Intelligent positioning method and system based on Beidou satellite

Abstract

The present invention discloses a Beidou satellite-based intelligent positioning method and system, which relate to the field of intelligent positioning technology. The method and system monitor and collect Beidou positioning data in real time through a Beidou satellite navigation system, and monitor and collect 5G positioning data through a 5G communication positioning module at the same time, and introduce a data processing and analysis algorithm at the back end to perform a time series collaborative analysis of the Beidou positioning data and the 5G positioning data, so as to correct the positioning data, thereby improving the positioning accuracy and stability. In this way, intelligent positioning can be comprehensively performed by combining the Beidou satellite navigation system and the 5G communication technology, thereby improving the accuracy and reliability of positioning, so as to provide more accurate positioning services for various application scenarios.

Description

Technical Field

[0001] The present application relates to the field of intelligent positioning technology, and more specifically, to an intelligent positioning method and system based on Beidou satellites. Background Art

[0002] The BeiDou satellite navigation system is a satellite-based positioning, navigation and timing service system that can provide high-precision, high-reliability and high-efficiency global coverage services and is widely used in transportation, agriculture, meteorology, mapping, logistics and aviation. The positioning accuracy of the BeiDou satellite navigation system is affected by many factors, such as atmospheric delay, multipath effect, satellite orbit error, etc., which leads to certain fluctuations and deviations in the positioning results.

[0003] Therefore, in order to improve the positioning accuracy of the Beidou satellite navigation system, an optimized Beidou satellite-based intelligent positioning solution is desired. Summary of the invention

[0004] In order to solve the above technical problems, this application is proposed. The embodiment of the present application provides an intelligent positioning method and system based on Beidou satellite, which monitors and collects Beidou positioning data in real time through the Beidou satellite navigation system, and monitors and collects 5G positioning data through the 5G communication positioning module, and introduces data processing and analysis algorithms at the back end to perform time series collaborative analysis of the Beidou positioning data and the 5G positioning data, so as to correct the positioning data, thereby improving the positioning accuracy and stability. In this way, intelligent positioning can be comprehensively performed by combining the Beidou satellite navigation system and 5G communication technology, thereby improving the accuracy and reliability of positioning, so as to provide more accurate positioning services for various application scenarios.

[0005] According to one aspect of the present application, there is provided a Beidou satellite-based intelligent positioning method, which includes:

[0006] Obtaining Beidou positioning data collected by Beidou satellites at multiple predetermined time points within a predetermined time period;

[0007] Acquire the 5G positioning data of the plurality of predetermined time points collected by the 5G communication positioning module;

[0008] Arrange the Beidou positioning data at the plurality of predetermined time points and the 5G positioning data at the plurality of predetermined time points into a Beidou positioning data input vector and a 5G positioning data input vector respectively according to the time dimension;

[0009] After vector segmentation of the Beidou positioning data input vector into a sequence of Beidou positioning data local input vectors, the sequence of Beidou positioning data local input vectors is passed through a positioning fluctuation pattern feature extractor based on a deep neural network model to obtain a sequence of Beidou positioning data local correlation feature vectors;

[0010] Performing positioning data feature analysis on the 5G positioning data input vector to obtain a 5G positioning data encoding feature vector;

[0011] Based on the sequence of the Beidou positioning data local correlation feature vector, the 5G positioning data encoding feature vector is enhanced by a posteriori expression of feature distribution information to obtain a corrected 5G positioning data encoding feature vector as a corrected 5G positioning data encoding feature;

[0012] Based on the corrected 5G positioning data encoding features, the corrected positioning data is determined.

[0013] According to another aspect of the present application, there is provided a Beidou satellite-based intelligent positioning system, comprising:

[0014] A Beidou positioning data acquisition module is used to acquire Beidou positioning data collected by Beidou satellites at multiple predetermined time points within a predetermined time period;

[0015] A 5G positioning data acquisition module, used to acquire the 5G positioning data of the plurality of predetermined time points collected by the 5G communication positioning module;

[0016] A positioning data timing arrangement module, used to arrange the Beidou positioning data at the plurality of predetermined time points and the 5G positioning data at the plurality of predetermined time points into a Beidou positioning data input vector and a 5G positioning data input vector respectively according to the time dimension;

[0017] A Beidou positioning data local correlation feature extraction module, used for vector segmenting the Beidou positioning data input vector into a sequence of Beidou positioning data local input vectors, and then passing the sequence of Beidou positioning data local input vectors through a positioning fluctuation pattern feature extractor based on a deep neural network model to obtain a sequence of Beidou positioning data local correlation feature vectors;

[0018] A 5G positioning data feature analysis module, used to perform positioning data feature analysis on the 5G positioning data input vector to obtain a 5G positioning data encoding feature vector;

[0019] A feature distribution information a posteriori expression enhancement module is used to enhance the feature distribution information a posteriori expression of the 5G positioning data encoding feature vector based on the sequence of the Beidou positioning data local correlation feature vector to obtain a corrected 5G positioning data encoding feature vector as a corrected 5G positioning data encoding feature;

[0020] The corrected positioning data determination module is used to determine the corrected positioning data based on the corrected 5G positioning data encoding characteristics.

