Terminal positioning method and device, electronic equipment, readable storage medium and program product

Abstract

The invention relates to a terminal positioning method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a first positioning result and a second positioning result of a user terminal; the first positioning result comprises position information determined according to the time difference of an uplink signal of the user terminal arriving at different base stations; the second positioning result comprises pose information determined based on a simultaneous positioning mapping method; and fusing the first positioning result and the second positioning result to obtain a target positioning result of the user terminal. By adopting the method, the positioning result precision of the terminal can be improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for locating a terminal. Background Technology

[0002] UTDOA (Uplink Time Difference of Arrival) is a cellular network-based positioning technology. Its principle is to calculate the distance difference between the terminal and different PRRUs based on the time difference reported by the terminal to different high-precision base station antennas (PRRU, Pico Remote Radio Unit), and then calculate the location coordinates of the terminal by solving the corresponding system of equations.

[0003] However, when the base station deployment density is insufficient, the positioning accuracy of this positioning method is low; or, in complex indoor scenarios, signal loss may occur due to obstructions, which will also affect the positioning accuracy.

[0004] Therefore, the relevant technologies suffer from the problem of low accuracy in terminal positioning results. Summary of the Invention

[0005] Therefore, it is necessary to provide a positioning method, device, electronic device, computer-readable storage medium, and computer program product for a terminal that can improve the accuracy of positioning results, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for locating a terminal, comprising:

[0007] The system acquires a first positioning result and a second positioning result from the user terminal. The first positioning result includes location information determined by the time difference between the uplink signals of the user terminal arriving at different base stations. The second positioning result includes pose information determined based on a simultaneous positioning and mapping method.

[0008] By combining the first positioning result and the second positioning result, the target positioning result of the user terminal is obtained.

[0009] In one embodiment, the position information in the first positioning result corresponds to a first coordinate system, and the pose information in the second positioning result corresponds to a second coordinate system;

[0010] The process of fusing the first positioning result and the second positioning result to obtain the target positioning result of the user terminal includes:

[0011] Based on the first positioning result, the pose information in the second positioning result is transformed from the second coordinate system to the first coordinate system to obtain the target pose information; the target pose information includes the target position information and target posture information of the user terminal in the first coordinate system;

[0012] The target pose information is used as the target localization result.

[0013] In one embodiment, the step of transforming the pose information in the second positioning result from the second coordinate system to the first coordinate system based on the first positioning result to obtain the target pose information includes:

[0014] The first positioning result and the second positioning result are input into the positioning result optimization model to obtain the target pose information; the positioning result optimization model is used to iteratively output the optimized pose information until there is optimized pose information that satisfies the target constraints; the optimized pose information includes the optimized position information and optimized attitude information of the user terminal in the first coordinate system.

[0015] The optimized pose information that satisfies the target constraints is used as the target pose information;

[0016] The target constraints include a first constraint and a second constraint; the first constraint is used to constrain the difference between the optimized position information and the position information in the first positioning result; the second constraint is used to constrain the difference between the optimized pose information and the pose information in the second positioning result.

[0017] In one embodiment, inputting the first positioning result and the second positioning result into a positioning result optimization model to obtain the target pose information includes:

[0018] Obtain first difference information corresponding to the optimized pose information; the first difference information is used to characterize the difference between the optimized position information and the position information in the first positioning result.

[0019] Obtain the second difference information corresponding to the optimized pose information; the second difference information is used to characterize the difference between the optimized pose information and the pose information in the second localization result.

[0020] If the sum of the first difference value in the first difference information and the second difference value in the second difference information satisfies the preset convergence condition, it is determined that the optimized pose information satisfies the target constraint.

[0021] In one embodiment, the pose information in the second positioning result includes multiple elements, each corresponding one-to-one with the optimized pose information. The step of obtaining the second difference information corresponding to the optimized pose information includes:

[0022] Obtain the first pose increment information between two adjacent pose information in the second positioning result;

[0023] Obtain second pose increment information; the second pose increment information includes pose increment information between two adjacent optimized pose information corresponding to the two adjacent pose information;

[0024] The second difference information is determined based on the difference between the first pose increment information and the second pose increment information.

[0025] In one embodiment, obtaining the second pose increment information includes:

[0026] The two adjacent optimized pose information corresponding to the two adjacent pose information are transformed from the first coordinate system to the second coordinate system to obtain the transformed two adjacent optimized pose information.

[0027] The pose increment information between two adjacent optimized pose information after the transformation is obtained as the second pose increment information.

