CN114501615A - Terminal positioning method, device, computer equipment, storage medium and program product - Google Patents
Terminal positioning method, device, computer equipment, storage medium and program product Download PDFInfo
- Publication number
- CN114501615A CN114501615A CN202111573153.1A CN202111573153A CN114501615A CN 114501615 A CN114501615 A CN 114501615A CN 202111573153 A CN202111573153 A CN 202111573153A CN 114501615 A CN114501615 A CN 114501615A
- Authority
- CN
- China
- Prior art keywords
- motion
- model
- terminal
- azimuth
- positioning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012937 correction Methods 0.000 claims abstract description 136
- 238000012549 training Methods 0.000 claims description 49
- 238000012545 processing Methods 0.000 claims description 31
- 238000005259 measurement Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 25
- 230000015654 memory Effects 0.000 claims description 23
- 238000001914 filtration Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 18
- 230000001133 acceleration Effects 0.000 claims description 15
- 230000007704 transition Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 15
- 238000013528 artificial neural network Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 8
- 238000003062 neural network model Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000006403 short-term memory Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/08—Position of single direction-finder fixed by determining direction of a plurality of spaced sources of known location
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Quality & Reliability (AREA)
- Navigation (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The application relates to a terminal positioning method, a terminal positioning device, a computer device, a storage medium and a program product. The method comprises the following steps: obtaining a measured value obtained by measuring azimuth angles of uplink reference signals of a target terminal by a plurality of base stations; inputting the obtained measured values into a pre-trained azimuth correction model to obtain a plurality of azimuth correction values output by the azimuth correction model; inputting the plurality of azimuth angle correction values into a terminal motion model to obtain positioning data output by the terminal motion model; and positioning the target terminal according to the positioning data. By adopting the method, the positioning and tracking precision of the terminal can be improved.
Description
Technical Field
The present application relates to the field of positioning technologies, and in particular, to a terminal positioning method, apparatus, computer device, storage medium, and program product.
Background
With the continuous development of 5G technology, 5G networks are also more and more widely applied. In a 5G network, a base station may determine the location of a terminal by measuring an azimuth angle of an uplink reference signal of the terminal, and perform location tracking on the terminal. Meanwhile, in practical applications, due to the influence of various reflectors such as buildings or plants, the uplink reference signal of the terminal received by the base station usually contains a large number of multipath signals, which may cause interference to the reference signal.
In the conventional technology, measurement noise introduced by a received multipath signal is modeled as color noise, and an estimation value of the measurement noise is obtained, so that a positioning result of a terminal is determined according to an azimuth angle and the estimation value of the measurement noise.
However, in the conventional technology, in practical application, multipath signals under different scenes are different, and measurement noise introduced by the multipath signals is also different, so that the influence of the multipath signals under different scenes cannot be eliminated, and the accuracy of the base station on the positioning of the terminal is reduced.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a terminal positioning method, an apparatus, a computer device, a storage medium, and a program product, which can improve the terminal positioning accuracy.
In a first aspect, the present application provides a terminal positioning method. The method comprises the following steps:
obtaining a measured value obtained by measuring azimuth angles of uplink reference signals of a target terminal by a plurality of base stations; inputting a plurality of acquired measurement values into a pre-trained azimuth correction model to obtain a plurality of azimuth correction values output by the azimuth correction model; inputting the plurality of azimuth angle correction values into a terminal motion model to obtain positioning data output by the terminal motion model; and positioning the target terminal according to the positioning data.
In one embodiment, the terminal motion model includes a plurality of motion submodels, the plurality of operation submodels respectively correspond to different motion modes, the plurality of azimuth correction values are input into the terminal motion model, and the obtaining of the positioning data output by the terminal motion model includes: inputting the plurality of azimuth angle correction values into the plurality of motion submodels to obtain a positioning result output by each motion submodel; and acquiring the positioning data according to the positioning result output by each motion sub-model.
In one embodiment, the plurality of motion submodels includes at least one of a near uniform motion submodel, a near uniform acceleration motion submodel, and a near cooperative turning motion submodel; wherein, the sub-model of the near uniform motion corresponds to the motion mode of the uniform motion; the sub-model of the near uniform accelerated motion corresponds to the motion mode of the uniform accelerated motion; the near cooperative turning motion sub-model corresponds to a motion pattern of the cooperative turning motion.
In one embodiment, inputting the plurality of azimuth correction values into the plurality of motion submodels comprises: acquiring a plurality of first state estimation values of the target terminal at the current moment, wherein the plurality of first state estimation values correspond to different motion modes respectively; for each motion sub-model, inputting a first state estimation value consistent with a motion mode corresponding to the motion sub-model and the plurality of azimuth angle correction values into the motion sub-model.
In one embodiment, obtaining a plurality of first state estimation values of the target terminal at the current time includes: acquiring a plurality of second state estimation values of the target terminal at the previous moment before the current moment, wherein the plurality of second state estimation values correspond to different motion modes respectively; and for each motion mode, calculating the first state estimation value corresponding to the motion mode according to the second state estimation value corresponding to the motion mode and the state transition matrix corresponding to the motion mode.
In one embodiment, obtaining a plurality of second state estimation values of the target terminal at a previous time before the current time includes: and if the previous time is the initial time of the azimuth angle of the uplink reference signal of the target terminal measured by the base station, determining the second state estimation value according to the azimuth angle of the uplink reference signal of the target terminal measured at the initial time.
In one embodiment, inputting a plurality of acquired measurement values into a pre-trained azimuth correction model includes: performing low-pass filtering processing on the obtained multiple measured values; and inputting the value obtained by the low-pass filtering processing into the azimuth angle correction model.
In one embodiment, the training process of the azimuth correction model includes: acquiring a plurality of training samples, wherein the training samples comprise a sample measurement value of a base station on an azimuth angle of an uplink reference signal of a sample terminal and a true value of the azimuth angle of the uplink reference signal of the sample terminal; and training the initial azimuth correction model based on the plurality of training samples to obtain the azimuth correction model.
In a second aspect, the present application further provides a terminal positioning device. The device includes:
the first acquisition module is used for acquiring the measured values of the azimuth angles of the uplink reference signals of the target terminal by the base stations;
the first correction module is used for inputting the acquired multiple measured values into a pre-trained azimuth correction model to obtain multiple azimuth correction values output by the azimuth correction model;
the first positioning module is used for inputting the plurality of azimuth angle correction values into a terminal motion model to obtain positioning data output by the terminal motion model;
and the first processing module is used for positioning the target terminal according to the positioning data.
