An outdoor positioning method, device, electronic equipment and storage medium

Abstract

The present application relates to the field of outdoor positioning, and particularly relates to an outdoor positioning method and device, electronic equipment and storage medium, the method comprising: acquiring GNSS positioning coordinates of a terminal to be positioned at a current time, base station signal state data, actual state data of a GNSS signal, motion state data and historical positioning coordinates at a previous time; inputting the base station signal state data into a terminal positioning model to obtain base station positioning coordinates of the terminal to be positioned at the current time; predicting an initial positioning trajectory of the terminal to be positioned from the previous time to the current time according to the motion state data and the historical positioning coordinates; inputting the GNSS positioning coordinates, the motion state data, a target confidence and the base station positioning coordinates and the initial positioning trajectory into a trajectory correction model to obtain a target positioning trajectory of the terminal to be positioned from the previous time to the current time. The present application can improve outdoor positioning accuracy and reliability.

Description

Technical Field

[0001] This invention relates to the field of outdoor positioning, and more specifically, to an outdoor positioning method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rapid development of information technology and smart terminals, location services have become an indispensable key support for the operation of modern society. As the mainstream technology in the field of outdoor positioning, the Global Navigation Satellite System (GNSS) has achieved deep penetration into many fields of social production and life due to its wide coverage, all-weather and continuous service characteristics.

[0003] However, the positioning performance of GNSS technology is highly dependent on the stable reception of satellite signals. In complex environments such as urban canyons with tall buildings, under overpasses, underground tunnels, and dense forests, satellite signals are prone to serious problems: buildings and bridge structures in urban canyons and under overpasses block the signal, causing a significant attenuation in signal strength. At the same time, the superposition of multipath signals formed by the reflection of the signal through obstacles and the direct signal distorts the phase and amplitude of the original signal; in enclosed environments such as underground tunnels, satellite signals may even be completely lost. These problems directly lead to a sharp decline in GNSS positioning accuracy, with positioning errors reaching tens to hundreds of meters, and even complete failure in some extreme scenarios. This greatly limits the application and expansion of location services in complex environments and cannot meet the urgent needs for high-precision and high-reliability positioning in scenarios such as intelligent driving, seamless indoor and outdoor navigation, and precise emergency rescue. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide an outdoor positioning method, device, electronic device and storage medium that can improve the accuracy and reliability of outdoor positioning.

[0005] In a first aspect, embodiments of this application provide an outdoor positioning method, the outdoor positioning method comprising:

[0006] The system acquires the GNSS positioning coordinates, base station signal status data, actual GNSS signal status data, motion status data, and historical positioning coordinates of the terminal to be located at the current moment; the actual status data is used to describe the signal quality of the GNSS signal; the motion status data includes the motion status of the terminal to be located from the previous moment to the current moment.

[0007] The target confidence level of the GNSS signal is determined based on the actual state data and the standard state data of the GNSS signal; the standard state data is determined based on the historical state data of the GNSS signal whose signal quality meets the preset GNSS positioning conditions; the confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning.

[0008] If the target confidence level is less than the preset second confidence level, the base station signal status data is input into the terminal positioning model to obtain the base station positioning coordinates of the terminal to be located at the current time.

[0009] Predict the initial positioning trajectory of the terminal to be located from the previous moment to the current moment based on the motion state data and the historical positioning coordinates;

[0010] The GNSS positioning coordinates, motion state data, target confidence, base station positioning coordinates, and initial positioning trajectory are input into the trajectory correction model to obtain the target positioning trajectory of the terminal to be positioned from the previous moment to the current moment.

[0011] In one possible implementation, determining the target confidence level of the GNSS signal based on the actual state data and the standard state data of the GNSS signal includes:

[0012] Calculate the similarity between the actual state data and the standard state data of the GNSS signal to obtain the initial confidence level of the GNSS signal;

[0013] Based on the numerical comparison between the initial confidence level and the preset confidence level, the target confidence level of the GNSS signal is determined according to the initial confidence level or the actual state data.

[0014] In one possible implementation, determining the target confidence level of the GNSS signal based on a numerical comparison between the initial confidence level and a preset confidence level, the initial confidence level, or the actual state data includes:

[0015] If the initial confidence level is less than the preset confidence level, then the initial confidence level and the actual state data are input into the confidence level estimation model to obtain the target confidence level of the GNSS signal;

[0016] If the initial confidence level is greater than or equal to the preset confidence level, then the initial confidence level is determined as the target confidence level of the GNSS signal.

[0017] In one possible implementation, the step of inputting the initial confidence level and the actual state data into the confidence level estimation model to obtain the target confidence level of the GNSS signal includes:

[0018] The initial confidence level and the actual state data are input into the preprocessing layer of the confidence estimation model, and the initial confidence level and the actual state data are standardized respectively to obtain the confidence feature vector and the state feature vector.

[0019] The confidence feature vector and the state feature vector are input into the feature extraction layer of the confidence estimation model to obtain the correlation feature matrix; the actual state data includes the values ​​of one or more indicators describing the signal quality of the GNSS signal; the correlation feature matrix includes the mapping relationship between the initial confidence and each indicator in the actual state data;

[0020] The state feature vector and the associated feature matrix are input into the confidence correction layer in the confidence estimation model to obtain the target confidence of the GNSS signal.

[0021] In one possible implementation, the step of inputting the state feature vector and the correlation feature matrix into the confidence correction layer of the confidence estimation model to obtain the target confidence of the GNSS signal includes:

[0022] The modified confidence level is obtained by mapping the associated feature matrix using an activation function;

[0023] If the corrected confidence level is within the preset first confidence level threshold range and the state feature vector satisfies the preset state data basic threshold condition, then the corrected confidence level is determined as the target confidence level.

[0024] If the corrected confidence level is outside the preset second confidence level threshold range and the state feature vector satisfies the preset state data basic threshold condition, then the product of the corrected confidence level and the adjustment coefficient is determined as the target confidence level.

[0025] If the state feature vector does not meet the preset state data basic threshold condition, then the lowest confidence level is determined as the target confidence level.