[0028] In one embodiment, the second difference information includes the difference information between the first pose increment information between all two adjacent pose information and the second pose increment information between the corresponding two adjacent optimized pose information; the first difference information includes the difference information between all the optimized position information in the optimized pose information and the position information in the first positioning result.

[0029] In one embodiment, the acquisition frequency corresponding to the pose information in the second positioning result is higher than the acquisition frequency corresponding to the position information in the first positioning result. The pose information in the second positioning result includes multiple components. The step of transforming the pose information in the second positioning result from the second coordinate system to the first coordinate system to obtain the target pose information includes:

[0030] Each pose information in the second positioning result is transformed from the second coordinate system to the first coordinate system to obtain the target pose information.

[0031] Secondly, this application also provides a positioning device for a terminal, comprising:

[0032] The acquisition unit is used to acquire a first positioning result and a second positioning result of the user terminal; the first positioning result includes location information determined by the time difference of the uplink signal of the user terminal arriving at different base stations; the second positioning result includes pose information determined based on the simultaneous positioning and mapping method.

[0033] The fusion unit is used to fuse the first positioning result and the second positioning result to obtain the target positioning result of the user terminal.

[0034] Thirdly, this application also provides an electronic device. The electronic device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, implements the steps of the method described above.

[0035] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0036] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described method.

[0037] The aforementioned positioning method, apparatus, electronic device, computer-readable storage medium, and computer program product for the terminal obtain a first positioning result and a second positioning result of the user terminal; the first positioning result includes location information determined by the time difference of the uplink signal of the user terminal reaching different base stations; the second positioning result includes pose information determined based on the simultaneous positioning mapping method; and the target positioning result of the user terminal is obtained by fusing the first positioning result and the second positioning result.

[0038] Thus, the location information determined by the time difference of uplink signals arriving at different base stations from the user terminal is used as the first positioning result of the user terminal, and the pose information of the user terminal determined by the simultaneous positioning and mapping method is used as the second positioning result of the user terminal. The first positioning result determined by the uplink time difference positioning method lacks local constraints, while the second positioning result determined by the simultaneous positioning and mapping method, although locally accurate, suffers from cumulative errors. By fusing the first and second positioning results, the first positioning result determined by the uplink time difference positioning method provides global information, while the second positioning result determined by the simultaneous positioning and mapping method provides local information. Utilizing the advantages of both methods, the fused target positioning result is locally accurate and globally drift-free, enhancing the positioning effect of the user terminal and effectively improving its positioning accuracy. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating a terminal positioning method in one embodiment;

[0041] Figure 2 This is a flowchart illustrating another terminal positioning method in one embodiment;

[0042] Figure 3 This is a flowchart illustrating the steps for obtaining target pose information in one embodiment;

[0043] Figure 4 This is a schematic diagram of a pose graph structure in one embodiment;

[0044] Figure 5 This is an example diagram illustrating the effect of fusing the first and second positioning results in one embodiment.

[0045] Figure 6 This is a flowchart illustrating a terminal positioning method in another embodiment;

[0046] Figure 7 This is a structural block diagram of a positioning device for a terminal in one embodiment;

[0047] Figure 8 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0050] In one embodiment, such as Figure 1 As shown, a method for locating a terminal is provided. This embodiment illustrates the application of this method to an electronic device. In this embodiment, the method includes steps S110 to S120:

[0051] Step S110: Obtain the first and second positioning results of the user terminal.

[0052] The first positioning result includes location information determined by the time difference between the uplink signals of the user terminal reaching different base stations.

[0053] Among them, electronic devices can use the 5G (5th Generation Mobile Communication Technology) UTDOA algorithm to calculate the distance difference between the user terminal and different PRRUs based on the time difference of the uplink signal reported by the user terminal (mobile phone, tablet, vehicle device, etc.) to different 5G high-precision base station antennas. Then, by solving the corresponding equation system, the location coordinates (5G positioning coordinates) of the user terminal are calculated and located as the first positioning result.

[0054] The second localization result includes pose information determined based on the simultaneous localization mapping method.

[0055] Among them, the simultaneous localization and mapping method refers to the Simultaneous Localization and Mapping (SLAM) algorithm.

[0056] In this embodiment, the simultaneous localization and mapping (SLAM) algorithm can employ Visual Simultaneous Localization and Mapping (VSLAM), a technology based on visual information for simultaneous localization and mapping. It utilizes a camera to perceive the environment and processes image data in real time to achieve localization and map building for the robot or mobile terminal. VSLAM can provide the terminal's pose information over a certain period, including 6DOF (six degrees of freedom) pose information.

[0057] Among them, the pose information of the user terminal determined by the simultaneous localization mapping method can be used as the second localization result of the user terminal.

