] ;
[0103] ;
[0104] ;
[0105] in, The expected weighting; This is the state transition matrix;
[0106] Then, repeat step two to calculate the predicted value at the current time (k):
[0107] ;
[0108] ;
[0109] ;
[0110] ;
[0111] in, Let H be the predicted observation vector; H is the Jacobian matrix. The weights are the weights of the covariance matrix; for The autocovariance matrix; R represents the distance obtained by the base station from the time difference of arrival; k The covariance matrix of the observation noise; for and The cross-covariance matrix;
[0112] Fifth, perform measurement updates to obtain the final location:
[0113] ;
[0114] ;
[0115] ;
[0116] in, This is the gain matrix.
[0117] In this embodiment of the invention, the data calculation process designed based on the iterative filtering algorithm can accurately and quickly obtain the positioning results.
[0118] In this embodiment of the invention, optionally, the step of recalculating the initial position based on the coverage environment if the result point calculated based on the initial position does not converge includes:
[0119] If the coverage type of the terminal to be located is a line-of-sight environment, then the location of the wireless signal communication device with a line-of-sight coverage environment among the target wireless signal communication devices shall be used as the initial location.
[0120] In this embodiment of the invention, if the location of a wireless signal communication device in the target wireless signal communication device with a line-of-sight environment is used as the initial location, and the iteration error still increases, or if no usable result is obtained after reaching the rated number of iterations, then the positioning result is calculated according to the non-line-of-sight environment.
[0121] In this embodiment of the invention, optionally, the step of recalculating the initial position based on the coverage environment if the result point calculated based on the initial position does not converge includes:
[0122] If the coverage type of the terminal to be located is a non-line-of-sight environment, the relative arrival time in the target uplink signal measurement data of the terminal is matched with the relative arrival time in the uplink signal measurement data in the fingerprint database of the wireless signal communication device to obtain the location information with the highest similarity as the initial location.
[0123] For example: A fingerprint has six relative arrival times. Let the six relative arrival times of a user's fingerprint be s, s1, s2, s3, s4, s5, and s6. Let the six relative arrival times of the fingerprint matched in the fingerprint database be r, r1, r2, r3, r4, r5, and r6. Using the Euclidean distance calculation formula, the relative arrival times of the target uplink signal measurement data of the terminal and the relative arrival times of the uplink signal measurement data in the fingerprint database are matched to calculate the similarity d: The smaller the value of d, the higher the similarity. The location information of the fingerprint with the smallest calculated d value is selected as the initial location (x0, y0).
[0124] In this embodiment of the invention, optionally, if the relative arrival time in the target uplink signal measurement data of the terminal is matched with the relative arrival time in the uplink signal measurement data in the fingerprint database of the wireless signal communication device, and the result point obtained by calculating the initial position does not converge, then the signal receiving power in the target uplink signal measurement data of the terminal is matched with the signal receiving power in the uplink signal measurement data in the fingerprint database of the wireless signal communication device, and the position information with the highest similarity is used as the initial position.
[0125] The final location of the terminal is calculated based on the initial location.
[0126] For example: A fingerprint has six signal reception powers. Let the six signal reception powers of a user's fingerprint be p, p1, p2, p3, p4, p5, and p6, and let the six signal reception powers of the fingerprints matched in the fingerprint database be v, v1, v2, v3, v4, v5, and v6. Using the Euclidean distance calculation formula, the similarity d is calculated by matching the signal reception power in the target uplink signal measurement data of the terminal with the signal reception power in the uplink signal measurement data of the fingerprint database. ;
[0127] The smaller the value of d, the higher the similarity. The location information of the fingerprint with the smallest calculated d value is selected as the initial location (x0, y0).
[0128] In this embodiment of the invention, the environmental coverage of the current positioning scene, whether at line of sight or not, is determined first. Then, calculations are performed for the two different scenes, combined with different initial points. This ensures the overall positioning accuracy of the positioning algorithm while maximizing the advantages of the parameters used in line-of-sight positioning. Furthermore, multiple branch processes are designed for line-of-sight or non-line-of-sight environments, so that the iterative filtering algorithm can maximize the calculation of the most suitable positioning result during application.