[0026] In one possible implementation, the step of inputting the GNSS positioning coordinates, the motion state data, the target confidence level, the base station positioning coordinates, and the initial positioning trajectory into a trajectory correction model to obtain the target positioning trajectory of the terminal to be located from the previous moment to the current moment includes:

[0027] The GNSS positioning coordinates, the target confidence score, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory are input into the fusion positioning layer in the trajectory correction model, so as to fuse the GNSS positioning coordinates, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory according to the target confidence score, and obtain the target positioning coordinates at the current moment.

[0028] The motion state data, the target positioning coordinates at the current moment, and the initial positioning trajectory are input into the trajectory correction layer of the trajectory correction model to correct the initial positioning trajectory based on the motion state data and the target positioning coordinates at the current moment, thereby obtaining the target positioning trajectory; wherein, the positioning coordinates at the previous moment in the target positioning trajectory are the same as the positioning coordinates at the previous moment in the initial positioning trajectory; and the positioning coordinates at the current moment in the target positioning trajectory are the same as the target positioning coordinates at the current moment.

[0029] In one possible implementation, the step of inputting the GNSS positioning coordinates, the target confidence score, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory into the fusion positioning layer of the trajectory correction model, so as to fuse the GNSS positioning coordinates, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory according to the target confidence score to obtain the target positioning coordinates at the current moment, includes:

[0030] The GNSS positioning coordinates and the target confidence level are input into the first weighted positioning unit in the fusion positioning layer to obtain the weighted GNSS positioning coordinates.

[0031] The base station positioning coordinates and the target confidence level are input into the second weighted positioning unit in the fusion positioning layer to obtain the weighted base station positioning coordinates.

[0032] The initial positioning coordinates at the current moment are input into the third weighted positioning unit in the fusion positioning layer to obtain the weighted initial positioning coordinates;

[0033] The weighted GNSS positioning coordinates, the weighted base station positioning coordinates, and the weighted initial positioning coordinates are input into the fusion unit in the fusion positioning layer to obtain the target positioning coordinates at the current time.

[0034] Secondly, embodiments of this application also provide an outdoor positioning device, the device comprising:

[0035] The acquisition module is used to acquire the GNSS positioning coordinates, base station signal status data, actual GNSS signal status data, motion status data, and historical positioning coordinates of the terminal to be located at the current moment; the actual status data is used to describe the signal quality of the GNSS signal; the motion status data includes the motion status of the terminal to be located from the previous moment to the current moment.

[0036] The determination module is used to determine the target confidence level of the GNSS signal based on the actual state data and the standard state data of the GNSS signal; the standard state data is determined based on the historical state data of the GNSS signal whose signal quality meets the preset GNSS positioning conditions; the confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning.

[0037] The input module is used to input the base station signal status data into the terminal positioning model if the target confidence level is less than a preset second confidence level, so as to obtain the base station positioning coordinates of the terminal to be located at the current time.

[0038] The prediction module is used to predict the initial positioning trajectory of the terminal to be located from the previous moment to the current moment based on the motion state data and the historical positioning coordinates.

[0039] The input module is further configured to input the GNSS positioning coordinates, the motion state data, the target confidence level, the base station positioning coordinates, and the initial positioning trajectory into the trajectory correction model to obtain the target positioning trajectory of the terminal to be positioned from the previous moment to the current moment.

[0040] In one possible implementation, the determining module is specifically used to calculate the similarity between the actual state data and the standard state data of the GNSS signal to obtain the initial confidence level of the GNSS signal; and to determine the target confidence level of the GNSS signal based on the numerical comparison result between the initial confidence level and the preset confidence level, or based on the initial confidence level or the actual state data.

[0041] In one possible implementation, the determining module is further configured to:

[0042] If the initial confidence level is less than the preset confidence level, then the initial confidence level and the actual state data are input into the confidence level estimation model to obtain the target confidence level of the GNSS signal;

[0043] If the initial confidence level is greater than or equal to the preset confidence level, then the initial confidence level is determined as the target confidence level of the GNSS signal.

[0044] In one possible implementation, the input module is specifically used to input the initial confidence level and the actual state data into the preprocessing layer of the confidence estimation model, and to standardize the initial confidence level and the actual state data respectively to obtain a confidence feature vector and a state feature vector; then, the input of the confidence feature vector and the state feature vector into the feature extraction layer of the confidence estimation model to obtain an association feature matrix; the actual state data includes the values ​​of one or more indicators describing the signal quality of the GNSS signal; the association feature matrix includes the mapping relationship between the initial confidence level and each indicator in the actual state data;

[0045] The state feature vector and the associated feature matrix are input into the confidence correction layer in the confidence estimation model to obtain the target confidence of the GNSS signal.

[0046] In one possible implementation, the input module is further configured to:

[0047] The modified confidence level is obtained by mapping the associated feature matrix using an activation function;

[0048] If the corrected confidence level is within the preset first confidence level threshold range and the state feature vector satisfies the preset state data basic threshold condition, then the corrected confidence level is determined as the target confidence level.

[0049] If the corrected confidence level is outside the preset second confidence level threshold range and the state feature vector satisfies the preset state data basic threshold condition, then the product of the corrected confidence level and the adjustment coefficient is determined as the target confidence level; if the state feature vector does not satisfy the preset state data basic threshold condition, then the lowest confidence level is determined as the target confidence level.

[0050] In one possible implementation, the input module is specifically used to input the GNSS positioning coordinates, the target confidence score, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory into the fusion positioning layer of the trajectory correction model, so as to fuse the GNSS positioning coordinates, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory according to the target confidence score to obtain the target positioning coordinates at the current moment; and to input the motion state data, the target positioning coordinates at the current moment, and the initial positioning trajectory into the trajectory correction layer of the trajectory correction model, so as to correct the initial positioning trajectory according to the motion state data and the target positioning coordinates at the current moment to obtain the target positioning trajectory; wherein, the positioning coordinates at the previous moment in the target positioning trajectory are the same as the positioning coordinates at the previous moment in the initial positioning trajectory; and the positioning coordinates at the current moment in the target positioning trajectory are the same as the target positioning coordinates at the current moment.

[0051] In one possible implementation, the input module is further configured to:

[0052] The GNSS positioning coordinates and the target confidence level are input into the first weighted positioning unit in the fusion positioning layer to obtain the weighted GNSS positioning coordinates.