[0058] Step S120: Fuse the first positioning result and the second positioning result to obtain the target positioning result of the user terminal.

[0059] In practice, electronic devices can fuse the first positioning result and the second positioning result to obtain the target positioning result of the user terminal.

[0060] In practical applications, such as Figure 2 The diagram illustrates another terminal positioning method. The electronic device can acquire a pre-built global optimizer, inputting the first positioning result (containing 5G positioning coordinates) from the 5G positioning module and the second positioning result (containing 6DOF pose) from the VSLAM positioning module into the global optimizer. The global optimizer performs iterative optimization and outputs the optimized result as the target positioning result.

[0061] In the above-mentioned terminal positioning method, a first positioning result and a second positioning result of the user terminal are obtained; the first positioning result includes the location information determined by the time difference of the uplink signal of the user terminal reaching different base stations; the second positioning result includes the pose information determined by the simultaneous positioning and mapping method; the first positioning result and the second positioning result are fused to obtain the target positioning result of the user terminal.

[0062] Thus, the location information determined by the time difference of uplink signals arriving at different base stations from the user terminal is used as the first positioning result of the user terminal, and the pose information of the user terminal determined by the simultaneous positioning and mapping method is used as the second positioning result of the user terminal. The first positioning result determined by the uplink time difference positioning method lacks local constraints, while the second positioning result determined by the simultaneous positioning and mapping method, although locally accurate, suffers from cumulative errors. By fusing the first and second positioning results, the first positioning result determined by the uplink time difference positioning method provides global information, while the second positioning result determined by the simultaneous positioning and mapping method provides local information. Utilizing the advantages of both methods, the fused target positioning result is locally accurate and globally drift-free, enhancing the positioning effect of the user terminal and effectively improving its positioning accuracy.

[0063] In some embodiments, the position information in the first positioning result corresponds to the first coordinate system, and the pose information in the second positioning result corresponds to the second coordinate system; fusing the first positioning result and the second positioning result to obtain the target positioning result of the user terminal includes: based on the first positioning result, transforming the pose information in the second positioning result from the second coordinate system to the first coordinate system to obtain target pose information; the target pose information includes the target position information and target posture information of the user terminal in the first coordinate system; and using the target pose information as the target positioning result.

[0064] Here, the first coordinate system can refer to the coordinate system in which the location information in the first positioning result, i.e., the 5G positioning coordinates, are located. In practical applications, the first coordinate system can be named the global coordinate system.

[0065] The second coordinate system can refer to the coordinate system containing the pose information in the second positioning result, i.e., the 6DOF pose. In practical applications, the second coordinate system can be named the local coordinate system.

[0066] Furthermore, the second positioning result can be calculated by the user terminal itself using the VSLAM algorithm, so that the electronic device can obtain the second positioning result from the user terminal. The coordinate system established with the terminal initiating the VSLAM algorithm as the origin, i.e., the VSLAM local coordinate system, is the second coordinate system.

[0067] In specific implementation, during the process of fusing the first positioning result and the second positioning result to obtain the target positioning result of the user terminal, the electronic device can, based on the first positioning result, transform the pose information in the second positioning result from the second coordinate system to the first coordinate system to obtain the target pose information; the target pose information includes the target position information and target attitude information of the user terminal in the first coordinate system; and the target pose information is used as the target positioning result.

[0068] Thus, the target localization result includes the target position information of the user terminal in the first coordinate system after fusion. Compared with the position information in the first localization result, the target position information in the target localization result not only includes the global information provided by the 5GUTDOA algorithm, but also incorporates the local information provided by VSLAM, thereby optimizing the 5G positioning effect and making its positioning accuracy higher. In addition, the target localization result also provides the target attitude information of the user terminal in the first coordinate system, providing richer positioning information.

[0069] In some embodiments, based on the first positioning result, the pose information in the second positioning result is transformed from the second coordinate system to the first coordinate system to obtain the target pose information, including: inputting the first positioning result and the second positioning result into a positioning result optimization model to obtain the target pose information; the positioning result optimization model is used to iteratively output the optimized pose information until there is optimized pose information that satisfies the target constraints; the optimized pose information includes the optimized position information and optimized attitude information of the user terminal in the first coordinate system; and the optimized pose information that satisfies the target constraints is used as the target pose information.

[0070] The target constraints include a first constraint and a second constraint; the first constraint is used to constrain the difference between the optimized position information and the position information in the first positioning result; the second constraint is used to constrain the difference between the optimized pose information and the pose information in the second positioning result.