In one embodiment, the terminal motion model includes a plurality of motion submodels, the plurality of operation submodels respectively correspond to different motion modes, and the first positioning module is specifically configured to: inputting the plurality of azimuth angle correction values into the plurality of motion submodels to obtain a positioning result output by each motion submodel; and acquiring the positioning data according to the positioning result output by each motion sub-model.
In one embodiment, the plurality of motion submodels includes at least one of a near uniform motion submodel, a near uniform acceleration motion submodel, and a near cooperative turning motion submodel; wherein, the sub-model of the near uniform motion corresponds to the motion mode of the uniform motion; the sub-model of the near uniform accelerated motion corresponds to the motion mode of the uniform accelerated motion; the near cooperative turning motion sub-model corresponds to a motion pattern of the cooperative turning motion.
In one embodiment, the first positioning module is specifically configured to: acquiring a plurality of first state estimation values of the target terminal at the current moment, wherein the plurality of first state estimation values correspond to different motion modes respectively; for each motion sub-model, inputting a first state estimation value consistent with a motion mode corresponding to the motion sub-model and the plurality of azimuth angle correction values into the motion sub-model.
In one embodiment, the first positioning module is specifically configured to: acquiring a plurality of second state estimation values of the target terminal at the previous moment before the current moment, wherein the plurality of second state estimation values correspond to different motion modes respectively; and for each motion mode, calculating the first state estimation value corresponding to the motion mode according to the second state estimation value corresponding to the motion mode and the state transition matrix corresponding to the motion mode.
In one embodiment, the first positioning module is specifically configured to: and if the previous time is the initial time of the azimuth angle of the uplink reference signal of the target terminal measured by the base station, determining the second state estimation value according to the azimuth angle of the uplink reference signal of the target terminal measured at the initial time.
In one embodiment, the first correction module is specifically configured to: performing low-pass filtering processing on the obtained multiple measured values; and inputting the value obtained by the low-pass filtering processing into the azimuth angle correction model.
In one embodiment, the apparatus further comprises a training module configured to: acquiring a plurality of training samples, wherein the training samples comprise a sample measurement value of a base station on an azimuth angle of an uplink reference signal of a sample terminal and a true value of the azimuth angle of the uplink reference signal of the sample terminal; and training the initial azimuth correction model based on the plurality of training samples to obtain the azimuth correction model.
In a third aspect, the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method described in any one of the above first aspects when executing the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of any of the first aspects described above.
In a fifth aspect, the present application also provides a computer program product comprising a computer program that, when executed by a processor, performs the steps of the method of any of the first aspects described above.
According to the terminal positioning method, the terminal positioning device, the computer equipment, the storage medium and the program product, firstly, a measured value obtained by measuring the azimuth angle of the uplink reference signal of the target terminal by a plurality of base stations is obtained; because the uplink reference signal is accompanied by multipath signals and can cause signal interference, the measured value of the azimuth can be corrected by inputting a plurality of acquired measured values into a pre-trained azimuth correction model, so that the azimuth value is closer to a real azimuth value, and the influence on the multipath signals of any scene can be eliminated by correction, thereby obtaining a plurality of azimuth correction values output by the azimuth correction model; furthermore, the plurality of azimuth correction values are input into the terminal motion model to match the motion state of the target terminal, so that the positioning data output by the terminal motion model is obtained, and the positioning data of the target terminal is determined by combining the motion state and the azimuth correction values, so that the target terminal is positioned according to the positioning data, and the obtained positioning result is more accurate.
Drawings
Fig. 1 is an application environment diagram of a terminal location method in one embodiment;
fig. 2 is a flowchart illustrating a terminal positioning method according to an embodiment;
FIG. 3 is a diagram illustrating a local coordinate system of a 5G base station and orientation definition of the 5G base station in one embodiment;
FIG. 4 is a schematic flow chart illustrating a training process of an azimuth correction model according to an embodiment;
FIG. 5 is a flowchart illustrating a training process for obtaining positioning data according to an embodiment;
FIG. 6 is a schematic flow diagram of a training process for motion sub-model data acquisition in one embodiment;
FIG. 7 is a diagram illustrating an internal flow of a terminal motion model in one embodiment;
FIG. 8 is a flowchart illustrating a process of acquiring location data of a 5G terminal according to an embodiment;
FIG. 9 is a schematic diagram of a model training and application process in one embodiment;
FIG. 10 is a schematic diagram of an experimental scenario provided in an embodiment;
FIG. 11 is a graph of error comparison provided in one embodiment;
FIG. 12 is a block diagram of a terminal positioning device in one embodiment;
FIG. 13 is a block diagram of a second exemplary terminal positioning device according to an embodiment;
FIG. 14 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The 5G base station may measure an Angle of Arrival (AOA) of the uplink reference signal of the 5G terminal, so as to obtain azimuth information of the 5G terminal. And estimating the position of the 5G terminal according to the position and attitude information of the plurality of 5G base stations and the measured azimuth angle of the 5G terminal. The 5G base station is widely deployed, so that the high-precision positioning of the indoor and outdoor 5G terminals can be realized at low cost without additional equipment, and particularly, the method can effectively solve the problem of positioning of the 5G terminals in parking lots and tunnels when satellite navigation signals are unavailable.
In typical application scenarios such as urban areas and indoor areas, due to the influence of various reflectors, such as walls and trees, the signals received by the 5G base station usually contain a large amount of multipath signals, and if the multipath signals are not processed properly, the positioning and tracking accuracy is significantly reduced, and therefore further research is required to deal with the problem.
In the field of conventional data processing, in order to solve the problem, measurement noise of AOA introduced by multipath signals is usually modeled as color noise, and then kalman filtering is modified to adapt to the high-precision positioning and tracking problem under the condition of color noise, however, in the method, the color noise is assumed to obey a first-order gaussian-markov (Gauss-Ma rkov) model and model coefficients are known, in an actual environment, multipath signals under different scenes are different, so that it is difficult to use a set of model coefficients to process the high-precision positioning and tracking problem under all multipath scenes, and a problem of noise mismatch exists.
In addition, in practice, the motion mode of the 5G terminal cannot be simple uniform motion, acceleration, deceleration and turning motion usually exist, and when the actual motion mode of the 5G terminal does not accord with the assumed model, the positioning and tracking accuracy is greatly reduced, so that the problem of model mismatch exists.