[0053] The base station positioning coordinates and the target confidence level are input into the second weighted positioning unit in the fusion positioning layer to obtain the weighted base station positioning coordinates.

[0054] The initial positioning coordinates at the current moment are input into the third weighted positioning unit in the fusion positioning layer to obtain the weighted initial positioning coordinates;

[0055] The weighted GNSS positioning coordinates, the weighted base station positioning coordinates, and the weighted initial positioning coordinates are input into the fusion unit in the fusion positioning layer to obtain the target positioning coordinates at the current time.

[0056] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the outdoor positioning method as described in any of the first aspects.

[0057] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the outdoor positioning method as described in any of the first aspects.

[0058] This application provides an outdoor positioning method, device, electronic device, and storage medium. The method includes: acquiring the GNSS positioning coordinates of a terminal to be positioned at the current moment, base station signal status data, actual status data of the GNSS signal, motion status data, and historical positioning coordinates at the previous moment; the actual status data is used to describe the signal quality of the GNSS signal; the motion status data includes the motion status of the terminal to be positioned from the previous moment to the current moment; determining the target confidence level of the GNSS signal based on the actual status data and the standard status data of the GNSS signal; the standard status data is based on the signal quality meeting preset GNSS positioning conditions. The historical state data of the GNSS signal is used to determine the accuracy of GNSS positioning; the confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning; if the target confidence level is less than a preset second confidence level, the base station signal state data is input into the terminal positioning model to obtain the base station positioning coordinates of the terminal to be positioned at the current time; the initial positioning trajectory of the terminal to be positioned from the previous time to the current time is predicted based on the motion state data and the historical positioning coordinates; the GNSS positioning coordinates, the motion state data, the target confidence level, the base station positioning coordinates, and the initial positioning trajectory are input into the trajectory correction model to obtain the target positioning trajectory of the terminal to be positioned from the previous time to the current time. This embodiment of the application improves outdoor positioning accuracy and reliability by combining GNSS positioning and base station positioning for terminal outdoor positioning. Attached Figure Description

[0059] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 A flowchart of an outdoor positioning method provided in an embodiment of this application is shown;

[0061] Figure 2 A flowchart illustrating the trajectory correction process of the trajectory correction model provided in this application is shown.

[0062] Figure 3 This paper shows a schematic diagram of the structure of an outdoor positioning device provided in an embodiment of this application;

[0063] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0065] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0066] To enable those skilled in the art to utilize the content of this application, and in conjunction with the specific application scenario of "outdoor positioning," the following implementation is provided. Those skilled in the art will be able to apply the general principles defined herein to other embodiments and application scenarios without departing from the spirit and scope of this application. Although this application is primarily described in the context of "outdoor positioning," it should be understood that this is merely an exemplary embodiment.

[0067] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0068] The following is a detailed description of an outdoor positioning method provided by an embodiment of this application.

[0069] Reference Figure 1 The diagram shown is a flowchart illustrating an outdoor positioning method provided in an embodiment of this application. The exemplary steps of this embodiment are described below:

[0070] S101. Obtain the GNSS positioning coordinates, base station signal status data, actual GNSS signal status data, motion status data, and historical positioning coordinates of the terminal to be positioned at the current moment.

[0071] In this embodiment, during the process of activating the positioning service on the terminal to be positioned, positioning-related data is collected by the data acquisition module built into the data acquisition software built into the terminal to be positioned. Specifically: (1) The GNSS module (such as GPS / BeiDou / Galileo) built into the terminal to be positioned receives satellite signals (carrier phase, pseudorange, etc.), and then uses the satellite signals to calculate the three-dimensional positioning coordinates of the terminal to be positioned, and obtains the GNSS positioning coordinates (i.e., obtains the coordinates of the terminal to be positioned through GNSS positioning). (2) The cellular communication module (such as 4G LTE / 5G NR) built into the terminal to be positioned scans the surrounding macro base stations / micro base stations and collects the base station signal status data of multiple base stations. (3) The GNSS module built into the terminal to be positioned outputs the actual status data of the GNSS signal in real time, which is used to describe the signal quality of the GNSS signal. (4) The IMU inertial measurement unit (accelerometer, gyroscope) integrated into the terminal to be positioned collects three-dimensional acceleration, angular velocity data, etc. in real time, and combines them with the speed sensor built into the terminal to be positioned to obtain the motion speed, heading angle and pitch angle, etc. (5) Local storage location result cache (including timestamp) is updated according to a preset period (e.g., 1Hz). When it is necessary to obtain the historical location coordinates of the previous sampling period at the current time, the coordinate data of the corresponding timestamp is read directly from the cache.

[0072] The current GNSS positioning coordinates include longitude, latitude, and elevation. Base station signal status data refers to the signal status between the terminal to be located and the base station at the current moment, including: the serving cell's CGI (Cell Global ID), RSRP (Reference Signal Receiving Power), RSRQ (Reference Signal Receiving Quality), and Timing Advance (TA), as well as the CGI, RSRP, and RSRQ of up to six neighboring cells. CGI is the unique identifier of the base station; it may also include the serving cell's and neighboring cells' MCC (Mobile Country Code) and MNC (Mobile Network Code). RSRP represents signal strength, RSRQ reflects signal quality, and Timing Advance is used to calculate the distance between the terminal and the base station. The actual state data of the GNSS signal is also included. The serving cell refers to the cell corresponding to the serving base station that has established a stable communication connection with the terminal to be located and provides core services (such as data transmission and signal interaction) for the terminal; it is the "primary base station cell" for the terminal's current communication. A neighboring cell refers to a cell whose coverage area is adjacent to or partially overlaps with that of the serving cell and is configured as a "candidate handover cell" by the network side (operator). It is a "backup / neighboring communication cell" of the serving cell.

[0073] The current GNSS signal status data includes one or more indicators that describe the signal quality of the GNSS signal, such as the number of visible satellites, the signal-to-noise ratio (CN0) of each satellite, the signal lock status (locked / unlocked), multipath error assessment (e.g., calculated by smoothing pseudorange through carrier phase), signal attenuation magnitude (compared to a reference value in open environments), and horizontal accuracy factor (HDOP). Motion status data includes the motion status of the terminal to be located from the previous moment to the current moment.