[0071] The first constraint can be named the global constraint (global residual), and the second constraint can be named the local constraint (local residual).

[0072] In specific implementation, when the electronic device transforms the pose information in the second positioning result from the second coordinate system to the first coordinate system based on the first positioning result to obtain the target pose information, the first positioning result and the second positioning result can be input into the positioning result optimization model to obtain the target pose information.

[0073] The localization result optimization model can serve as a global optimizer, iteratively optimizing the first and second localization results under the constraints of the target constraints. It iteratively outputs optimized pose information until optimized pose information that satisfies the target constraints exists. This optimized pose information is then used as the target pose information. Thus, the optimized position information within the optimized pose information that satisfies the target constraints is the target position information, and the optimized attitude information within the optimized pose information that satisfies the target constraints is the target attitude information.

[0074] In practical applications, the localization result optimization model determines the transformation relationship (i.e., transformation matrix) from the local coordinate system to the global coordinate system based on the first and second localization results and the target constraints. Based on the transformation relationship from the local coordinate system to the global coordinate system, it outputs the optimized pose information.

[0075] The technical solution of this embodiment obtains target pose information by inputting the first positioning result and the second positioning result into a positioning result optimization model. The positioning result optimization model is used to iteratively output optimized pose information until optimized pose information that satisfies the target constraints exists. The optimized pose information includes the optimized position information and optimized attitude information of the user terminal in the first coordinate system. The optimized pose information that satisfies the target constraints is used as the target pose information. The target constraints include a first constraint and a second constraint. The first constraint is used to constrain the difference between the optimized position information and the position information in the first positioning result. The second constraint is used to constrain the difference between the optimized pose information and the pose information in the second positioning result.

[0076] Thus, the first constraint is used to constrain the difference between the optimized position information and the position information in the first positioning result, providing a global constraint. The second constraint is used to constrain the difference between the optimized pose information and the pose information in the second positioning result, providing a local constraint. Under the global and local constraints, the positioning result optimization model fuses the first and second positioning results to output the optimized pose information, making the optimized pose information that meets the target constraints locally accurate and globally zero drift, thus solving the technical problems of low accuracy and instability in 5G UTDOA positioning schemes in related technologies.

[0077] In one embodiment, for a certain optimized pose information, if the sum of the difference between the optimized position information and the position information in the first positioning result and the difference between the optimized pose information and the pose information in the second positioning result satisfies a preset convergence condition, it can be determined that the optimized pose information satisfies the target constraint.

[0078] Specifically, such as Figure 3 As shown, the first and second positioning results are input into the positioning result optimization model to obtain the target pose information, including steps S310 to S330:

[0079] Step S310: Obtain the first difference information corresponding to the optimized pose information.

[0080] The first difference information is used to characterize the difference between the optimized location information and the location information in the first positioning result.

[0081] In a specific implementation, the electronic device can obtain the first difference information corresponding to the optimized pose information, which is used to characterize the difference between the optimized position information in the optimized pose information and the position information in the first positioning result.

[0082] Step S320: Obtain the second difference information corresponding to the optimized pose information.

[0083] The second difference information is used to characterize the difference between the optimized pose information and the pose information in the second localization result.

[0084] In practice, the electronic device can obtain the second difference information corresponding to the optimized pose information, which is used to characterize the difference between the optimized pose information and the pose information in the second positioning result.

[0085] Step S330: If the sum of the first difference value in the first difference information and the second difference value in the second difference information satisfies the preset convergence condition, it is determined that the optimized pose information satisfies the target constraint.

[0086] In practice, the electronic device can determine that the optimized pose information satisfies the target constraint if the sum of the first difference value in the first difference information and the second difference value in the second difference information satisfies the preset convergence condition.

[0087] Specifically, if the sum of the first difference value and the second difference value reaches the minimum value, it can be determined that the optimized pose information meets the target constraint.

[0088] The technical solution of this embodiment involves obtaining first difference information corresponding to the optimized pose information; the first difference information is used to characterize the difference between the optimized position information and the position information in the first positioning result; obtaining second difference information corresponding to the optimized pose information; the second difference information is used to characterize the difference between the optimized pose information and the pose information in the second positioning result; and determining that the optimized pose information satisfies the target constraint if the sum of the first difference value in the first difference information and the second difference value in the second difference information satisfies a preset convergence condition. Thus, by determining whether the sum of the first difference value in the first difference information and the second difference value in the second difference information satisfies the preset convergence condition, it is possible to accurately determine whether the optimized pose information satisfies global and local constraints.