[0021] Compared with the prior art, the present application provides a Beidou satellite-based intelligent positioning method and system, which monitors and collects Beidou positioning data in real time through the Beidou satellite navigation system, and monitors and collects 5G positioning data through a 5G communication positioning module, and introduces data processing and analysis algorithms at the back end to perform time series collaborative analysis of the Beidou positioning data and the 5G positioning data, so as to correct the positioning data, thereby improving the positioning accuracy and stability. In this way, intelligent positioning can be comprehensively performed by combining the Beidou satellite navigation system and 5G communication technology, thereby improving the accuracy and reliability of positioning, so as to provide more accurate positioning services for various application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0023] Figure 1 The present invention is a flowchart of an intelligent positioning method based on Beidou satellites according to an embodiment of the present application.

[0024] Figure 2 Schematic diagram of the architecture of the Beidou satellite-based intelligent positioning method according to an embodiment of the present application.

[0025] Figure 3 The present invention is a flowchart for training the positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model, the positioning accuracy feature extractor based on the one-dimensional convolutional layer, and the decoder in the Beidou satellite-based intelligent positioning method according to an embodiment of the present application.

[0026] Figure 4 The present invention is a flowchart of passing the training corrected 5G positioning data encoding feature vector through the decoder to obtain a decoding loss function value in the Beidou satellite-based intelligent positioning method according to an embodiment of the present application.

[0027] Figure 5 4 is a block diagram of a Beidou satellite-based intelligent positioning system according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0029] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0030] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0031] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0032] The BeiDou satellite navigation system is a satellite-based positioning, navigation and timing service system independently developed by China. It consists of a group of satellites operating in Earth orbit, ground control systems and user terminals, and can provide positioning, navigation and timing services to users around the world. The positioning accuracy of the BeiDou satellite navigation system is affected by many factors. The following are some common influencing factors: 1. Atmospheric delay: Satellite signals will be refracted and delayed when passing through the atmosphere, resulting in errors in positioning results. 2. Multipath effect: The multipath effect refers to the reflection of satellite signals from objects such as the ground and buildings during propagation, resulting in the receiver receiving multiple signal paths. This effect will cause signal interference and positioning errors. 3. Satellite orbit error: There may be errors in the orbital parameters of the satellite, which will cause errors in the positioning results. In addition to the above factors, there are other factors that may affect the positioning accuracy of the BeiDou satellite navigation system, such as receiver performance, signal shielding, multipath interference environment, etc., resulting in a certain degree of deviation in the positioning results.

[0033] 5G communication technology is a mobile communication technology based on radio waves, which can provide a new communication experience with high speed, low latency and large number of connections. 5G communication technology can also be used for positioning services, by measuring the propagation time, angle, strength and other parameters of the radio signal to calculate the location information of the mobile device. However, the positioning accuracy of 5G communication technology will be affected by the radio signal propagation environment, such as obstruction, reflection, attenuation, etc., resulting in certain uncertainties and errors in the positioning results. Therefore, in order to improve the accuracy and reliability of positioning and provide more accurate positioning services for various application scenarios, it is necessary to use different positioning technologies to correct and optimize the positioning data.

[0034] Based on this, the technical concept of this application is to monitor and collect Beidou positioning data in real time through the Beidou satellite navigation system, and monitor and collect 5G positioning data through the 5G communication positioning module, and introduce data processing and analysis algorithms at the back end to perform time series collaborative analysis of the Beidou positioning data and the 5G positioning data, so as to correct the positioning data, thereby improving the positioning accuracy and stability. In this way, intelligent positioning can be comprehensively performed by combining the Beidou satellite navigation system and 5G communication technology, thereby improving the accuracy and reliability of positioning, so as to provide more accurate positioning services for various application scenarios.