[0074] S102. Determine the target confidence level of the GNSS signal based on the actual state data and the standard state data of the GNSS signal.

[0075] In the embodiments of this application, the standard state data of the GNSS signal includes numerical values ​​of various indicators describing the signal quality of the GNSS signal. The indicators corresponding to the actual state data are the same as those corresponding to the standard state data. The confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning, and the numerical range is [0,1]. The higher the confidence level, the more accurate the GNSS positioning is, that is, the more reliable the GNSS positioning coordinates are.

[0076] The standard status data is determined based on historical status data of GNSS signals whose signal quality meets preset GNSS positioning conditions. The better the signal quality, the more accurate the GNSS positioning.

[0077] For example, the preset GNSS positioning conditions can be that the number of visible satellites is greater than 4 and HDOP is less than 3.

[0078] Specifically, the similarity between actual state data and standard state data of the GNSS signal can be directly determined as the target confidence level of the GNSS signal. Alternatively, the target confidence level of the GNSS signal can be determined using the following steps:

[0079] Step 1: Calculate the similarity between the actual state data and the standard state data of the GNSS signal to obtain the initial confidence level of the GNSS signal.

[0080] In this embodiment, the similarity between actual state data and standard state data of GNSS signals can be calculated using methods such as cosine similarity. This can be determined based on actual circumstances and is not specifically limited. The actual state data of GNSS signals includes core parameters such as the number of visible satellites, the signal-to-noise ratio (CN0) of each satellite, signal lock status, multipath error assessment value, and signal attenuation amplitude. The standard state data is obtained through statistical analysis of historical state data under ideal scenarios such as open environments, no obstructions or interference, and stable equipment conditions. For example, it can be determined by calculating the mean and fitting the probability distribution of historical state data of GNSS signals when the GNSS signal is stable from a large number of historical GNSS signal samples to form a feature vector.

[0081] Step 2: Determine the target confidence level of the GNSS signal based on the numerical comparison results between the initial confidence level and the preset confidence level, the initial confidence level, or the actual state data.

[0082] In the real-time approach of this application, the standard state data is determined based on historical state data. However, the collection of historical state data is often limited by specific time periods, geographical environments, equipment operating status, and external propagation conditions. It cannot cover unforeseen changes that may occur in future scenarios (such as obstruction by new urban buildings, base station signal interference, signal attenuation due to extreme weather, and aging equipment modules). This results in potential historical bias in the standard state data; it can only reflect the optimal or stable signal state in historical scenarios and cannot adapt to the complex and dynamically changing environment of the future. Consequently, the similarity between the actual state data and the standard state data in the new scenario is unreasonably reduced, leading to an underestimation of the initial confidence level. Even if the current GNSS positioning coordinates still have some positioning reference value, they may be judged as having low confidence due to deviation from historical standard data, affecting the accuracy and reliability of subsequent positioning data fusion. Specifically:

[0083] i. If the initial confidence level is less than the preset confidence level, the initial confidence level and the actual state data are input into the confidence level estimation model to obtain the target confidence level of the GNSS signal.

[0084] In this embodiment of the application, to avoid underestimating the confidence level of the GNSS signal, when the initial confidence level is less than a preset confidence level, a confidence level estimation model is further used to estimate the confidence level of the GNSS signal. The specific implementation process is as follows:

[0085] a) Input the initial confidence level and actual state data into the preprocessing layer of the confidence estimation model, and standardize the initial confidence level and actual state data respectively to obtain the confidence feature vector and the state feature vector.

[0086] In this embodiment, the initial confidence level is converted into a one-dimensional vector to obtain a confidence feature vector. The heterogeneous data is then uniformly converted into a standardized feature vector recognizable by the model by combining feature normalization of each indicator value in the actual state data with one-hot encoding (e.g., converting the signal lock state "locked / unlocked" into a binary feature vector), thus obtaining a state feature vector. The dimension of the state feature vector is the same as the number of indicator values ​​contained in the actual state data.

[0087] For example, if the initial confidence level is 0.42, then the confidence feature vector is [0.42]. The state feature vector is [0.5, 0.68, 1, 0, 0.35], and the values ​​in the state feature vector correspond to the number of visible satellites, average CN0, lockout state code, HDOP value, and multipath error, respectively.

[0088] b. Input the confidence feature vector and the state feature vector into the feature extraction layer in the confidence estimation model to obtain the correlation feature matrix; the correlation feature matrix includes the mapping relationship between the initial confidence and each indicator in the actual state data.

[0089] In this embodiment, the confidence feature vector and the state feature vector are linearly fused into the fully connected unit in the feature extraction layer to obtain the fused feature matrix; the fused feature matrix is ​​then input into the feature mapping unit (such as a convolutional neural network CNN or a gated recurrent unit GRU) in the feature extraction layer to obtain the associated feature matrix.

[0090] Here, a fully connected unit linearly fuses the confidence feature vector and the state feature vector to generate a basic feature matrix containing the correlation between "confidence" and "signal state," achieving information complementarity between the two types of input data. A deep learning network (such as a convolutional neural network (CNN) or a gated recurrent unit (GRU)) is introduced to perform nonlinear transformations and high-order feature extraction on the fused feature matrix. The focus is on uncovering the potential mapping relationship between the initial confidence and various state data (such as the number of visible satellites, HDOP value, and multipath error). For example, it identifies special scenario features such as "low initial confidence, but the number of visible satellites meets positioning requirements, and the HDOP value is within the usable range," avoiding confidence bias caused by misjudgment based on single-dimensional data.

[0091] c. Input the state feature vector and the associated feature matrix into the confidence correction layer in the confidence estimation model to obtain the target confidence of the GNSS signal.

[0092] In this embodiment, the associated feature matrix is ​​mapped using an activation function (such as the sigmoid function) to obtain a corrected confidence score; if the corrected confidence score is within a preset first confidence score threshold range (e.g., the corrected confidence score is within a preset first confidence score threshold range), then the corrected confidence score is determined by the following steps: If the state feature vector satisfies the preset state data basic threshold condition, then the corrected confidence level is determined as the target confidence level; if the corrected confidence level is within the preset second confidence level threshold range (e.g., ...), then the corrected confidence level is determined as the target confidence level. If the state feature vector satisfies the preset state data basic threshold condition, then the product of the corrected confidence level and the adjustment coefficient (a value greater than 1, such as 1.1) is determined as the target confidence level; if the state feature vector does not satisfy the preset state data basic threshold condition, then the lowest confidence level is determined as the target confidence level.