[0089] In one embodiment, since the VSLAM positioning frequency is higher than the 5G positioning frequency (typically 1Hz for 5G and 50Hz for VSLAM), this application optimizes the positioning results using a lower frequency (1Hz), i.e., calculating the target positioning result once per second. Therefore, when a first positioning result (containing one location information) is obtained, a second positioning result contains multiple pose information (e.g., 50 pose information). Thus, in the process of inputting the first and second positioning results into the positioning result optimization model, one location information calculated based on the 5G UTDOA method and multiple pose information calculated by the VSLAM method are input into the model. Each pose information in the second positioning result is transformed from the second coordinate system to the first coordinate system. Therefore, the optimized pose information output by the positioning result optimization model in each iteration also contains multiple pose information, corresponding one-to-one with the input pose information. This effectively solves the problem of low output frequency in 5G positioning, allowing the output frequency of 5G positioning with VSLAM to be consistent with the VSLAM positioning frequency, achieving a high-frequency positioning effect after fusion.

[0090] Accordingly, the electronic device can calculate the difference between the pose increment between the optimized pose information of two adjacent frames obtained after fusion and the pose increment of the pose information of two adjacent frames in the second positioning result, and determine the second difference information.

[0091] Specifically, obtaining the second difference information corresponding to the optimized pose information includes: obtaining the first pose increment information between two adjacent pose information in the second localization result; obtaining the second pose increment information; the second pose increment information includes the pose increment information between two adjacent optimized pose information corresponding to the two adjacent pose information; and determining the second difference information based on the difference information between the first pose increment information and the second pose increment information.

[0092] In specific implementation, during the process of obtaining the second difference information corresponding to the optimized pose information, the electronic device can obtain the pose increment information between two adjacent pose information in the second positioning result as the first pose increment information, and obtain the pose increment information between two adjacent optimized pose information corresponding to two adjacent pose information as the second pose increment information. Based on the difference information between the first pose increment information and the second pose increment information, the second difference information is determined.

[0093] In this embodiment, the pose information in the second positioning result includes multiple pose information, which correspond one-to-one with the optimized pose information. The process involves obtaining the first pose increment information between two adjacent pose information in the second positioning result; obtaining the second pose increment information; the second pose increment information includes the pose increment information between two adjacent optimized pose information corresponding to the two adjacent pose information; and determining the second difference information based on the difference information between the first pose increment information and the second pose increment information.

[0094] Thus, by using the first pose increment information between two adjacent pose information in the second localization result and the second pose increment information between two adjacent optimized pose information as the second difference information corresponding to the local constraint, the relative motion observed by the simultaneous localization and mapping method and the relative motion reflected by the fused pose can be accurately determined, so as to determine whether the inter-frame motion continuity of the fused pose matches the actual motion observed by the simultaneous localization and mapping method, thereby improving the localization effect.

[0095] In one embodiment, the electronic device can specifically project the pose increment between the optimized pose information of two adjacent frames obtained after fusion onto a local coordinate system (second coordinate system), and then calculate the difference between the pose increment of the pose information of two adjacent frames in the second positioning result to determine the second difference information.

[0096] Specifically, obtaining the second pose increment information includes: transforming the two adjacent optimized pose information corresponding to the two adjacent pose information from the first coordinate system to the second coordinate system to obtain the transformed two adjacent optimized pose information; and obtaining the pose increment information between the transformed two adjacent optimized pose information as the second pose increment information.

[0097] In specific implementation, during the process of acquiring the second pose increment information, the electronic device can transform the two adjacent optimized pose information corresponding to the two adjacent pose information from the first coordinate system to the second coordinate system to obtain the transformed two adjacent optimized pose information; and acquire the pose increment information between the transformed two adjacent optimized pose information as the second pose increment information.

[0098] The technical solution of this embodiment transforms the two adjacent optimized pose information corresponding to two adjacent pose information from the first coordinate system to the second coordinate system to obtain the transformed two adjacent optimized pose information; the pose increment information between the two transformed adjacent optimized pose information is obtained as the second pose increment information. In this way, the difference information between the first pose increment information and the second pose increment information can be solved in the same coordinate system, and the second difference information can be accurately obtained.

[0099] In some embodiments, the second difference information includes the difference information between the first pose increment information between all two adjacent pose information and the second pose increment information between the corresponding two adjacent optimized pose information; the first difference information includes the difference information between all optimized position information in the optimized pose information and the position information in the first positioning result.