[0035] Figure 1 The present invention is a flowchart of an intelligent positioning method based on Beidou satellites according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the architecture of the Beidou satellite-based intelligent positioning method according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the embodiment of the present application, the intelligent positioning method based on Beidou satellite includes: S110, obtaining Beidou positioning data of multiple predetermined time points within a predetermined time period collected by Beidou satellite; S120, obtaining 5G positioning data of the multiple predetermined time points collected by the 5G communication positioning module; S130, arranging the Beidou positioning data of the multiple predetermined time points and the 5G positioning data of the multiple predetermined time points into Beidou positioning data input vectors and 5G positioning data input vectors according to the time dimension respectively; S140, after vector cutting the Beidou positioning data input vector into a sequence of Beidou positioning data local input vectors, the Beidou positioning data local input vectors are arranged. The sequence of local input data vectors is passed through a positioning fluctuation pattern feature extractor based on a deep neural network model to obtain a sequence of Beidou positioning data local correlation feature vectors; S150, positioning data feature analysis is performed on the 5G positioning data input vector to obtain a 5G positioning data coding feature vector; S160, based on the sequence of Beidou positioning data local correlation feature vectors, the 5G positioning data coding feature vector is enhanced by a posteriori expression of feature distribution information to obtain a corrected 5G positioning data coding feature vector as a corrected 5G positioning data coding feature; and, S170, based on the corrected 5G positioning data coding feature, the corrected positioning data is determined.

[0036] In step S110, Beidou positioning data at multiple predetermined time points within a predetermined time period collected by Beidou satellites are obtained. In step S120, 5G positioning data at the multiple predetermined time points collected by the 5G communication positioning module are obtained. It should be understood that the positioning data collected by the Beidou satellite navigation system and the 5G communication positioning module have different characteristics and advantages. Specifically, Beidou positioning data has better coverage and positioning performance in outdoor environments, while 5G positioning data has better robustness in complex environments such as cities. Based on this, in the technical solution of the present application, Beidou positioning data at multiple predetermined time points within a predetermined time period collected by Beidou satellites and 5G positioning data at the multiple predetermined time points collected by the 5G communication positioning module are obtained, and the two positioning data can be compared and corrected using a timing collaborative analysis algorithm. Accordingly, the positioning data at different time points can provide different perspectives and information. By comprehensively analyzing the Beidou positioning data and the 5G positioning data, the positioning error can be reduced, and their respective limitations can be compensated, thereby improving the positioning accuracy and stability.

[0037] In step S130, the Beidou positioning data at the multiple predetermined time points and the 5G positioning data at the multiple predetermined time points are arranged as Beidou positioning data input vectors and 5G positioning data input vectors according to the time dimension, respectively. Accordingly, considering that both the Beidou positioning data and the 5G positioning data have a dynamic change law of time series in the time dimension, that is, the positioning data will continue to change with the change of time, this time series change feature is of great significance to the accuracy of positioning. Therefore, in the technical solution of the present application, it is necessary to arrange the Beidou positioning data at the multiple predetermined time points and the 5G positioning data at the multiple predetermined time points as Beidou positioning data input vectors and 5G positioning data input vectors according to the time dimension, respectively, so as to integrate the distribution information of the Beidou positioning data and the 5G positioning data in time series, respectively.

[0038] In step S140, after the Beidou positioning data input vector is vector-sliced ​​into a sequence of Beidou positioning data local input vectors, the sequence of Beidou positioning data local input vectors is passed through a positioning fluctuation pattern feature extractor based on a deep neural network model to obtain a sequence of Beidou positioning data local correlation feature vectors. In particular, here, the deep neural network model is a one-dimensional convolutional neural network model. It should be understood that, considering that in the process of intelligent positioning, the Beidou positioning data often has certain timing fluctuations and changes. These fluctuations and changes may be related to the location change of the terminal, or may be caused by the environment or other factors. Therefore, in order to more fully and finely capture the fluctuation pattern and associated information of the Beidou positioning data, so as to facilitate more accurate positioning, in the technical solution of the present application, after further vector segmentation of the Beidou positioning data input vector into a sequence of Beidou positioning data local input vectors, the sequence of Beidou positioning data local input vectors is subjected to feature mining in a positioning fluctuation pattern feature extractor based on a one-dimensional convolutional neural network model, so as to respectively extract the local time series feature information of the Beidou positioning data in each local time period, thereby obtaining a sequence of Beidou positioning data local associated feature vectors. It should be understood that the positioning fluctuation pattern feature extractor of the one-dimensional convolutional neural network model can perform feature extraction on each local input vector in the time dimension through a convolution operation. The convolution operation can capture the characteristic patterns of the Beidou positioning data in each local time series area, such as the fluctuation pattern and trend characteristics of the local time series and other associated information.