[0129] Please refer to Figure 4 This invention provides a method for terminal positioning, comprising:
[0130] Step 41: Obtain the positioning request sent by the terminal to be located, wherein the positioning request includes target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, the relative arrival time and signal receiving power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located.
[0131] Step 42: Input the location request into the terminal location model;
[0132] Step 43: Obtain the final location output by the terminal positioning model.
[0133] In this embodiment of the invention, the positioning request of the terminal is input into the trained terminal positioning model. The positioning model determines the coverage environment of the terminal and combines the information in the fingerprint database established by the corresponding wireless signal communication device in the coverage environment to select a suitable initial position. The initial position is then calculated using an iterative filtering algorithm to obtain the final positioning position, thus ensuring the overall positioning accuracy of the positioning algorithm.
[0134] Please refer to Figure 5 This invention provides a training device for a terminal positioning model, comprising:
[0135] The first acquisition module 51 is used to acquire a positioning request sent by the terminal to be located, wherein the positioning request includes target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, the relative arrival time and the signal receiving power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located.
[0136] Processing module 52 is used to determine the coverage environment of the terminal based on the target uplink signal measurement data; the coverage environment includes: line-of-sight environment and non-line-of-sight environment;
[0137] The first calculation module 53 is used to match the relative arrival time and signal receiving power in the target uplink signal measurement data of the terminal with the relative arrival time and signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device, to obtain the uplink signal measurement data with the highest similarity, and to use the location information corresponding to the uplink signal measurement data with the highest similarity as the initial position; the fingerprint database includes: the correspondence between uplink signal measurement data and location information;
[0138] The second calculation module 54 is used to calculate the final positioning position of the terminal based on the initial position using an iterative filtering algorithm.
[0139] The third calculation module 55 is used to redetermine the initial position based on the coverage environment if the result points calculated based on the initial position do not converge, and calculate the final positioning position of the terminal based on the initial position through an iterative filtering algorithm until the result points calculated based on the initial position converge, thereby obtaining the final positioning position and completing the training of the terminal positioning model.
[0140] In this embodiment of the invention, optionally, the fingerprint database of the wireless signal communication device further includes: device information of the wireless signal communication device; wherein, the device information includes at least one of the following: the identification of the wireless signal communication device, the coordinates of the wireless signal communication device, the mounting height of the wireless signal communication device, and the coverage type of the wireless signal communication device; the coverage type includes: line-of-sight and non-line-of-sight.
[0141] In this embodiment of the invention, optionally, the processing module includes:
[0142] The acquisition submodule is used to acquire information about the target wireless signal communication device contained in the target uplink signal measurement data of the terminal; the information includes the uplink signal measurement data of the target wireless signal communication device contained in the target uplink signal measurement data of the terminal.
[0143] The processing submodule is used to determine that the coverage type of the terminal is a line-of-sight environment if there is a wireless signal communication device with a coverage environment of line-of-sight, and the uplink signal measurement data corresponding to the wireless signal communication device with a coverage environment of line-of-sight meets the preset requirements.
[0144] Otherwise, the coverage type of the terminal is determined to be a non-line-of-sight environment.
[0145] In this embodiment of the invention, optionally, the third calculation module includes:
[0146] The first calculation submodule is used to take the location of a wireless signal communication device with a line-of-sight coverage environment among the target wireless signal communication devices as the initial location if the coverage type of the terminal to be located is a line-of-sight environment.
[0147] In this embodiment of the invention, optionally, the third calculation module includes:
[0148] The second calculation submodule is used to match the relative arrival time in the target uplink signal measurement data of the terminal with the relative arrival time in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device if the coverage type of the terminal to be located is a non-line-of-sight environment, to obtain the uplink signal measurement data with the highest similarity, and to use the location information corresponding to the uplink signal measurement data with the highest similarity as the initial location.