[0100] In this way, the local residual (second difference information) can cover the pose increment differences of all adjacent frames, so that the optimized pose information obtained after fusion can follow the actual motion law perceived by VSLAM, smooth the observation noise of a single frame, ensure the trajectory continuity of high-frequency output, and suppress the cumulative error of VSLAM from the frame-by-frame motion unit. On the other hand, the global residual can achieve multi-time global calibration by associating all optimized positions with 5G positioning results, unify the coordinate system of fused pose and 5G UTDOA, avoid long-term drift, balance the impact of single 5G noise, and improve global robustness.

[0101] In some embodiments, for the convenience of those skilled in the art to understand, Figure 4 A schematic diagram of a pose graph (factor graph) structure associated with a global optimizer (localization result optimization model) is provided to explain in detail the construction and calculation process of the global optimizer.

[0102] Specific virtues, Figure 4 The pose graph is constructed by the relationships between states (pose information) at different times. Circles in the pose graph represent... to The state variables at each moment are also nodes of the pose graph; the blue squares represent constraints for global observation, i.e., the 5G positioning results (first positioning results), and the yellow squares represent constraints for local observation, i.e., the relative pose transformations from VSLAM (relative pose transformations from the second positioning results), which are also edges of the pose graph.

[0103] The construction of local constraints (residuals) is based on the pose increment between the optimized pose information of two adjacent frames obtained after fusion. After projecting onto the local coordinate system (second coordinate system), the difference between this difference and the pose increment of the pose information of two adjacent frames in the second localization result is calculated to determine the second difference information.

[0104] Local residual (second difference information) =

[0105] in, This represents the pose increment between two adjacent frames in the second localization result; This is a function used to solve for the second pose increment information in the second coordinate system (local coordinate system). The optimized pose information for two adjacent frames.

[0106] The global constraint is the difference between the location information (5G positioning coordinates) in the first positioning result and the fused coordinates (optimized location information obtained after fusion). The residual of the global constraint is:

[0107] Global residual (first difference information) =

[0108] in, This indicates the location information in the first positioning result; This represents the optimized location information obtained after fusion.

[0109] Using the two residual terms mentioned above as constraints on the pose graph, a least-squares problem is constructed and solved using the Gauss-Newton method or the Levenberg-Marquardt method. The solution process is equivalent to finding the configuration of nodes that match as many edges as possible, thus obtaining the transformation relationship from local frames to global coordinates. In other words, while satisfying both global and local constraints and minimizing the two residual terms, the values ​​of edges (displacements between two consecutive time steps) and nodes (poses at each time step) are determined to obtain the target localization result.

[0110] Since 5G positioning frequency is generally 1Hz and VSLAM positioning frequency is generally 50Hz, this embodiment uses a low frequency (1Hz) to optimize the pose map, that is, it calculates once per second to obtain the transformation relationship from local frame to global coordinates, and applies it to subsequent local pose information. That is, after obtaining the transformation relationship from local to global (actually a transformation matrix), it is used to transform the pose information in the subsequent local coordinate system to achieve the high-frequency positioning effect after fusion.

[0111] Since the computational complexity of the attitude diagram increases with... The number of nodes increases linearly. This method is designed to maintain a window for pose graph optimization to obtain accurate and globally drift-free pose estimation. When the computational complexity exceeds real-time computing capabilities, old pose information and measurements can be discarded, while keeping the window at a finite size.

[0112] like Figure 5 As shown, an example diagram illustrating the effect of fusing the first and second localization results is provided. Figure 5 As shown, by enhancing the positioning effect of 5G UTDOA through factor graph optimization, with 5G UTDOA providing global constraints and visual VSLAM providing local constraints, the advantages of each method can be utilized to achieve local accuracy, global zero drift, and high-frequency output positioning effect, realizing pose graph-based fusion positioning.

[0113] Compared to standalone 5G UTDOA positioning technology, this method, by incorporating local constraints provided by vision, effectively improves the accuracy, stability, and output frequency of 5G positioning. It addresses issues such as low accuracy, instability, and low frame rate found in related 5G UTDOA positioning schemes. This reduces the high requirements for the number and density of 5G base stations required for 5G UTDOA positioning, and allows the system to continue providing positioning capabilities even when some base stations are obstructed or signals are lost, enabling 5G positioning to achieve high-frequency positioning capabilities. This effect is achieved with minimal terminal costs, resulting in improved overall system accuracy, stability, and availability.

[0114] In another embodiment, such as Figure 6 The diagram shows a flowchart of a terminal positioning method, which includes the following steps:

[0115] Step S602: Obtain the first and second positioning results of the user terminal.

[0116] Step S604: Input the first positioning result and the second positioning result into the positioning result optimization model, and iteratively output the optimized pose information.

[0117] Step S606: Obtain the first difference information corresponding to the optimized pose information.