[0039] In step S150, the 5G positioning data input vector is subjected to positioning data feature analysis to obtain a 5G positioning data encoding feature vector. Specifically, in an embodiment of the present application, the 5G positioning data input vector is subjected to positioning data feature analysis to obtain a 5G positioning data encoding feature vector, including: passing the 5G positioning data input vector through a positioning accuracy feature extractor based on a one-dimensional convolutional layer to obtain the 5G positioning data encoding feature vector. Accordingly, considering that the 5G positioning data contains a series of information related to positioning accuracy, such as signal strength, multipath effect, etc., in order to capture the timing encoding features of the 5G positioning data to represent its positioning accuracy, in the technical solution of the present application, the 5G positioning data input vector is further subjected to feature mining in a positioning accuracy feature extractor based on a one-dimensional convolutional layer to extract the timing feature information of the 5G positioning data, thereby obtaining a 5G positioning data encoding feature vector. Processing the 5G positioning data input vector through the positioning accuracy feature extractor based on the one-dimensional convolutional layer can capture the local time series feature pattern of the 5G positioning data, so as to reflect the changing trend of the signal strength, the influence of the multipath effect, etc., and provide a basis for subsequent positioning data correction.

[0040] In step S160, based on the sequence of the local associated feature vectors of the Beidou positioning data, the feature distribution information of the 5G positioning data encoding feature vector is enhanced a posteriori to obtain the corrected 5G positioning data encoding feature vector as the corrected 5G positioning data encoding feature. It should be understood that in intelligent positioning, different positioning data sources may have certain errors and deviations. In other words, the Beidou positioning data and the 5G positioning data have their own characteristics and limitations. Therefore, in order to be able to use the local timing characteristics of the Beidou positioning data to enhance the expression of the timing encoding characteristics of the 5G positioning data, so as to complement and correct each other by using the feature information of the two, so as to obtain a more accurate positioning result, in the technical solution of the present application, the feature distribution information of the 5G positioning data encoding feature vector is further enhanced based on the sequence of the local associated feature vectors of the Beidou positioning data to obtain the corrected 5G positioning data encoding feature vector. It should be understandable that since the sequence of local correlation feature vectors based on Beidou positioning data can provide information about the timing fluctuation pattern and change correlation of Beidou positioning data, this information can be used to perform a posteriori expression and enhancement of the feature distribution information of the encoded feature vector of 5G positioning data, and the encoding features of the 5G positioning data can be corrected, thereby correcting possible errors and deviations and improving the accuracy of the positioning data.

[0041] Specifically, in an embodiment of the present application, based on the sequence of the Beidou positioning data locally associated feature vectors, the 5G positioning data encoding feature vector is subjected to feature distribution information a posteriori expression enhancement to obtain a corrected 5G positioning data encoding feature vector as the corrected 5G positioning data encoding feature, including: performing feature a posteriori expression enhancement on the sequence of the Beidou positioning data locally associated feature vectors and the 5G positioning data encoding feature vector using the following a posteriori expression enhancement formula to obtain the corrected 5G positioning data encoding feature vector as the corrected 5G positioning data encoding feature; wherein the a posteriori expression enhancement formula is:

[0042]

[0043]

[0044] Wherein, V represents the 5G positioning data encoding feature vector, a represents 1×n w The matrix, N w is equal to the scale of the 5G positioning data encoding feature vector, and B is 1×N h The matrix, N h is equal to the number of Beidou positioning data local correlation feature vectors in the sequence of Beidou positioning data local correlation feature vectors, σ is the Sigmoid function, s is the weight coefficient, M w and M h represents the convolution operation of 1×1 convolution kernel, h i Represents each Beidou positioning data local correlation feature vector in the sequence of Beidou positioning data local correlation feature vectors, N represents the scale of each Beidou positioning data local correlation feature vector in the sequence of Beidou positioning data local correlation feature vectors, and v' represents the corrected 5G positioning data encoding feature vector.

[0045] In step S170, based on the corrected 5G positioning data coding features, the corrected positioning data is determined. It should be understood that the corrected feature vector combines the Beidou positioning data and the 5G positioning data. Based on this, in the technical solution of the present application, the corrected positioning data is further determined based on the corrected 5G positioning data coding features, and the local correlation features of the Beidou positioning data can be used to make up for the limitations of the 5G positioning data, which can better reflect the real location information, thereby improving the positioning precision and accuracy.