The terminal positioning method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. The computer device 101 is in communication with the base station 102 and the base station 103, the base station 102 and the base station 103 can measure an azimuth of an uplink reference signal of a target terminal to obtain a corresponding measured value, and send the measured value to the computer device 101, and the computer device 101 calculates positioning data of the target terminal according to the received measured value of each azimuth to obtain a positioning result of the target terminal. The computer device 101 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, servers, server clusters, and the like; it should be noted that the computer device 101 may communicate with a plurality of base stations to obtain the measured value of the range angle of the target terminal measured by each base station, for example, only the base station 102 and the base station 103 are provided in fig. 1 for illustration, and the number of the base stations is not limited in the embodiment of the present application.
In one embodiment, as shown in fig. 2, a terminal positioning method is provided, which is described by taking the method as an example applied to the computer device 101 in fig. 1, and includes the following steps:
The base station, namely a public mobile communication base station, is an interface device for accessing mobile equipment to the internet, and nowadays, 5G base stations are widely used; generally, a plurality of 5G base stations may be deployed in a large area, and each 5G base station may receive an uplink reference signal of a 5G terminal using a mobile network in the area, so that an azimuth value of the terminal may be obtained by measuring an angle of arrival of the uplink reference signal. The terminal may be a locatable device such as a mobile phone or an automatic robot.
When a terminal needs to be located, the terminal is used as a target terminal, and in an area where the terminal is located, each base station in the area can obtain a measurement value of an azimuth angle by measuring the azimuth angle of an uplink reference signal of the target terminal, so that measurement values of a plurality of azimuth angles are obtained. The computer device can receive or actively acquire the measured value of the azimuth angle of the target terminal measured by each base station so as to perform positioning calculation on the target terminal.
The uplink reference signal of the target terminal received by each base station is usually accompanied by a multipath signal, the multipath signal can cause a large amount of measurement noise to be introduced into the measured azimuth angle, and the positioning calculation is directly performed according to the measured value of each measured azimuth angle, which can reduce the accuracy of the positioning result.
The pre-trained azimuth angle correction model is used for correcting the measured values of the azimuth angles according to the input measured values of the azimuth angles so as to remove the measurement noise in the measured values of the azimuth angles, and therefore the azimuth angle correction model can input a plurality of azimuth angle correction values which are obtained after the measured values of the azimuth angles are subjected to measurement noise processing and are closer to the actual values of the azimuth angles. And according to a plurality of azimuth correction values output by the azimuth correction model, calculating the subsequent positioning result of the target terminal.
In an actual scene, the motion mode of the 5G terminal cannot be simple uniform motion, acceleration, deceleration and turning motion usually exist, when the actual motion mode of the 5G terminal is not consistent with the assumed motion mode, the positioning and tracking precision is greatly reduced, a model mismatch problem exists, and the accuracy of the positioning and tracking result is greatly reduced. Therefore, in the embodiment of the present application, the plurality of azimuth correction values obtained through correction are input into a predetermined terminal motion model to match the actual motion mode of the target terminal; and the terminal motion model can determine and output the positioning data of the target terminal through the plurality of azimuth angle correction values and the motion mode of the target terminal.
And step 204, positioning the target terminal according to the positioning data.
The positioning data may be coordinates of the target terminal in a rectangular coordinate system of the area, and according to the positioning data, the position of the target terminal may be determined, so as to perform positioning processing on the target terminal.
In the terminal positioning method, firstly, a plurality of base stations are obtained to measure the azimuth angle of the uplink reference signal of a target terminal to obtain a measured value; because the uplink reference signal is accompanied by multipath signals and can cause signal interference, the measured value of the azimuth can be corrected by inputting a plurality of acquired measured values into a pre-trained azimuth correction model, so that the azimuth value is closer to a real azimuth value, and the influence on the multipath signals of any scene can be eliminated by correction, thereby obtaining a plurality of azimuth correction values output by the azimuth correction model; furthermore, the plurality of azimuth correction values are input into the terminal motion model to match the motion state of the target terminal, so that positioning data output by the terminal motion model is obtained, the positioning data of the target terminal is determined by combining the motion state and the azimuth correction values, the target terminal is positioned according to the positioning data, and the obtained positioning result is more accurate.
In an embodiment, optionally, the azimuth correction model in step 202 may be obtained by training a neural network model; the Neural Network model may be a feed-forward Neural Network or a recurrent Neural Network, for example, a Long Short Term Memory Neural Network (LSTMNN), a Multilayer Perceptron (MLP), a Radial Basis Function (RBF), or the like, without loss of generality.
In general, in a scenario accompanied by multipath signals, a measured value of an azimuth angle of a 5G terminal measured by a 5G base station may be expressed as a mathematical equation shown in formula (1):
in the formula (1), the first and second groups,
the psi is a counterclockwise included angle between a y-axis of the local coordinate system of the 5G base station and a y-axis of the rectangular coordinate system of the geographic area where the y-axis of the local coordinate system of the 5G base station is, i.e., a normal direction of the array antenna, and the y-axis of the rectangular coordinate system of the geographic area where the y-axis of the local coordinate system of the 5G base station is, i.e., an orientation of the 5G base station. Fig. 3 is a schematic diagram illustrating a local coordinate system of a 5G base station and an orientation definition of the 5G base station according to an embodiment of the present disclosure. ollRepresenting the origin of a rectangular coordinate system of the located geographic area; x is the number ofllAnd yllRespectively representing an x axis and a y axis of a rectangular coordinate system of the located geographic region;
and
respectively as the coordinates of the phase center of the 5G base station array antenna under a rectangular coordinate system of the geographic area where the phase center is located;
and
respectively as the coordinates of the phase center of the 5G terminal array antenna in a rectangular coordinate system of the geographic area where the antenna is located; arctan (g) is an arctangent function;
measurement noise, i.e., color noise, introduced for multipath signals;
is white noise.