[0118] Step S608: Obtain the first pose increment information between two adjacent pose information in the second positioning result.

[0119] Step S610: Transform the two adjacent optimized pose information corresponding to the two adjacent pose information from the first coordinate system to the second coordinate system to obtain the transformed two adjacent optimized pose information.

[0120] Step S612: Obtain the pose increment information between two adjacent optimized pose information after conversion, and use it as the second pose increment information.

[0121] Step S614: Based on the difference between the first pose increment information and the second pose increment information, determine the second difference information corresponding to the optimized pose information.

[0122] Step S616: If the sum of the first difference value in the first difference information and the second difference value in the second difference information satisfies the preset convergence condition, it is determined that the optimized pose information satisfies the target constraint.

[0123] Step S618: The optimized pose information that satisfies the target constraints is used as the target localization result of the user terminal.

[0124] It should be noted that the specific limitations of the above steps can be found in the specific limitations of a terminal positioning method described above.

[0125] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0126] Based on the same inventive concept, this application also provides a terminal positioning device for implementing the terminal positioning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more terminal positioning device embodiments provided below can be found in the limitations of the terminal positioning method described above, and will not be repeated here.

[0127] In one exemplary embodiment, such as Figure 7 As shown, a positioning device for a terminal is provided, comprising: an acquisition unit 710 and a fusion unit 720, wherein:

[0128] The acquisition unit 710 is used to acquire a first positioning result and a second positioning result of the user terminal; the first positioning result includes location information determined by the time difference of the uplink signal of the user terminal reaching different base stations; the second positioning result includes pose information determined based on the simultaneous positioning mapping method.

[0129] The fusion unit 720 is used to fuse the first positioning result and the second positioning result to obtain the target positioning result of the user terminal.

[0130] In one embodiment, the position information in the first positioning result corresponds to a first coordinate system, and the pose information in the second positioning result corresponds to a second coordinate system; the fusion unit 720 is specifically used to transform the pose information in the second positioning result from the second coordinate system to the first coordinate system based on the first positioning result to obtain target pose information; the target pose information includes the target position information and target posture information of the user terminal in the first coordinate system; and the target pose information is used as the target positioning result.

[0131] In one embodiment, the fusion unit 720 is specifically used to input the first positioning result and the second positioning result into a positioning result optimization model to obtain the target pose information; the positioning result optimization model is used to iteratively output optimized pose information until there is optimized pose information that satisfies the target constraints; the optimized pose information includes optimized position information and optimized attitude information of the user terminal in the first coordinate system; the optimized pose information that satisfies the target constraints is used as the target pose information; wherein, the target constraints include a first constraint and a second constraint; the first constraint is used to constrain the difference between the optimized position information and the position information in the first positioning result; the second constraint is used to constrain the difference between the optimized pose information and the pose information in the second positioning result.

[0132] In one embodiment, the fusion unit 720 is specifically configured to acquire first difference information corresponding to the optimized pose information; the first difference information is used to characterize the difference between the optimized position information and the position information in the first positioning result; acquire second difference information corresponding to the optimized pose information; the second difference information is used to characterize the difference between the optimized pose information and the pose information in the second positioning result; and determine that the optimized pose information satisfies the target constraint if the sum of the first difference value in the first difference information and the second difference value in the second difference information satisfies a preset convergence condition.

[0133] In one embodiment, the pose information in the second positioning result includes multiple pose information, each corresponding one-to-one with the optimized pose information. The fusion unit 720 is specifically used to obtain the first pose increment information between two adjacent pose information in the second positioning result; obtain the second pose increment information; the second pose increment information includes the pose increment information between two adjacent optimized pose information corresponding to the two adjacent pose information; and determine the second difference information based on the difference information between the first pose increment information and the second pose increment information.

[0134] In one embodiment, the fusion unit 720 is specifically used to transform the two adjacent optimized pose information corresponding to the two adjacent pose information from the first coordinate system to the second coordinate system to obtain the transformed two adjacent optimized pose information; and to obtain the pose increment information between the two transformed adjacent optimized pose information as the second pose increment information.

[0135] In one embodiment, the second difference information includes the difference information between the first pose increment information between all two adjacent pose information and the second pose increment information between the corresponding two adjacent optimized pose information; the first difference information includes the difference information between all the optimized position information in the optimized pose information and the position information in the first positioning result.

[0136] In one embodiment, the acquisition frequency corresponding to the pose information in the second positioning result is higher than the acquisition frequency corresponding to the position information in the first positioning result. The pose information in the second positioning result includes multiple pose information. The fusion unit 720 is specifically used to transform each pose information in the second positioning result from the second coordinate system to the first coordinate system to obtain the target pose information.