[0046] Specifically, in an embodiment of the present application, based on the corrected 5G positioning data coding features, determining the corrected positioning data includes: passing the corrected 5G positioning data coding feature vector through a decoder to obtain a decoding result, and the decoding result is the corrected positioning data. In other words, decoding regression is performed using the 5G positioning data coding feature information corrected by the Beidou positioning data timing features, so as to correct the positioning data, thereby improving positioning accuracy and stability.

[0047] It is worth mentioning that those skilled in the art should be aware that before applying a deep neural network model for inference, the deep neural network model must be trained so that the deep neural network can implement specific functional capabilities.

[0048] Specifically, in an embodiment of the present application, a training step is also included: for training the positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model, the positioning accuracy feature extractor based on the one-dimensional convolutional layer, and the decoder.

[0049] Figure 3 The present invention is a flowchart of training the positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model, the positioning accuracy feature extractor based on the one-dimensional convolutional layer, and the decoder in the Beidou satellite-based intelligent positioning method according to an embodiment of the present application. Figure 3As shown, the training step includes: S210, obtaining training data, the training data including training Beidou positioning data at multiple predetermined time points within a predetermined time period collected by Beidou satellites, training 5G positioning data at multiple predetermined time points collected by a 5G communication positioning module, and corrected real positioning data; S220, arranging the training Beidou positioning data at the multiple predetermined time points and the training 5G positioning data at the multiple predetermined time points into a training Beidou positioning data input vector and a training 5G positioning data input vector according to the time dimension respectively; S230, after vector segmentation of the training Beidou positioning data input vector into a sequence of training Beidou positioning data local input vectors, the sequence of training Beidou positioning data local input vectors is passed through the positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model to obtain a sequence of training Beidou positioning data local correlation feature vectors; S240, arranging the training 5G positioning data According to the input vector, the positioning accuracy feature extractor based on the one-dimensional convolution layer is passed to obtain the training 5G positioning data encoding feature vector; S250, based on the sequence of the training Beidou positioning data local correlation feature vector, the feature distribution information of the training 5G positioning data encoding feature vector is enhanced by the posterior expression to obtain the training correction 5G positioning data encoding feature vector; S260, the training correction 5G positioning data encoding feature vector is passed through the decoder to obtain the decoding loss function value; and, S270, based on the decoding loss function value and through the back propagation of gradient descent, the positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model, the positioning accuracy feature extractor based on the one-dimensional convolution layer and the decoder are trained, wherein each time the training correction 5G positioning data encoding feature vector passes through the decoder for decoding iteration, the training correction 5G positioning data encoding feature vector is optimized.

[0050] Specifically, in step S260, the training corrected 5G positioning data encoding feature vector is passed through the decoder to obtain a decoding loss function value. Figure 4 The present invention is a flowchart of passing the training corrected 5G positioning data encoding feature vector through the decoder to obtain a decoding loss function value in the Beidou satellite-based intelligent positioning method according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 4 As shown, the training corrected 5G positioning data encoding feature vector is passed through the decoder to obtain a decoding loss function value, including: S310, passing the training corrected 5G positioning data encoding feature vector through the decoder to obtain a training decoding result; and, S320, calculating the cross entropy loss function value between the training decoding result and the corrected true positioning data as the decoding loss function value.

[0051] Specifically, in step S270, the positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model, the positioning accuracy feature extractor based on the one-dimensional convolutional layer, and the decoder are trained based on the decoding loss function value and through back propagation of gradient descent, wherein each time the training correction 5G positioning data encoding feature vector is decoded iteratively through the decoder, the training correction 5G positioning data encoding feature vector is optimized. It should be understood that in the technical solution of the present application, the sequence of the training Beidou positioning data local correlation feature vectors expresses the temporal correlation characteristics of the training Beidou positioning data in the local time domain after the global time domain is divided, and the training 5G positioning data encoding feature vector expresses the local temporal correlation characteristics of the training 5G positioning data in the global time domain based on the one-dimensional convolution kernel. Therefore, when the feature distribution information of the training 5G positioning data encoding feature vector is enhanced based on the sequence of the training Beidou positioning data local correlation feature vectors, the local correlation characteristics of the training Beidou positioning data are taken into consideration. The difference in source data time series distribution and feature time domain scale expression between the sequence of vectors and the training 5G positioning data encoding feature vectors, the obtained training correction 5G positioning data encoding feature vectors will have local distribution non-uniformity based on the eigenvalue granularity due to the feature distribution alignment difference corresponding to the sequence of the training Beidou positioning data local correlation feature vectors, that is, the training correction 5G positioning data encoding feature vectors have a local distribution non-uniformity class mapping illusion, thereby affecting the convergence effect of the training correction 5G positioning data encoding feature vector to the decoding regression probability density space when it is decoded by the decoder. Based on this, in the technical solution of the present application, each time the training correction 5G positioning data encoding feature vector is decoded iteratively by the decoder, the training correction 5G positioning data encoding feature vector is optimized.