In a geographic area including a plurality of 5G base stations, each 5G base station may measure an azimuth angle of an uplink reference signal of a certain 5G terminal, and the total expression may be expressed as a mathematical equation as shown in formula (4):
in the formula (4), N represents the number of 5G base stations,
the measured value of the azimuth angle of the 5G terminal array antenna phase center under a 5G base station n local coordinate system is represented; psinThe included angle between the y axis of a local coordinate system of the 5G base station n, namely the normal direction of the array antenna, and the y axis of a rectangular coordinate system of the geographic area where the array antenna is located is anticlockwise;
and
respectively as the coordinates of the phase center of the n array antenna of the 5G base station under a rectangular coordinate system of the geographic area,
measurement noise for 5G base station n;
for white noise of 5G base station n, equation (4) can be further abbreviated as equation (7):
wherein,
further, formula (1) represents a mathematical expression of the azimuth angle of the 5G terminal measured by the 5G base station at any time, and at the time K +1, the mathematical expression of the azimuth angle of the 5G terminal measured by each 5G base station at the time K +1 can be simplified to formula (14) according to formula (1):
wherein K is a positive integer,
is white noise, and is,
wherein M is the time before the K +1 time; xi [. cndot ] is a linear or non-linear function; thus, the following formula (16) can be obtained:
assuming that θ is approximately constant around the time k +1, it can be obtained
θ (k +1) ≈ θ (η) equation (17) where η is a time near k +1, and thus, it is possible to obtain
According to the formula (16) and the formula (18), after calculation, the following expression can be obtained:
mathematically transforming equation (19) to yield equation (20):
where Ψ [ · ] is an unknown linear or nonlinear function that can be approximated using a neural network, ω (k +1) is the residual error term, and equation (20) can be expressed as:
in equation (21), θ (k +1) can be approximated by using a neural network according to equation (20), and θ (k +1) can be regarded as a measured value of the azimuth angle of the 5G terminal measured by the 5G base station,
visible viewThe measured value of the azimuth angle of the 5G terminal measured by the 5G base station is processed by the neural network model to obtain the value of the azimuth angle output by the neural network model; according to the formula (14) and the formula (21), the value of the azimuth angle output after the neural network model processing is not affected by the measurement noise introduced by the multipath signal, so that the positioning data of the 5G terminal can be further calculated according to the value of the azimuth angle output after the neural network model processing, and the accuracy of the positioning data is improved.
The azimuth correction model can be constructed by adopting a long-time memory neural network, a multilayer perceptron or a radial basis function neural network and other neural network algorithms according to a formula (20) so as to correct the measured value of the azimuth of the 5G terminal measured by the 5G base station and improve the accuracy of acquiring the positioning data.
In one embodiment, inputting a plurality of the acquired measurement values into a pre-trained azimuth correction model comprises: performing low-pass filtering processing on the obtained multiple measured values; and inputting the value obtained by the low-pass filtering processing into the azimuth angle correction model.
When the measured value of the azimuth angle of the uplink reference signal of the target terminal measured by each base station is obtained, Low-Pass filtering processing may be performed on each measured value, for example, a Low Pass Filter (LPF) is used, so that a high-frequency signal in each measured value may be removed; by inputting the value subjected to the low-pass filtering processing into the azimuth correction model, the influence of high-frequency signals can be removed, the processing of the azimuth correction model on the measured value can be accelerated, and the generalization capability of the azimuth correction model can be improved.
Please refer to fig. 4, which illustrates a flowchart of a training process of an azimuth correction model according to an embodiment of the present application; the training process of the azimuth correction model comprises the following steps:
During the training of the azimuth correction model, a certain terminal is used as a sample terminal in a certain geographic area, the measured value of the azimuth of the uplink reference signal of the sample terminal by a certain base station in the geographic area is collected, the true value of the azimuth of the uplink reference signal of the sample terminal received by the base station is collected at the same time, and the neural network model is trained according to the measured value and the true value to obtain the azimuth correction model; the measured values and the real values of a plurality of sample terminals can be obtained to train the azimuth correction model.
The collected measurement value of the sample terminal is input into a pre-constructed Neural Network after low-pass filtering, the output of an LPF is taken as the input of an LSTMNN (Long Short Term Memory Neural Network, LSTMNN) as an example, and the reference output of the LSTMNN is the true value of the azimuth angle of the sample terminal; and training the LSTMNN according to each training sample, and continuously adjusting parameters until the error between the output of the LSTMNN and the true value of the azimuth is less than a certain threshold value, so as to obtain model parameters of the LSTMNN, and taking the LSTMNN of the determined model parameters as an azimuth correction model for correcting the measured value of the azimuth of the target terminal.
Training is carried out on the model by collecting training samples, so that the precision of the model is continuously improved, an azimuth correction model capable of correcting the measured value of the azimuth of the terminal is obtained, an accurate correction value of the azimuth is provided for acquiring the positioning data of the target terminal, and the precision of the positioning data is improved.
In one embodiment, the terminal motion model includes a plurality of motion sub-models, and the plurality of operation sub-models respectively correspond to different motion modes.
The plurality of motion submodels comprise at least one of a near uniform motion submodel, a near uniform acceleration motion submodel and a near cooperative turning motion submodel; wherein, the sub-model of the near uniform motion corresponds to the motion mode of the uniform motion; the sub-model of the near uniform accelerated motion corresponds to the motion mode of the uniform accelerated motion; the near cooperative turning motion sub-model corresponds to a motion pattern of the cooperative turning motion.
The motion state of the terminal can be uniform motion, uniform acceleration motion, turning motion or other motion, and respectively corresponds to different motion sub-models; the method includes the steps that a near uniform motion sub-model, a near uniform acceleration sub-model and a near cooperative turning motion sub-model are listed only by way of example; in order to match the actual motion state of the terminal, the terminal motion model may include a near uniform velocity motion sub-model, a near uniform acceleration motion sub-model and a near cooperative turning motion sub-model; the terminal motion model also can comprise at least one of a near-uniform-speed motion submodel, a near-uniform acceleration motion submodel and a near-cooperative turning motion submodel and motion submodels corresponding to other motion states. Further, the terminal motion model can determine the motion state of the target terminal according to the input correction value of the azimuth angle, so that more accurate positioning data can be output.
Please refer to fig. 5, which illustrates a flowchart of acquiring positioning data according to an embodiment of the present application; inputting the plurality of azimuth angle correction values into a terminal motion model to obtain positioning data output by the terminal motion model, wherein the positioning data comprises:
After the azimuth correction values output by the plurality of azimuth correction models are obtained, the azimuth correction values are input into a terminal motion model, specifically, in the terminal motion model, each azimuth correction value is input into a plurality of motion submodels included in the terminal motion model, and each motion submodel performs motion mode calculation according to each received azimuth correction value to obtain a positioning result output by each motion submodel and related to a target terminal.