[0093] Among them, the preset state data basic threshold condition, the preset first confidence threshold range, the preset second confidence threshold range, the adjustment coefficient, and the minimum confidence are all trainable parameters of the confidence estimation model.

[0094] For example, the preset basic threshold conditions for state data can be "number of visible satellites ≥ 4, HDOP ≤ 8.0, multipath error ≤ 0.5m".

[0095] Here, the confidence estimation model is an Artificial Intelligence (AI) model. It addresses the problem of underestimated confidence caused by historical data bias in traditional methods by extracting features and correcting confidence levels from the input GNSS signal state data. The confidence estimation model is pre-trained based on actual state data samples of the GNSS sample signal and their corresponding confidence labels. The specific training process is as follows: The similarity between the actual state data samples and the standard state data of the GNSS signal is calculated to obtain the initial confidence level of the GNSS sample signal; the initial confidence level samples and the actual state data samples are input into the confidence estimation model to obtain the target confidence level of the GNSS sample signal; the parameters of the confidence estimation model are updated and trained based on the target confidence level and confidence labels of the GNSS sample signal until the confidence estimation model converges, resulting in the final trained confidence estimation model.

[0096] ii. If the initial confidence level is greater than or equal to the preset first confidence level, then the initial confidence level is determined as the target confidence level of the GNSS signal.

[0097] In this embodiment, when the initial confidence level is greater than or equal to a preset first confidence level (e.g., 0.8), it indicates that the GNSS signal's reliability is already very high, and there is no risk of it being underestimated. Therefore, the initial confidence level can be set as the target confidence level of the GNSS signal.

[0098] Here, it is possible to determine the target confidence level of a GNSS signal directly by training an AI model, without needing to determine the initial confidence level using standard state data. However, the computational complexity of the AI ​​model is far greater than that of determining the initial confidence level using standard state data, requiring significantly more computation time. Therefore, the method described in this application, which uses a numerical comparison between the initial confidence level and a preset first confidence level to determine whether to use an AI model to determine the target confidence level, improves the efficiency of confidence level estimation. Furthermore, the confidence level estimation model provided in this application is a modified version of the initial confidence level, and by combining it with historical state data, the accuracy of confidence level estimation is improved.

[0099] S103. If the target confidence level is less than the preset second confidence level, the base station signal status data is input into the terminal positioning model to obtain the base station positioning coordinates of the terminal to be located at the current time.

[0100] In this embodiment of the application, if the target confidence level is less than the preset second confidence level, it indicates that the GNSS positioning coordinates are not reliable and need to be combined with base station signal status data for further positioning.

[0101] Among them, the terminal positioning model is a pre-trained AI model, which is obtained by training in advance using base station signal status sample data and corresponding base station positioning coordinate labels.

[0102] S104. Based on motion state data and historical positioning coordinates, predict the initial positioning trajectory of the terminal to be positioned from the previous moment to the current moment.

[0103] In this embodiment, "previous time" refers to the time preceding the current time. There is a time difference between adjacent times; to ensure positioning continuity, the positioning trajectory needs to be smoothed using motion state data and historical positioning coordinates. The motion state data includes the motion state of the terminal to be positioned at each time point between the previous time and the current time. The initial positioning trajectory includes the initial positioning coordinates at each time point between the previous time and the current time. The initial positioning coordinates at any given time point are calculated using the following formula:

[0104] ;

[0105] in, Let the longitude be the initial positioning coordinate at time point i. The latitude is the initial positioning coordinate at the (i-1)th time point (the initial positioning coordinate at the first time point is the historical positioning coordinate). The duration of the interval between adjacent time points. Let be the heading angle at the i-th time point in the motion state data. Let be the horizontal velocity at the i-th time point in the motion state data.

[0106] ;

[0107] in, Let latitude be the initial positioning coordinate of the i-th time point. The latitude is the initial positioning coordinate of the (i-1)th time point (the initial positioning coordinate of the first time point is the historical positioning coordinate).

[0108] ;

[0109] in, Let be the altitude in the initial positioning coordinates at the i-th time point. The elevation is the initial positioning coordinate at time point i-1. Let be the vertical velocity at the i-th time point in the motion state data. Let be the pitch angle at the i-th time point in the motion state data.

[0110] S105. Input the GNSS positioning coordinates, motion state data, target confidence, base station positioning coordinates, and initial positioning trajectory into the trajectory correction model to obtain the target positioning trajectory of the terminal to be positioned from the previous moment to the current moment.

[0111] Reference Figure 2 The diagram shown is a flowchart of the trajectory correction process of the trajectory correction model provided in this application embodiment. The specific process is as follows:

[0112] S201. Input the GNSS positioning coordinates, target confidence, base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory into the fusion positioning layer in the trajectory correction model, so as to fuse the GNSS positioning coordinates, base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory according to the target confidence to obtain the target positioning coordinates at the current moment.

[0113] i. Input the GNSS positioning coordinates and target confidence into the first weighted positioning unit in the fusion positioning layer to obtain the weighted GNSS positioning coordinates.

[0114] In this embodiment, the product of the GNSS positioning coordinates, the target confidence score, and the first weighting coefficient is determined as the weighted GNSS positioning coordinates. The first weighting coefficient is a trainable parameter of the fusion positioning layer; the product of the target confidence score and the first weighting coefficient is the fusion weight of the GNSS positioning coordinates.

[0115] ii. Input the base station positioning coordinates into the second weighted positioning unit in the fusion positioning layer to obtain the weighted base station positioning coordinates.

[0116] In this embodiment, the product of the base station positioning coordinates, the target confidence level, and the second weighting coefficient is determined as the weighted base station positioning coordinates. The second weighting coefficient is a trainable parameter of the fusion positioning layer; the second weighting coefficient is the fusion weight of the base station positioning coordinates.

[0117] iii. Input the initial positioning coordinates at the current moment into the third weighted positioning unit in the fusion positioning layer to obtain the weighted initial positioning coordinates.