[0052] More specifically, in an embodiment of the present application, each time the training corrected 5G positioning data encoding feature vector is decoded and iterated through the decoder, the training corrected 5G positioning data encoding feature vector is optimized, including: each time the training corrected 5G positioning data encoding feature vector is decoded and iterated through the decoder, the training corrected 5G positioning data encoding feature vector is optimized using the following optimization formula; wherein the optimization formula is:

[0053]

[0054]

[0055] Wherein, V represents the training correction 5G positioning data encoding feature vector, v i and v (are the eigenvalues ​​of the i-th and j-th positions of the training and correction 5G positioning data encoding feature vector, m μ represents the first intermediate matrix, M σ represents the second intermediate matrix, M μ (i, j) represents the eigenvalue of the (i, j) position of the first intermediate matrix, M σ (i,j) represents the eigenvalue of the (i,j) position of the second intermediate matrix, It means adding by position. represents matrix multiplication, and V′ represents the optimized training correction 5G positioning data encoding feature vector.

[0056] That is, by introducing the local statistical information distribution of the training corrected 5G positioning data encoding feature vector V as an external information source to enhance the retrieval of the feature vector, based on the local statistical dense information structuring to avoid the local overflow information distribution leading to the non-uniform feature distribution class mapping illusion of the training corrected 5G positioning data encoding feature vector V, so as to obtain the information credible response reasoning based on the local distribution group dimension retention corresponding to the sequence of the training Beidou positioning data local associated feature vector of the training corrected 5G positioning data encoding feature vector V, that is, to obtain the credible distribution response of the training corrected 5G positioning data encoding feature vector V in the probability density space based on the non-uniform local feature distribution, so as to improve the convergence effect of the decoding regression probability density space, so as to improve the decoding training speed and the accuracy of the training results. In this way, it is possible to comprehensively perform intelligent positioning by combining the Beidou satellite navigation system and 5G communication technology, thereby improving the accuracy and reliability of positioning, so as to provide more accurate positioning services for various application scenarios.

[0057] In summary, the Beidou satellite-based intelligent positioning method based on the embodiment of the present application is explained, which monitors and collects Beidou positioning data in real time through the Beidou satellite navigation system, and monitors and collects 5G positioning data through the 5G communication positioning module, and introduces data processing and analysis algorithms at the back end to perform time series collaborative analysis of the Beidou positioning data and the 5G positioning data, so as to correct the positioning data, thereby improving the positioning accuracy and stability. In this way, intelligent positioning can be comprehensively performed by combining the Beidou satellite navigation system and 5G communication technology, thereby improving the accuracy and reliability of positioning, so as to provide more accurate positioning services for various application scenarios.

[0058] Figure 5 FIG. 1 is a block diagram of an intelligent positioning system based on Beidou satellites according to an embodiment of the present application. Figure 5As shown, according to the embodiment of the present application, the Beidou satellite-based intelligent positioning system 100 includes: a Beidou positioning data acquisition module 110, which is used to acquire Beidou positioning data at multiple predetermined time points within a predetermined time period collected by Beidou satellites; a 5G positioning data acquisition module 120, which is used to acquire the 5G positioning data at the multiple predetermined time points collected by the 5G communication positioning module; a positioning data timing arrangement module 130, which is used to arrange the Beidou positioning data at the multiple predetermined time points and the 5G positioning data at the multiple predetermined time points into Beidou positioning data input vectors and 5G positioning data input vectors according to the time dimension respectively; a Beidou positioning data local correlation feature extraction module 140, which is used to vector-slice the Beidou positioning data input vector into a sequence of Beidou positioning data local input vectors, and then The sequence of the local input vectors of the Beidou positioning data is passed through a positioning fluctuation pattern feature extractor based on a deep neural network model to obtain a sequence of local correlation feature vectors of the Beidou positioning data; a 5G positioning data feature analysis module 150 is used to perform positioning data feature analysis on the 5G positioning data input vector to obtain a 5G positioning data encoding feature vector; a feature distribution information posterior expression enhancement module 160 is used to perform feature distribution information posterior expression enhancement on the 5G positioning data encoding feature vector based on the sequence of local correlation feature vectors of the Beidou positioning data to obtain a corrected 5G positioning data encoding feature vector as a corrected 5G positioning data encoding feature; and a corrected positioning data determination module 170 is used to determine the corrected positioning data based on the corrected 5G positioning data encoding feature.