Fig. 6 is a schematic flow chart illustrating a motion sub-model data acquisition process provided by an embodiment of the present application; inputting a plurality of azimuth correction values into the plurality of motion sub-models, including:
601, acquiring a plurality of first state estimation values of the target terminal at the current moment; wherein the plurality of first state estimation values respectively correspond to different motion modes.
The current moment refers to the moment when the azimuth angle measurement value of the target terminal is obtained; in the terminal motion model, each motion sub-model acquires an azimuth angle correction value input into the terminal motion model; and acquiring a first state estimation value corresponding to the motion mode of the target terminal, wherein the first state estimation value is a predicted value and is used for inputting into each motion sub-model, so that the calculation of the motion mode of the target terminal is carried out by combining the acquired azimuth angle correction value of the target terminal at the current moment, and the corresponding positioning result is output. The first state estimation value can be obtained by interacting a plurality of state estimation values of the target terminal at the previous moment of the current moment.
In the terminal motion model, noise estimation and calculation of positioning data are further performed according to positioning results output by each motion sub-model, so that positioning data of the target terminal, namely positioning coordinates, can be output, and the target terminal can be positioned according to the positioning data.
Optionally, the terminal motion Model may be implemented by using an Adaptive Interaction Multiple Model (AIMM) algorithm, which includes three motion sub models, namely a Near Constant Velocity (NCV) motion Model, a Near uniform Acceleration (NCA) motion Model, and a Near Coordinated Turning (NCT) motion Model. An internal flow diagram of the terminal motion model implemented according to the AIMM algorithm may be as shown in fig. 7. Wherein, X (K)NCVThe state of the target terminal at the previous moment of the current moment of the target terminal corresponding to the near uniform motion modeEstimate, X (K)NCAThe state estimation value of the target terminal at the previous moment of the current moment of the target terminal corresponding to the near-uniform acceleration motion mode is obtained; x (K)NCTIs a state estimation value of the target terminal at a time immediately preceding the current time of the target terminal corresponding to the near cooperative turning motion pattern,
the azimuth angle correction value of the current moment of the target terminal input into the terminal motion model.
And each motion sub-model performs motion mode matching calculation by acquiring the azimuth angle correction value of the target terminal at the current moment and each first state estimation value corresponding to each motion mode, so as to solve the problem that the accurate precision of positioning data is influenced due to the mismatch of the motion models of the terminals.
In one embodiment, obtaining a plurality of first state estimation values of the target terminal at the current time includes: acquiring a plurality of second state estimation values of the target terminal at the previous moment before the current moment, wherein the plurality of second state estimation values correspond to different motion modes respectively; and for each motion mode, calculating the first state estimation value corresponding to the motion mode according to the second state estimation value corresponding to the motion mode and the state transition matrix corresponding to the motion mode.
Wherein, the evolution model of the motion state of the 5G terminal can be represented by the following formula (22):
x (k +1) ═ fx (k) + v (k) equation (22)
In the formula (22), F is a state transition matrix, and different motion modes correspond to different state transition matrices; x (k) is a state estimation value of the terminal at the moment k, namely a second state estimation value, and different motion modes correspond to different second state estimation values; v (k) is state noise at the moment k, and is obtained by internal calculation of a terminal motion model; x (k +1) is a first state estimation value of the terminal at the k moment; for each motion mode, the first state estimation value corresponding to the motion mode can be calculated according to the second state estimation value corresponding to the motion mode and the state transition matrix corresponding to the motion mode, i.e. in the form of formula (22).
For the target terminal, taking the sub-model of the near uniform motion as an example, the first state estimation value of the target terminal at the current time, that is, the time k +1, obtained according to the formula (22) is:
x(k+1)＝[x(k+1) vx(k+1 )y(k+1) vy(k+1)]Tformula (23)
Wherein x (k +1) and y (k +1) are respectively the horizontal and vertical coordinate values of the target terminal at the moment of k +1 under the rectangular coordinate system of the geographic region where the target terminal is located, and vx(k +1) and vyAnd (k +1) is the movement speed of the target terminal at the moment k +1 respectively.
Equation (21) can be expressed using the following mathematical equation:
in the formula (24), the first and second groups,
ω＝[ω1 ω2 L ωN]T。
from equation (23) and equation (24), a state space model for terminal location tracking can be constructed, namely:
x(k+1)＝Fx(k)+v(k)
that is, the terminal motion model may be constructed in combination with the AIMM algorithm according to equation (25).
In one embodiment, obtaining a plurality of second state estimates for the target terminal at a previous time before the current time comprises: and if the previous time is the initial time of the azimuth angle of the uplink reference signal of the target terminal measured by the base station, determining the second state estimation value according to the azimuth angle of the uplink reference signal of the target terminal measured at the initial time.
Wherein, in the formula (22), x (k) is the end of time kA state estimate of the terminal, i.e. a second state estimate; the initial time is the time when each base station initially receives the uplink reference signal of the target terminal for the first time, and according to the formula (1), the measured value of the azimuth angle of the target terminal measured by each base station includes the coordinates of the measured target terminal in the rectangular coordinate system of the region where the target terminal is located, that is, the coordinates are obtained
And
obtaining the coordinates of the target terminal measured at the initial moment, i.e.
And
and obtaining the state estimation value of the initial time of the target terminal by adopting a nonlinear least square method. For example, the initial time state estimation value is denoted as x (1), x (1) is input to the terminal motion model, and the state estimation value at the next time, that is, x (2), can be obtained from x (1) as can be seen from equation (22); therefore, at the current time, that is, at the time K +1, a plurality of first state estimation values x (K +1) of the target terminal can be obtained through a plurality of second state estimation values x (K) pre-calculated in the terminal motion mode. Furthermore, the output result of each motion submodel can be determined by combining the input correction value of the azimuth angle of the target terminal through each first state estimation value, and the positioning data can be further acquired, so that the target terminal can be positioned.
In an embodiment, as shown in fig. 8, a schematic flowchart of acquiring 5G terminal location data provided in an embodiment of the present application is shown; the method comprises the following steps that a 5G terminal which needs to be positioned and tracked is used as a target terminal, and the positioning process of the target terminal comprises the following steps:
The computer equipment can obtain a measured value obtained by measuring the azimuth angle of the uplink reference signal of the target terminal by each base station in the geographic area.
In step 802, a plurality of acquired measurement values are low-pass filtered.