[0118] In this embodiment, the product of the initial positioning coordinates and the third weighting coefficient is determined as the weighted initial positioning coordinates. The third weighting coefficient is a trainable parameter of the fusion positioning layer; the third weighting coefficient is the fusion weight of the initial positioning coordinates.

[0119] iv. Input the weighted GNSS positioning coordinates, the weighted base station positioning coordinates, and the weighted initial positioning coordinates into the fusion unit in the fusion positioning layer to obtain the target positioning coordinates at the current time.

[0120] In this embodiment of the application, the sum of the weighted GNSS positioning coordinates, the weighted base station positioning coordinates, and the weighted initial positioning coordinates is determined as the target positioning coordinates at the current moment.

[0121] S202. Input the motion state data, the target positioning coordinates at the current time, and the initial positioning trajectory into the trajectory correction layer in the trajectory correction model, so as to correct the initial positioning trajectory according to the motion state data and the target positioning coordinates at the current time, and obtain the target positioning trajectory.

[0122] In this embodiment of the application, under the condition that the positioning coordinates at the previous moment in the target positioning trajectory are the same as the positioning coordinates at the previous moment in the initial positioning trajectory, and the positioning coordinates at the current moment in the target positioning trajectory are the same as the target positioning coordinates at the current moment, the positioning coordinates at each time point in the initial positioning trajectory are appropriately corrected by motion state data.

[0123] Here, the trajectory correction layer can be any network architecture of an AI model, as long as it can achieve its function; no specific restrictions are made here.

[0124] In summary, this application provides an outdoor positioning method, which includes: acquiring the GNSS positioning coordinates of a terminal to be positioned at the current moment, base station signal status data, actual state data of the GNSS signal, motion state data, and historical positioning coordinates at the previous moment; the actual state data is used to describe the signal quality of the GNSS signal; the motion state data includes the motion state of the terminal to be positioned from the previous moment to the current moment; determining the target confidence level of the GNSS signal based on the actual state data and the standard state data of the GNSS signal; the standard state data is based on the GNSS signal whose signal quality meets preset GNSS positioning conditions. Historical state data is used to determine the accuracy of GNSS positioning; the confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning; if the target confidence level is less than a preset second confidence level, the base station signal state data is input into the terminal positioning model to obtain the base station positioning coordinates of the terminal to be positioned at the current time; the initial positioning trajectory of the terminal to be positioned from the previous time to the current time is predicted based on the motion state data and the historical positioning coordinates; the GNSS positioning coordinates, the motion state data, the target confidence level, the base station positioning coordinates, and the initial positioning trajectory are input into the trajectory correction model to obtain the target positioning trajectory of the terminal to be positioned from the previous time to the current time. This embodiment of the application improves outdoor positioning accuracy and reliability by combining GNSS positioning and base station positioning for terminal outdoor positioning.

[0125] Based on the same inventive concept, this application also provides an outdoor positioning device corresponding to the outdoor positioning method. Since the principle of the device in this application is similar to that of the outdoor positioning method described above in this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0126] Reference Figure 3 The diagram shown is a schematic representation of an outdoor positioning device provided in an embodiment of this application. The outdoor positioning device includes:

[0127] The acquisition module 301 is used to acquire the GNSS positioning coordinates, base station signal status data, actual status data of the GNSS signal, motion status data, and historical positioning coordinates of the terminal to be located at the current time; the actual status data is used to describe the signal quality of the GNSS signal; the motion status data includes the motion status of the terminal to be located from the previous time to the current time.

[0128] The determining module 302 is used to determine the target confidence level of the GNSS signal based on the actual state data and the standard state data of the GNSS signal; the standard state data is determined based on the historical state data of the GNSS signal whose signal quality meets the preset GNSS positioning conditions; the confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning.

[0129] The input module 303 is used to input the base station signal status data into the terminal positioning model if the target confidence is less than a preset second confidence, so as to obtain the base station positioning coordinates of the terminal to be located at the current time.

[0130] Prediction module 304 is used to predict the initial positioning trajectory of the terminal to be located from the previous moment to the current moment based on the motion state data and the historical positioning coordinates.

[0131] The input module 303 is further configured to input the GNSS positioning coordinates, the motion state data, the target confidence level, the base station positioning coordinates, and the initial positioning trajectory into the trajectory correction model to obtain the target positioning trajectory of the terminal to be positioned from the previous moment to the current moment.

[0132] In one possible implementation, the determining module 302 is specifically used to calculate the similarity between the actual state data and the standard state data of the GNSS signal to obtain the initial confidence level of the GNSS signal; and to determine the target confidence level of the GNSS signal based on the numerical comparison result between the initial confidence level and the preset confidence level, or based on the initial confidence level or the actual state data.

[0133] In one possible implementation, the determining module 302 is further configured to:

[0134] If the initial confidence level is less than the preset confidence level, then the initial confidence level and the actual state data are input into the confidence level estimation model to obtain the target confidence level of the GNSS signal;

[0135] If the initial confidence level is greater than or equal to the preset confidence level, then the initial confidence level is determined as the target confidence level of the GNSS signal.

[0136] In one possible implementation, the input module 303 is specifically used to input the initial confidence level and the actual state data into the preprocessing layer of the confidence estimation model, and to standardize the initial confidence level and the actual state data respectively to obtain a confidence feature vector and a state feature vector; input the confidence feature vector and the state feature vector into the feature extraction layer of the confidence estimation model to obtain an association feature matrix; the actual state data includes the values ​​of one or more indicators describing the signal quality of the GNSS signal; the association feature matrix includes the mapping relationship between the initial confidence level and each indicator in the actual state data;

[0137] The state feature vector and the associated feature matrix are input into the confidence correction layer in the confidence estimation model to obtain the target confidence of the GNSS signal.

[0138] In one possible implementation, the input module 303 is further configured to:

[0139] The modified confidence level is obtained by mapping the associated feature matrix using an activation function;

[0140] If the corrected confidence level is within the preset first confidence level threshold range and the state feature vector satisfies the preset state data basic threshold condition, then the corrected confidence level is determined as the target confidence level.