[0059] Here, those skilled in the art will appreciate that the specific operations of each step in the above-mentioned Beidou satellite-based intelligent positioning system have been described in detail above. Figures 1 to 4 The description of the Beidou satellite-based intelligent positioning method has been introduced in detail, and therefore, its repeated description will be omitted.

[0060] As described above, the Beidou satellite-based intelligent positioning system 100 according to the embodiment of the present disclosure can be implemented in various wireless terminals, such as a server with a Beidou satellite-based intelligent positioning algorithm. In a possible implementation, the Beidou satellite-based intelligent positioning system 100 according to the embodiment of the present disclosure can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the Beidou satellite-based intelligent positioning system 100 can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the Beidou satellite-based intelligent positioning system 100 can also be one of the many hardware modules of the wireless terminal.

[0061] Alternatively, in another example, the Beidou satellite-based intelligent positioning system 100 and the wireless terminal may also be separate devices, and the Beidou satellite-based intelligent positioning system 100 may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0062] The foregoing is merely an example of the principles of the present disclosure, and various modifications may be made by those skilled in the art without departing from the scope of the present disclosure. The above embodiments are presented for the purpose of illustration and not limitation. The present disclosure may also take many forms other than those explicitly described herein. Therefore, it is emphasized that the present disclosure is not limited to the methods, systems and devices explicitly disclosed, but is intended to include variations and modifications within the spirit and scope of the appended claims.

Claims

1. An intelligent positioning method based on Beidou satellite, characterized in that: include: Obtaining Beidou positioning data collected by Beidou satellites at multiple predetermined time points within a predetermined time period; Acquire the 5G positioning data of the plurality of predetermined time points collected by the 5G communication positioning module; Arrange the Beidou positioning data at the plurality of predetermined time points and the 5G positioning data at the plurality of predetermined time points into a Beidou positioning data input vector and a 5G positioning data input vector respectively according to the time dimension; After vector segmentation of the Beidou positioning data input vector into a sequence of Beidou positioning data local input vectors, the sequence of Beidou positioning data local input vectors is passed through a positioning fluctuation pattern feature extractor based on a deep neural network model to obtain a sequence of Beidou positioning data local correlation feature vectors; Performing positioning data feature analysis on the 5G positioning data input vector to obtain a 5G positioning data encoding feature vector; Based on the sequence of the Beidou positioning data local correlation feature vector, the 5G positioning data encoding feature vector is enhanced by a posteriori expression of feature distribution information to obtain a corrected 5G positioning data encoding feature vector as a corrected 5G positioning data encoding feature; Based on the corrected 5G positioning data encoding features, the corrected positioning data is determined.

2. The Beidou satellite-based intelligent positioning method according to claim 1, characterized in that: The deep neural network model is a one-dimensional convolutional neural network model.

3. The Beidou satellite-based intelligent positioning method according to claim 2, characterized in that: Performing positioning data feature analysis on the 5G positioning data input vector to obtain a 5G positioning data encoding feature vector, including: passing the 5G positioning data input vector through a positioning accuracy feature extractor based on a one-dimensional convolutional layer to obtain the 5G positioning data encoding feature vector.

4. The Beidou satellite-based intelligent positioning method according to claim 3, characterized in that: Based on the sequence of the Beidou positioning data local correlation feature vectors, the 5G positioning data coding feature vector is subjected to feature distribution information a posteriori expression enhancement to obtain the corrected 5G positioning data coding feature vector as the corrected 5G positioning data coding feature, including: performing feature a posteriori expression enhancement on the sequence of the Beidou positioning data local correlation feature vectors and the 5G positioning data coding feature vector using the following a posteriori expression enhancement formula to obtain the corrected 5G positioning data coding feature vector as the corrected 5G positioning data coding feature; Among them, the posterior expression enhancement formula is: ; ； in, represents the 5G positioning data encoding feature vector, Indicates 1× The matrix of is equal to the scale of the 5G positioning data encoding feature vector, and B is 1× The matrix of is equal to the number of Beidou positioning data local correlation feature vectors in the sequence of Beidou positioning data local correlation feature vectors, is the Sigmoid function, is the weight coefficient, and represents the convolution operation of a 1×1 convolution kernel, each Beidou positioning data local correlation feature vector in the sequence of Beidou positioning data local correlation feature vectors, represents the scale of each Beidou positioning data local correlation feature vector in the sequence of Beidou positioning data local correlation feature vectors, Represents the corrected 5G positioning data encoding feature vector.