Wherein, a Low Pass Filter (LPF) can be used to perform Low Pass filtering processing on the measured values, so as to remove high frequency signals in each measured value; by inputting the value subjected to the low-pass filtering processing into the azimuth correction model, the influence of high-frequency signals can be removed, the processing of the azimuth correction model on the measured value can be accelerated, and the generalization capability of the azimuth correction model can be improved.
Step 803, inputting the obtained multiple measured values into a pre-trained azimuth correction model to obtain multiple azimuth correction values output by the azimuth correction model.
The training process of the azimuth correction model comprises the following steps: in the geographic area, a certain 5G terminal is used as a sample terminal, a measured value of the azimuth angle of the uplink reference signal of the sample terminal by a certain base station in the geographic area is collected, a true value of the azimuth angle of the uplink reference signal of the sample terminal received by the base station is collected at the same time, and a neural network model is trained according to the measured value and the true value to obtain an azimuth angle correction model; the measured values and the real values of a plurality of sample terminals can be obtained to train the azimuth correction model. And training the LSTMNN based on a plurality of training samples to obtain an azimuth correction model.
And step 804, inputting a plurality of azimuth angle correction values into the terminal motion model.
The terminal motion model comprises a plurality of motion submodels, and the plurality of motion submodels comprise at least one of a near uniform motion submodel, a near uniform acceleration motion submodel and a near cooperative turning motion submodel; wherein, the sub-model of the near uniform motion corresponds to the motion mode of the uniform motion; the sub-model of the near uniform accelerated motion corresponds to the motion mode of the uniform accelerated motion; the near cooperative turning motion sub-model corresponds to a motion pattern of the cooperative turning motion.
Step 805, obtaining a plurality of first state estimation values of the target terminal at the current time.
Wherein the plurality of first state estimation values correspond to different motion modes respectively; and calculating a first state estimation value corresponding to the motion mode according to the second state estimation value corresponding to the motion mode and the state transition matrix corresponding to the motion mode by acquiring a plurality of second state estimation values of the target terminal at the previous moment before the current moment. And each first state estimation value is a prediction value and is used for being input into each motion sub-model and calculating the positioning result of the target terminal by combining the azimuth angle correction value of the target terminal. Wherein the plurality of second state estimation values correspond to different motion modes, respectively.
And if the previous moment is the initial moment of the azimuth angle of the uplink reference signal of the target terminal measured by the base station, determining a second state estimation value according to the azimuth angle of the uplink reference signal of the target terminal measured at the initial moment.
Step 806, inputting the first state estimation value consistent with the motion mode corresponding to the motion sub-model and the plurality of azimuth angle correction values into the motion sub-model.
In step 807, positioning data is obtained according to the positioning result output by each motion sub-model.
Please refer to fig. 9, which illustrates a schematic diagram of a model training and application process provided by an embodiment of the present application; in the training process, the LSTMNN model is continuously trained based on training samples, and the determined model parameters are issued to the LSTMNN applied to the positioning and tracking process, so that the positioning data of the target terminal can be obtained by combining with the AIMM algorithm, wherein,
θ (k) is the true value of the azimuth of the training sample, which is the measured value of the azimuth of the training sample.
An experimental scene is shown in fig. 10, a black dotted arrow represents a traveling route of a 5G terminal, and fig. 11 shows a positioning and tracking error of a conventional positioning method and a positioning and tracking error of a use method provided by the present application, where a horizontal axis is time and a vertical axis is the positioning and tracking error; the solid line is the positioning and tracking error of the traditional positioning method, and the dotted line is the positioning and tracking error of the using method provided by the application; as can be seen from fig. 11, the method used in the present application can significantly reduce the positioning and tracking error in the presence of multipath signals.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a terminal positioning apparatus for implementing the above-mentioned terminal positioning method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so specific limitations in one or more embodiments of the terminal positioning device provided below can be referred to the limitations of the terminal positioning method in the foregoing, and details are not described herein again.
In one embodiment, as shown in fig. 12, there is provided a terminal positioning device including: a first obtaining module 1201, a first correcting module 1202, a first positioning module 1203 and a first processing module 1204, wherein:
a first obtaining module 1201, configured to obtain measured values of azimuth angles of uplink reference signals of a target terminal by multiple base stations; the first correction module 1202 is configured to input the obtained multiple measured values into a pre-trained azimuth correction model, so as to obtain multiple azimuth correction values output by the azimuth correction model; a first positioning module 1203, configured to input the plurality of azimuth correction values into a terminal motion model, so as to obtain positioning data output by the terminal motion model; the first processing module 1204 is configured to perform positioning processing on the target terminal according to the positioning data.
In an embodiment, the terminal motion model includes a plurality of motion submodels, the plurality of operation submodels respectively correspond to different motion modes, and the first positioning module 1203 is specifically configured to: inputting the plurality of azimuth angle correction values into the plurality of motion submodels to obtain a positioning result output by each motion submodel; and acquiring the positioning data according to the positioning result output by each motion sub-model.
In one embodiment, the plurality of motion submodels includes at least one of a near uniform motion submodel, a near uniform acceleration motion submodel, and a near cooperative turning motion submodel; wherein, the sub-model of the near uniform motion corresponds to the motion mode of the uniform motion; the sub-model of the near uniform accelerated motion corresponds to the motion mode of the uniform accelerated motion; the near cooperative turning motion sub-model corresponds to a motion pattern of the cooperative turning motion.
In an embodiment, the first positioning module 1203 is specifically configured to: acquiring a plurality of first state estimation values of the target terminal at the current moment, wherein the plurality of first state estimation values correspond to different motion modes respectively; for each motion sub-model, inputting a first state estimation value consistent with a motion mode corresponding to the motion sub-model and the plurality of azimuth angle correction values into the motion sub-model.
In an embodiment, the first positioning module 1203 is specifically configured to: acquiring a plurality of second state estimation values of the target terminal at the previous moment before the current moment, wherein the plurality of second state estimation values correspond to different motion modes respectively; and for each motion mode, calculating the first state estimation value corresponding to the motion mode according to the second state estimation value corresponding to the motion mode and the state transition matrix corresponding to the motion mode.
In an embodiment, the first positioning module 1203 is specifically configured to: and if the previous time is the initial time of the azimuth angle of the uplink reference signal of the target terminal measured by the base station, determining the second state estimation value according to the azimuth angle of the uplink reference signal of the target terminal measured at the initial time.