[0141] If the corrected confidence level is outside the preset second confidence level threshold range and the state feature vector satisfies the preset state data basic threshold condition, then the product of the corrected confidence level and the adjustment coefficient is determined as the target confidence level; if the state feature vector does not satisfy the preset state data basic threshold condition, then the lowest confidence level is determined as the target confidence level.

[0142] In one possible implementation, the input module 303 is specifically configured to input the GNSS positioning coordinates, the target confidence score, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory into the fusion positioning layer of the trajectory correction model, so as to fuse the GNSS positioning coordinates, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory according to the target confidence score to obtain the target positioning coordinates at the current moment; and to input the motion state data, the target positioning coordinates at the current moment, and the initial positioning trajectory into the trajectory correction layer of the trajectory correction model, so as to correct the initial positioning trajectory according to the motion state data and the target positioning coordinates at the current moment to obtain the target positioning trajectory; wherein, the positioning coordinates at the previous moment in the target positioning trajectory are the same as the positioning coordinates at the previous moment in the initial positioning trajectory; and the positioning coordinates at the current moment in the target positioning trajectory are the same as the target positioning coordinates at the current moment.

[0143] In one possible implementation, the input module 303 is further configured to:

[0144] The GNSS positioning coordinates and the target confidence level are input into the first weighted positioning unit in the fusion positioning layer to obtain the weighted GNSS positioning coordinates.

[0145] The base station positioning coordinates and the target confidence level are input into the second weighted positioning unit in the fusion positioning layer to obtain the weighted base station positioning coordinates.

[0146] The initial positioning coordinates at the current moment are input into the third weighted positioning unit in the fusion positioning layer to obtain the weighted initial positioning coordinates;

[0147] The weighted GNSS positioning coordinates, the weighted base station positioning coordinates, and the weighted initial positioning coordinates are input into the fusion unit in the fusion positioning layer to obtain the target positioning coordinates at the current time.

[0148] This application provides an outdoor positioning device, comprising: an acquisition module 301, configured to acquire the GNSS positioning coordinates of a terminal to be positioned at the current moment, base station signal status data, actual status data of the GNSS signal, motion status data, and historical positioning coordinates at the previous moment; the actual status data is used to describe the signal quality of the GNSS signal; the motion status data includes the motion status of the terminal to be positioned from the previous moment to the current moment; and a determination module 302, configured to determine the target confidence level of the GNSS signal based on the actual status data and the standard status data of the GNSS signal; the standard status data is obtained by analyzing the historical status data of the GNSS signal whose signal quality meets preset GNSS positioning conditions. The confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning. Input module 303 is used to input the base station signal status data into the terminal positioning model if the target confidence level is less than a preset second confidence level, thereby obtaining the base station positioning coordinates of the terminal to be positioned at the current time. Prediction module 304 is used to predict the initial positioning trajectory of the terminal to be positioned from the previous time to the current time based on the motion state data and the historical positioning coordinates. Input module 303 is also used to input the GNSS positioning coordinates, the motion state data, the target confidence level, the base station positioning coordinates, and the initial positioning trajectory into the trajectory correction model to obtain the target positioning trajectory of the terminal to be positioned from the previous time to the current time. This embodiment of the application improves outdoor positioning accuracy and reliability by combining GNSS positioning and base station positioning for outdoor terminal positioning.

[0149] like Figure 4As shown in the embodiment of this application, an electronic device 400 includes a processor 401, a memory 402, and a bus. The memory 402 stores machine-readable instructions that can be executed by the processor 401. When the electronic device is running, the processor 401 communicates with the memory 402 via the bus, and the processor 401 executes the machine-readable instructions to perform the steps of the outdoor positioning method described above.

[0150] Specifically, the memory 402 and processor 401 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 401 runs the computer program stored in the memory 402, it can execute the outdoor positioning method mentioned above.

[0151] Corresponding to the above-described outdoor positioning method, this application embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described outdoor positioning method.

[0152] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0153] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0154] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0155] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the outdoor positioning method described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0156] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An outdoor positioning method, characterized in that, The method includes: The system acquires the GNSS positioning coordinates, base station signal status data, actual GNSS signal status data, motion status data, and historical positioning coordinates of the terminal to be located at the current moment; the actual status data is used to describe the signal quality of the GNSS signal; the motion status data includes the motion status of the terminal to be located from the previous moment to the current moment. The target confidence level of the GNSS signal is determined based on the actual state data and the standard state data of the GNSS signal; the standard state data is determined based on the historical state data of the GNSS signal whose signal quality meets the preset GNSS positioning conditions; the confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning. If the target confidence level is less than the preset second confidence level, the base station signal status data is input into the terminal positioning model to obtain the base station positioning coordinates of the terminal to be located at the current time. Predict the initial positioning trajectory of the terminal to be located from the previous moment to the current moment based on the motion state data and the historical positioning coordinates; The GNSS positioning coordinates, motion state data, target confidence, base station positioning coordinates, and initial positioning trajectory are input into the trajectory correction model to obtain the target positioning trajectory of the terminal to be located from the previous moment to the current moment. The step of determining the target confidence level of the GNSS signal based on the actual state data and the standard state data of the GNSS signal includes: calculating the similarity between the actual state data and the standard state data of the GNSS signal to obtain the initial confidence level of the GNSS signal; and determining the target confidence level of the GNSS signal based on the numerical comparison result between the initial confidence level and the preset confidence level, the initial confidence level, or the actual state data. The step of determining the target confidence level of the GNSS signal based on the numerical comparison result between the initial confidence level and the preset confidence level, the initial confidence level, or the actual state data includes: if the initial confidence level is less than the preset confidence level, then inputting the initial confidence level and the actual state data into a confidence estimation model to obtain the target confidence level of the GNSS signal; if the initial confidence level is greater than or equal to the preset confidence level, then determining the initial confidence level as the target confidence level of the GNSS signal. The step of inputting the initial confidence level and the actual state data into a confidence estimation model to obtain the target confidence level of the GNSS signal includes: inputting the initial confidence level and the actual state data into a preprocessing layer of the confidence estimation model, standardizing the initial confidence level and the actual state data respectively to obtain a confidence feature vector and a state feature vector; inputting the confidence feature vector and the state feature vector into a feature extraction layer of the confidence estimation model to obtain a correlation feature matrix; the actual state data includes the values ​​of one or more indicators describing the signal quality of the GNSS signal; the correlation feature matrix includes the mapping relationship between the initial confidence level and each indicator in the actual state data; and inputting the state feature vector and the correlation feature matrix into a confidence correction layer of the confidence estimation model to obtain the target confidence level of the GNSS signal. The step of inputting the state feature vector and the correlation feature matrix into the confidence correction layer of the confidence estimation model to obtain the target confidence of the GNSS signal includes: mapping the correlation feature matrix through an activation function to obtain a corrected confidence; if the corrected confidence is within a preset first confidence threshold range and the state feature vector satisfies a preset state data basic threshold condition, then the corrected confidence is determined as the target confidence; if the corrected confidence is outside a preset second confidence threshold range and the state feature vector satisfies the preset state data basic threshold condition, then the product of the corrected confidence and the up-adjustment coefficient is determined as the target confidence; if the state feature vector does not satisfy the preset state data basic threshold condition, then the lowest confidence is determined as the target confidence.