[0149] In this embodiment of the invention, optionally, if the result point obtained by matching the relative arrival time in the target uplink signal measurement data of the terminal with the relative arrival time in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device does not converge, then the signal receiving power in the target uplink signal measurement data of the terminal and the signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device are matched to obtain the uplink signal measurement data with the highest similarity, and the position information corresponding to the uplink signal measurement data with the highest similarity is used as the initial position;
[0150] The final location of the terminal is calculated based on the initial location.
[0151] The terminal positioning device provided in this embodiment of the invention can achieve Figure 1 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.
[0152] Please refer to Figure 6 This invention provides a terminal positioning device, comprising:
[0153] The second acquisition module 61 is used to acquire a positioning request sent by the terminal to be located, wherein the positioning request includes target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, the relative arrival time and signal receiving power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located.
[0154] Input module 62 is used to input the positioning request into the terminal positioning model;
[0155] The third acquisition module 63 is used to acquire the final positioning location output by the terminal positioning model.
[0156] The terminal positioning device provided in this embodiment of the invention can achieve Figure 4 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.
[0157] This invention provides an electronic device 70, see [link to relevant documentation]. Figure 7 As shown, Figure 7 This is a schematic diagram of the electronic device 70 according to an embodiment of the present invention, including a processor 71, a memory 72, and a program or instructions stored in the memory 72 and executable on the processor 71. When the program or instructions are executed by the processor, they implement the steps of the training method of the terminal positioning model according to any one of the present invention, or implement the steps of the terminal positioning method according to any one of the present invention.
[0158] This invention provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the training method for the terminal positioning model as described in any of the above claims, or implement various processes of an embodiment of the terminal positioning method as described in any of the claims of this invention, and can achieve the same technical effect. To avoid repetition, further details are omitted here.
[0159] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0160] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0161] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0162] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a service classification device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0163] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. A training method for a terminal positioning model, characterized in that, include: The system acquires a location request sent by the terminal to be located, the location request including: target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, relative arrival time and signal reception power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located. Based on the target uplink signal measurement data, the coverage environment of the terminal is determined; the coverage environment includes: line-of-sight environment and non-line-of-sight environment; The relative arrival time and signal receiving power in the target uplink signal measurement data of the terminal are matched with the relative arrival time and signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device to obtain the uplink signal measurement data with the highest similarity, and the location information corresponding to the uplink signal measurement data with the highest similarity is used as the initial position; the fingerprint database includes: the correspondence between uplink signal measurement data and location information; Based on the initial position, the final location of the terminal is calculated using an iterative filtering algorithm; If the result points calculated based on the initial position do not converge, the initial position is re-determined based on the coverage environment, and the final positioning position of the terminal is calculated using an iterative filtering algorithm based on the initial position until the result points calculated based on the initial position converge, thus obtaining the final positioning position and completing the training of the terminal positioning model.
2. The training method for the terminal positioning model according to claim 1, characterized in that, The fingerprint database for wireless signal communication devices also includes: device information of the wireless signal communication devices; wherein, the device information includes at least one of the following: the identification of the wireless signal communication device, the coordinates of the wireless signal communication device, the mounting height of the wireless signal communication device, and the coverage type of the wireless signal communication device; the coverage type includes: line-of-sight and non-line-of-sight.
3. The training method for the terminal positioning model according to claim 2, characterized in that, The determination of the coverage environment of the terminal includes: The information of the target wireless signal communication device contained in the target uplink signal measurement data of the terminal is obtained; the information includes the uplink signal measurement data of the target wireless signal communication device contained in the target uplink signal measurement data of the terminal. If the target wireless signal communication device has a coverage environment of line-of-sight, and the uplink signal measurement data corresponding to the wireless signal communication device with a coverage environment of line-of-sight meets the preset requirements, then the coverage type of the terminal is determined to be line-of-sight. Otherwise, the coverage type of the terminal is determined to be a non-line-of-sight environment.