In one embodiment, the first calibration module 1202 is specifically configured to: performing low-pass filtering processing on the obtained multiple measured values; and inputting the value obtained by the low-pass filtering processing into the azimuth angle correction model.
In an embodiment, as shown in fig. 13, which shows a block diagram of a second terminal positioning apparatus provided in an embodiment of the present application, the terminal positioning apparatus 1300 includes: a first obtaining module 1201, a first correcting module 1202, a first positioning module 1203, a first processing module 1204, and a training module 1205, wherein:
a training module 1205 for: acquiring a plurality of training samples, wherein the training samples comprise a sample measurement value of a base station on an azimuth angle of an uplink reference signal of a sample terminal and a true value of the azimuth angle of the uplink reference signal of the sample terminal; and training the initial azimuth correction model based on the plurality of training samples to obtain the azimuth correction model.
The modules in the terminal positioning device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 14. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing terminal positioning data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a terminal positioning method.
Those skilled in the art will appreciate that the architecture shown in fig. 14 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
obtaining a measured value obtained by measuring azimuth angles of uplink reference signals of a target terminal by a plurality of base stations; inputting a plurality of acquired measurement values into a pre-trained azimuth correction model to obtain a plurality of azimuth correction values output by the azimuth correction model; inputting the plurality of azimuth angle correction values into a terminal motion model to obtain positioning data output by the terminal motion model; and positioning the target terminal according to the positioning data.
In one embodiment, the terminal motion model includes a plurality of motion sub-models, the plurality of operation sub-models respectively correspond to different motion modes, and the plurality of azimuth correction values are input into the terminal motion model to obtain the positioning data output by the terminal motion model, including: inputting the plurality of azimuth angle correction values into the plurality of motion submodels to obtain a positioning result output by each motion submodel; and acquiring the positioning data according to the positioning result output by each motion sub-model.
In one embodiment, the plurality of motion sub-models includes at least one of a near uniform motion sub-model, a near uniform acceleration motion sub-model, and a near cooperative turning motion sub-model; wherein, the sub-model of the near uniform motion corresponds to the motion mode of the uniform motion; the sub-model of the near uniform accelerated motion corresponds to the motion mode of the uniform accelerated motion; the near cooperative turning motion sub-model corresponds to a motion pattern of the cooperative turning motion.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a plurality of first state estimation values of the target terminal at the current moment, wherein the plurality of first state estimation values correspond to different motion modes respectively; for each motion sub-model, inputting a first state estimation value consistent with a motion mode corresponding to the motion sub-model and the plurality of azimuth angle correction values into the motion sub-model.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a plurality of second state estimation values of the target terminal at the previous moment before the current moment, wherein the plurality of second state estimation values correspond to different motion modes respectively; and for each motion mode, calculating the first state estimation value corresponding to the motion mode according to the second state estimation value corresponding to the motion mode and the state transition matrix corresponding to the motion mode.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and if the previous time is the initial time of the azimuth angle of the uplink reference signal of the target terminal measured by the base station, determining the second state estimation value according to the azimuth angle of the uplink reference signal of the target terminal measured at the initial time.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
performing low-pass filtering processing on the obtained multiple measured values; and inputting the value obtained by the low-pass filtering processing into the azimuth angle correction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a plurality of training samples, wherein the training samples comprise a sample measurement value of a base station on an azimuth angle of an uplink reference signal of a sample terminal and a true value of the azimuth angle of the uplink reference signal of the sample terminal; and training the initial azimuth correction model based on the plurality of training samples to obtain the azimuth correction model.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (12)
1. A terminal positioning method, characterized in that the method comprises:
obtaining a measured value obtained by measuring azimuth angles of uplink reference signals of a target terminal by a plurality of base stations;
inputting the obtained measured values into a pre-trained azimuth correction model to obtain a plurality of azimuth correction values output by the azimuth correction model;
inputting the plurality of azimuth angle correction values into a terminal motion model to obtain positioning data output by the terminal motion model;
and positioning the target terminal according to the positioning data.
2. The method of claim 1, wherein the terminal motion model comprises a plurality of motion sub-models, the plurality of running sub-models respectively correspond to different motion modes, and the inputting the plurality of azimuth correction values into the terminal motion model to obtain the positioning data output by the terminal motion model comprises:
inputting the plurality of azimuth angle correction values into the plurality of motion submodels to obtain a positioning result output by each motion submodel;
and acquiring the positioning data according to the positioning result output by each motion sub-model.
3. The method of claim 2, wherein the plurality of motion sub-models comprises at least one of a near uniform motion sub-model, a near uniform acceleration motion sub-model, and a near cooperative turning motion sub-model;
the sub-model of the near uniform motion corresponds to a motion mode of the uniform motion; the sub-model of the near uniform accelerated motion corresponds to the motion mode of the uniform accelerated motion; the near cooperative turning motion sub-model corresponds to a motion mode of the cooperative turning motion.
4. A method according to claim 2 or 3, wherein said inputting the plurality of azimuth correction values into the plurality of motion submodels comprises:
acquiring a plurality of first state estimation values of the target terminal at the current moment, wherein the plurality of first state estimation values correspond to different motion modes respectively;
for each of the motion sub-models, inputting a first state estimation value that coincides with a motion mode corresponding to the motion sub-model and the plurality of azimuth correction values into the motion sub-model.
5. The method of claim 4, wherein obtaining a plurality of first state estimates for the target terminal at a current time comprises:
acquiring a plurality of second state estimation values of the target terminal at the previous moment before the current moment, wherein the plurality of second state estimation values correspond to different motion modes respectively;
and for each motion mode, calculating the first state estimation value corresponding to the motion mode according to the second state estimation value corresponding to the motion mode and the state transition matrix corresponding to the motion mode.
6. The method of claim 5, wherein obtaining a plurality of second state estimates for the target terminal at a previous time before the current time comprises:
and if the previous moment is the initial moment of the azimuth angle of the uplink reference signal of the target terminal measured by the base station, determining the second state estimation value according to the azimuth angle of the uplink reference signal of the target terminal measured at the initial moment.
7. The method of claim 1, wherein inputting the acquired plurality of measurements into a pre-trained azimuth correction model comprises:
carrying out low-pass filtering processing on the obtained multiple measured values;
and inputting the value obtained by the low-pass filtering processing into the azimuth angle correction model.