2. The outdoor positioning method according to claim 1, characterized in that, The step of inputting the GNSS positioning coordinates, the motion state data, the target confidence level, the base station positioning coordinates, and the initial positioning trajectory into the trajectory correction model to obtain the target positioning trajectory of the terminal to be located from the previous moment to the current moment includes: The GNSS positioning coordinates, the target confidence score, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory are input into the fusion positioning layer in the trajectory correction model, so as to fuse the GNSS positioning coordinates, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory according to the target confidence score, and obtain the target positioning coordinates at the current moment. The motion state data, the target positioning coordinates at the current moment, and the initial positioning trajectory are input into the trajectory correction layer of the trajectory correction model to correct the initial positioning trajectory based on the motion state data and the target positioning coordinates at the current moment, thereby obtaining the target positioning trajectory; wherein, the positioning coordinates at the previous moment in the target positioning trajectory are the same as the positioning coordinates at the previous moment in the initial positioning trajectory; and the positioning coordinates at the current moment in the target positioning trajectory are the same as the target positioning coordinates at the current moment.

3. The outdoor positioning method according to claim 2, characterized in that, The step of inputting the GNSS positioning coordinates, the target confidence score, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory into the fusion positioning layer of the trajectory correction model, so as to fuse the GNSS positioning coordinates, the base station positioning coordinates, and the initial positioning coordinates at the current moment in the initial positioning trajectory according to the target confidence score, to obtain the target positioning coordinates at the current moment, includes: The GNSS positioning coordinates and the target confidence level are input into the first weighted positioning unit in the fusion positioning layer to obtain the weighted GNSS positioning coordinates. The base station positioning coordinates and the target confidence level are input into the second weighted positioning unit in the fusion positioning layer to obtain the weighted base station positioning coordinates. The initial positioning coordinates at the current moment are input into the third weighted positioning unit in the fusion positioning layer to obtain the weighted initial positioning coordinates; The weighted GNSS positioning coordinates, the weighted base station positioning coordinates, and the weighted initial positioning coordinates are input into the fusion unit in the fusion positioning layer to obtain the target positioning coordinates at the current time.

4. An outdoor positioning device, characterized in that, The device includes: The acquisition module is used to acquire the GNSS positioning coordinates, base station signal status data, actual GNSS signal status data, motion status data, and historical positioning coordinates of the terminal to be located at the current moment; the actual status data is used to describe the signal quality of the GNSS signal; the motion status data includes the motion status of the terminal to be located from the previous moment to the current moment. The determination module is used to determine the target confidence level of the GNSS signal based on the actual state data and the standard state data of the GNSS signal; the standard state data is determined based on the historical state data of the GNSS signal whose signal quality meets the preset GNSS positioning conditions; the confidence level of the GNSS signal is used to reflect the accuracy of GNSS positioning. The input module is used to input the base station signal status data into the terminal positioning model if the target confidence level is less than a preset second confidence level, so as to obtain the base station positioning coordinates of the terminal to be located at the current time. The prediction module is used to predict the initial positioning trajectory of the terminal to be located from the previous moment to the current moment based on the motion state data and the historical positioning coordinates. The input module is further configured to input the GNSS positioning coordinates, the motion state data, the target confidence, the base station positioning coordinates, and the initial positioning trajectory into the trajectory correction model to obtain the target positioning trajectory of the terminal to be positioned from the previous moment to the current moment; Specifically, the determining module is used to calculate the similarity between the actual state data and the standard state data of the GNSS signal to obtain the initial confidence level of the GNSS signal; and to determine the target confidence level of the GNSS signal based on the numerical comparison result between the initial confidence level and the preset confidence level, the initial confidence level or the actual state data. The determining module is further configured to: if the initial confidence level is less than the preset confidence level, input the initial confidence level and the actual state data into the confidence level estimation model to obtain the target confidence level of the GNSS signal; if the initial confidence level is greater than or equal to the preset confidence level, determine the initial confidence level as the target confidence level of the GNSS signal; The input module is specifically used to input the initial confidence level and the actual state data into the preprocessing layer of the confidence estimation model, and to standardize the initial confidence level and the actual state data respectively to obtain a confidence feature vector and a state feature vector; input the confidence feature vector and the state feature vector into the feature extraction layer of the confidence estimation model to obtain an association feature matrix; the actual state data includes the values ​​of one or more indicators describing the signal quality of the GNSS signal; the association feature matrix includes the mapping relationship between the initial confidence level and each indicator in the actual state data; input the state feature vector and the association feature matrix into the confidence correction layer of the confidence estimation model to obtain the target confidence level of the GNSS signal; The input module is further configured to map the associated feature matrix using an activation function to obtain a corrected confidence level; if the corrected confidence level is within a preset first confidence level threshold range and the state feature vector satisfies a preset state data basic threshold condition, then the corrected confidence level is determined as the target confidence level; if the corrected confidence level is outside a preset second confidence level threshold range and the state feature vector satisfies the preset state data basic threshold condition, then the product of the corrected confidence level and the up-adjustment coefficient is determined as the target confidence level; if the state feature vector does not satisfy the preset state data basic threshold condition, then the lowest confidence level is determined as the target confidence level.

5. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is in operation, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the outdoor positioning method as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the outdoor positioning method as described in any one of claims 1 to 3.

Images