[0137] Each module in the positioning device of the aforementioned terminal can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the electronic device in hardware form or independent of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to each module.

[0138] In one exemplary embodiment, an electronic device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, this electronic device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores positioning result data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a terminal positioning method.

[0139] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0140] In one embodiment, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0141] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0142] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0143] 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 used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0144] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. 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). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0145] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0146] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for locating a terminal, characterized in that, The method includes: The system acquires a first positioning result and a second positioning result from the user terminal. The first positioning result includes location information determined by the time difference between the uplink signals of the user terminal arriving at different base stations. The second positioning result includes pose information determined based on a simultaneous positioning and mapping method. By combining the first positioning result and the second positioning result, the target positioning result of the user terminal is obtained.

2. The method according to claim 1, characterized in that, The position information in the first positioning result corresponds to the first coordinate system, and the pose information in the second positioning result corresponds to the second coordinate system; The process of fusing the first positioning result and the second positioning result to obtain the target positioning result of the user terminal includes: Based on the first positioning result, the pose information in the second positioning result is transformed from the second coordinate system to the first coordinate system to obtain the target pose information; the target pose information includes the target position information and target posture information of the user terminal in the first coordinate system; The target pose information is used as the target localization result.

3. The method according to claim 2, characterized in that, The step of transforming the pose information in the second positioning result from the second coordinate system to the first coordinate system based on the first positioning result to obtain the target pose information includes: The first positioning result and the second positioning result are input into the positioning result optimization model to obtain the target pose information; the positioning result optimization model is used to iteratively output the optimized pose information until there is optimized pose information that satisfies the target constraints; the optimized pose information includes the optimized position information and optimized attitude information of the user terminal in the first coordinate system. The optimized pose information that satisfies the target constraints is used as the target pose information; The target constraints include a first constraint and a second constraint; the first constraint is used to constrain the difference between the optimized position information and the position information in the first positioning result; the second constraint is used to constrain the difference between the optimized pose information and the pose information in the second positioning result.

4. The method according to claim 3, characterized in that, The step of inputting the first positioning result and the second positioning result into the positioning result optimization model to obtain the target pose information includes: Obtain first difference information corresponding to the optimized pose information; the first difference information is used to characterize the difference between the optimized position information and the position information in the first positioning result. Obtain the second difference information corresponding to the optimized pose information; the second difference information is used to characterize the difference between the optimized pose information and the pose information in the second localization result. If the sum of the first difference value in the first difference information and the second difference value in the second difference information satisfies the preset convergence condition, it is determined that the optimized pose information satisfies the target constraint.

5. The method according to claim 4, characterized in that, The pose information in the second positioning result includes multiple elements, each corresponding one-to-one with the optimized pose information. Obtaining the second difference information corresponding to the optimized pose information includes: Obtain the first pose increment information between two adjacent pose information in the second positioning result; Obtain second pose increment information; the second pose increment information includes pose increment information between two adjacent optimized pose information corresponding to the two adjacent pose information; The second difference information is determined based on the difference between the first pose increment information and the second pose increment information.

6. The method according to claim 5, characterized in that, The acquisition of the second pose increment information includes: The two adjacent optimized pose information corresponding to the two adjacent pose information are transformed from the first coordinate system to the second coordinate system to obtain the transformed two adjacent optimized pose information. The pose increment information between two adjacent optimized pose information after the transformation is obtained as the second pose increment information.

7. The method according to claim 5, characterized in that, The second difference information includes the difference between the first pose increment information between all two adjacent pose information and the second pose increment information between the corresponding two adjacent optimized pose information; the first difference information includes the difference between all the optimized position information in the optimized pose information and the position information in the first positioning result.

8. The method according to claim 2, characterized in that, The sampling frequency corresponding to the pose information in the second positioning result is higher than the sampling frequency corresponding to the position information in the first positioning result. The pose information in the second positioning result includes multiple components. The step of transforming the pose information in the second positioning result from the second coordinate system to the first coordinate system to obtain the target pose information includes: Each pose information in the second positioning result is transformed from the second coordinate system to the first coordinate system to obtain the target pose information.

9. A positioning device for a terminal, characterized in that, The device includes: The acquisition unit is used to acquire a first positioning result and a second positioning result of the user terminal; the first positioning result includes location information determined by the time difference of the uplink signal of the user terminal arriving at different base stations; the second positioning result includes pose information determined based on the simultaneous positioning and mapping method. The fusion unit is used to fuse the first positioning result and the second positioning result to obtain the target positioning result of the user terminal.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

Images