8. The method of claim 1, wherein the training process of the azimuth correction model comprises:
acquiring a plurality of training samples, wherein the training samples comprise a sample measurement value of a base station on an azimuth angle of an uplink reference signal of a sample terminal and a true value of the azimuth angle of the uplink reference signal of the sample terminal;
and training an initial azimuth correction model based on the plurality of training samples to obtain the azimuth correction model.
9. A terminal positioning apparatus, characterized in that the apparatus comprises:
the first acquisition module is used for acquiring the measured values of the azimuth angles of the uplink reference signals of the target terminal by the base stations;
the first correction module is used for inputting the acquired multiple measured values into a pre-trained azimuth correction model to obtain multiple azimuth correction values output by the azimuth correction model;
the first positioning module is used for inputting the plurality of azimuth angle correction values into a terminal motion model to obtain positioning data output by the terminal motion model;
and the first processing module is used for positioning the target terminal according to the positioning data.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
12. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 8 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111573153.1A CN114501615B (en) | 2021-12-21 | 2021-12-21 | Terminal positioning method, terminal positioning device, computer equipment, storage medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111573153.1A CN114501615B (en) | 2021-12-21 | 2021-12-21 | Terminal positioning method, terminal positioning device, computer equipment, storage medium and program product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114501615A true CN114501615A (en) | 2022-05-13 |
| CN114501615B CN114501615B (en) | 2024-04-12 |
Family
ID=81494286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111573153.1A Active CN114501615B (en) | 2021-12-21 | 2021-12-21 | Terminal positioning method, terminal positioning device, computer equipment, storage medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114501615B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116193574A (en) * | 2023-02-22 | 2023-05-30 | 中电建建筑集团有限公司 | 5g network-based observation information fusion positioning key technical method and system |
| WO2024140722A1 (en) * | 2022-12-31 | 2024-07-04 | 网络通信与安全紫金山实验室 | Terminal position determination method and apparatus, and computer device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101813759A (en) * | 2009-02-19 | 2010-08-25 | 中国科学院微电子研究所 | Method for carrying out subsequent processing on original positioning result of global positioning system |
| US20190195631A1 (en) * | 2017-12-22 | 2019-06-27 | Ubtech Robotics Corp | Positioning method, positioning device, and robot |
| CN112484710A (en) * | 2019-09-11 | 2021-03-12 | 杭州海康微影传感科技有限公司 | Target positioning method, device and equipment and storage medium |
| CN113484879A (en) * | 2021-06-02 | 2021-10-08 | 歌尔股份有限公司 | Positioning method and device of wearable equipment |
-
2021
- 2021-12-21 CN CN202111573153.1A patent/CN114501615B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101813759A (en) * | 2009-02-19 | 2010-08-25 | 中国科学院微电子研究所 | Method for carrying out subsequent processing on original positioning result of global positioning system |
| US20190195631A1 (en) * | 2017-12-22 | 2019-06-27 | Ubtech Robotics Corp | Positioning method, positioning device, and robot |
| CN112484710A (en) * | 2019-09-11 | 2021-03-12 | 杭州海康微影传感科技有限公司 | Target positioning method, device and equipment and storage medium |
| CN113484879A (en) * | 2021-06-02 | 2021-10-08 | 歌尔股份有限公司 | Positioning method and device of wearable equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024140722A1 (en) * | 2022-12-31 | 2024-07-04 | 网络通信与安全紫金山实验室 | Terminal position determination method and apparatus, and computer device and storage medium |
| CN116193574A (en) * | 2023-02-22 | 2023-05-30 | 中电建建筑集团有限公司 | 5g network-based observation information fusion positioning key technical method and system |
| CN116193574B (en) * | 2023-02-22 | 2023-10-13 | 中电建建筑集团有限公司 | 5g network-based observation information fusion positioning key technical method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114501615B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110849369B (en) | Robot tracking method, device, equipment and computer readable storage medium | |
| CN104019813B (en) | Method and system of target immediate location and map establishing | |
| CN111896914A (en) | Cooperative positioning method, device, equipment and storage medium | |
| CN111208492A (en) | Vehicle-mounted laser radar external parameter calibration method and device, computer equipment and storage medium | |
| CN109883423B (en) | Positioning method, system, equipment and storage medium based on Kalman filtering | |
| CN114501615B (en) | Terminal positioning method, terminal positioning device, computer equipment, storage medium and program product | |
| CN109782240A (en) | One kind being based on the modified multisensor syste error registration method of recursion and system | |
| CN112184768A (en) | SFM reconstruction method and device based on laser radar and computer equipment | |
| CN115063454B (en) | Multi-target tracking matching method, device, terminal and storage medium | |
| CN111707294B (en) | Pedestrian navigation zero-speed interval detection method and device based on optimal interval estimation | |
| CN114430294A (en) | Method and device for calibrating ground beams of GEO satellite, electronic equipment and storage medium | |
| CN114485594B (en) | Antenna pose information measuring method, apparatus, device, medium, and program product | |
| CN112965076A (en) | Multi-radar positioning system and method for robot | |
| CN109343013B (en) | Spatial registration method and system based on restarting mechanism | |
| CN112435299B (en) | Airborne point cloud assisted satellite image stereo matching point cloud orientation method | |
| CN111665470A (en) | Positioning method and device and robot | |
| CN116608859A (en) | Navigation method, storage medium and device of self-adaptive unscented Kalman filtering based on threshold processing | |
| CN115688569A (en) | Gain adjustment method, gain adjustment device, computer equipment and storage medium | |
| US10848920B1 (en) | Generation of precise geospatial coordinates | |
| CN109919998B (en) | Satellite attitude determination method and device and terminal equipment | |
| CN114415698A (en) | Robot, positioning method and device of robot and computer equipment | |
| CN114463429A (en) | Robot, map creation method, positioning method, and medium | |
| CN115035190A (en) | Pose positioning method and device, computer equipment and storage medium | |
| CN112800889A (en) | Target tracking method based on distributed matrix weighting and Gaussian filtering fusion | |
| CN114705223A (en) | Inertial navigation error compensation method and system for multiple mobile intelligent bodies in target tracking |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: No. 9 Mozhou East Road, Nanjing City, Jiangsu Province, 211111 Patentee after: Zijinshan Laboratory Country or region after: China Address before: No. 9 Mozhou East Road, Jiangning Economic Development Zone, Jiangning District, Nanjing City, Jiangsu Province Patentee before: Purple Mountain Laboratories Country or region before: China |