4. The training method for the terminal positioning model according to claim 3, characterized in that, If the result point calculated based on the initial position does not converge, then recalculating the initial position based on the coverage environment includes: If the coverage type of the terminal to be located is a line-of-sight environment, then the location of the wireless signal communication device with a line-of-sight coverage environment among the target wireless signal communication devices shall be used as the initial location.
5. The training method for the terminal positioning model according to claim 3, characterized in that, If the result point calculated based on the initial position does not converge, then recalculating the initial position based on the coverage environment includes: If the coverage type of the terminal to be located is a non-line-of-sight environment, the relative arrival time in the target uplink signal measurement data of the terminal is matched with the relative arrival time in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device to obtain the uplink signal measurement data with the highest similarity, and the location information corresponding to the uplink signal measurement data with the highest similarity is used as the initial location.
6. The training method for the terminal positioning model according to claim 5, characterized in that, If the relative arrival time in the target uplink signal measurement data of the terminal is matched with the relative arrival time in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device, and the result point obtained by calculating the initial position does not converge, then the signal receiving power in the target uplink signal measurement data of the terminal is matched with the signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device to obtain the uplink signal measurement data with the highest similarity, and the position information corresponding to the uplink signal measurement data with the highest similarity is used as the initial position; The final location of the terminal is calculated based on the initial location.
7. A method for terminal positioning, characterized in that, The terminal positioning model according to any one of claims 1-6 includes: The system acquires a location request sent by the terminal to be located, the location request including target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, relative arrival time, and signal reception power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located. Input the location request into the terminal location model; Obtain the final location output by the terminal positioning model.
8. A training device for a terminal positioning model, characterized in that, include: The first acquisition module is used to acquire a positioning request sent by the terminal to be located. The positioning request includes: target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, the relative arrival time and signal receiving power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located. The processing module is used to determine the coverage environment of the terminal based on the uplink signal measurement data of the target; the coverage environment includes: line-of-sight environment and non-line-of-sight environment; The first calculation module is used to match the relative arrival time and signal receiving power in the target uplink signal measurement data of the terminal with the relative arrival time and signal receiving power in the uplink signal measurement data of each target wireless signal communication device in the fingerprint database of the wireless signal communication device, to obtain the uplink signal measurement data with the highest similarity, and to use the location information corresponding to the uplink signal measurement data with the highest similarity as the initial position; the fingerprint database includes: the correspondence between uplink signal measurement data and location information; The second calculation module is used to calculate the final location of the terminal based on the initial location using an iterative filtering algorithm. The third calculation module is used to redetermine the initial position based on the coverage environment if the result points calculated based on the initial position do not converge, and calculate the final positioning position of the terminal based on the initial position using an iterative filtering algorithm until the result points calculated based on the initial position converge, thereby obtaining the final positioning position and completing the training of the terminal positioning model.
9. A device for terminal positioning, characterized in that, include: The second acquisition module is used to acquire a positioning request sent by the terminal to be located. The positioning request includes: target uplink signal measurement data; the target uplink signal measurement data includes: the identification of the target wireless signal communication device, the relative arrival time and signal receiving power; the target wireless signal communication device is a wireless signal communication device within the coverage environment of the terminal to be located. An input module is used to input the positioning request into a terminal positioning model, wherein the terminal positioning model is a model trained using the training device described in claim 8; The third acquisition module is used to acquire the final positioning location output by the terminal positioning model.
10. An electronic device, characterized in that: It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein when the program or instructions are executed by the processor, they implement the training method of the terminal positioning model as described in any one of claims 1 to 6, or implement the steps in the terminal positioning method as described in claim 7.
11. A readable storage medium, characterized in that: The readable storage medium stores a program or instructions that, when executed by a processor, implement the training method for the terminal positioning model as described in any one of claims 1 to 6, or implement the steps in the terminal positioning method as described in claim 7.
Citation Information
Patent Citations
Positioning track correction method and device, computer equipment and storage medium
CN110913338A
Positioning device
JP2016090311A