5. The Beidou satellite-based intelligent positioning method according to claim 4, characterized in that: Based on the encoding characteristics of the corrected 5G positioning data, the corrected positioning data is determined, including: passing the encoding characteristic vector of the corrected 5G positioning data through a decoder to obtain a decoding result, and the decoding result is the corrected positioning data.

6. The Beidou satellite-based intelligent positioning method according to claim 5, characterized in that: It also includes a training step: used to train the positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model, the positioning accuracy feature extractor based on the one-dimensional convolutional layer, and the decoder.

7. The Beidou satellite-based intelligent positioning method according to claim 6, characterized in that: The training step comprises: Acquire training data, the training data including training Beidou positioning data at multiple predetermined time points within a predetermined time period collected by Beidou satellites, training 5G positioning data at multiple predetermined time points collected by a 5G communication positioning module, and corrected real positioning data; Arrange the training Beidou positioning data at the plurality of predetermined time points and the training 5G positioning data at the plurality of predetermined time points into a training Beidou positioning data input vector and a training 5G positioning data input vector respectively according to the time dimension; After vector segmentation of the training Beidou positioning data input vector into a sequence of training Beidou positioning data local input vectors, the sequence of training Beidou positioning data local input vectors is passed through the positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model to obtain a sequence of training Beidou positioning data local correlation feature vectors; Passing the training 5G positioning data input vector through the positioning accuracy feature extractor based on the one-dimensional convolutional layer to obtain a training 5G positioning data encoding feature vector; Based on the sequence of the training Beidou positioning data local correlation feature vectors, the training 5G positioning data encoding feature vector is enhanced by a posteriori expression of feature distribution information to obtain a training correction 5G positioning data encoding feature vector; Passing the training corrected 5G positioning data encoding feature vector through the decoder to obtain a decoding loss function value; The positioning fluctuation pattern feature extractor based on the one-dimensional convolutional neural network model, the positioning accuracy feature extractor based on the one-dimensional convolutional layer and the decoder are trained based on the decoding loss function value and through back propagation of gradient descent, wherein the training corrected 5G positioning data encoding feature vector is optimized each time the training corrected 5G positioning data encoding feature vector is decoded iteratively through the decoder.

8. The Beidou satellite-based intelligent positioning method according to claim 7, characterized in that: Passing the training corrected 5G positioning data encoding feature vector through a decoder to obtain a decoding loss function value includes: Passing the training corrected 5G positioning data encoding feature vector through the decoder to obtain a training decoding result; A cross entropy loss function value between the training decoding result and the corrected true positioning data is calculated as the decoding loss function value.

9. An intelligent positioning system based on Beidou satellite, characterized in that: include: A Beidou positioning data acquisition module is used to acquire Beidou positioning data collected by Beidou satellites at multiple predetermined time points within a predetermined time period; A 5G positioning data acquisition module, used to acquire the 5G positioning data of the plurality of predetermined time points collected by the 5G communication positioning module; A positioning data timing arrangement module, used to arrange the Beidou positioning data at the plurality of predetermined time points and the 5G positioning data at the plurality of predetermined time points into a Beidou positioning data input vector and a 5G positioning data input vector respectively according to the time dimension; A Beidou positioning data local correlation feature extraction module, used for vector segmenting the Beidou positioning data input vector into a sequence of Beidou positioning data local input vectors, and then passing the sequence of Beidou positioning data local input vectors through a positioning fluctuation pattern feature extractor based on a deep neural network model to obtain a sequence of Beidou positioning data local correlation feature vectors; A 5G positioning data feature analysis module, used to perform positioning data feature analysis on the 5G positioning data input vector to obtain a 5G positioning data encoding feature vector; A feature distribution information a posteriori expression enhancement module is used to enhance the feature distribution information a posteriori expression of the 5G positioning data encoding feature vector based on the sequence of the Beidou positioning data local correlation feature vector to obtain a corrected 5G positioning data encoding feature vector as a corrected 5G positioning data encoding feature; The corrected positioning data determination module is used to determine the corrected positioning data based on the corrected 5G positioning data encoding characteristics.

10. The Beidou satellite-based intelligent positioning system according to claim 9, characterized in that: The 5G positioning data feature analysis module is used to: pass the 5G positioning data input vector through a positioning accuracy feature extractor based on a one-dimensional convolutional layer to obtain the 5G positioning data encoding feature vector.

Images