A multi-source navigation information data fusion analysis method and system

By calculating the stability characterization value and degree of interference of navigation data, and assigning the navigation data weight value for weighting fusion, the problem of low navigation accuracy and reliability in multi-source navigation data fusion is solved, and more reliable navigation data fusion is achieved.

CN118862001BActive Publication Date: 2024-12-03XIAN HEZHONGSIZHUANG DEFENSE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411341065.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-25
Publication Date
2024-12-03
Estimated Expiration
2044-09-25

AI Technical Summary

Technical Problem

When fusion of multi-source navigation information data, the environmental interference of different types of navigation data cannot be effectively considered, resulting in low navigation accuracy and reliability.

Method used

By obtaining the characteristic mark value of the navigation data to be fused and the characteristic mark value of the historical navigation data, calculate the stability characterization value and degree of interference of each navigation data, assign each navigation data weight value, and perform weight fusion to improve the navigation data reliability.

Benefits of technology

Improve the reliability of multi-source navigation data fusion, ensuring that the acquired converged navigation data is more reliable and accurate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118862001B_ABST
    Figure CN118862001B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data fusion technology, and in particular to a multi-source navigation information data fusion analysis method and system. The method comprises: obtaining a first weight value of each navigation data to be fused according to the location of the target mobile object at the current analysis moment; obtaining a stability characterization value of the navigation data to be fused, and taking the ratio of the stability characterization value of the navigation data to be fused to the comprehensive stability characterization value as the second weight value of the corresponding navigation data to be fused; obtaining a third weight value of each navigation data to be fused according to the historical navigation data in the historical navigation data vector; recording the average of the first weight value, the second weight value and the third weight value of each navigation data to be fused as the target weight value of the corresponding navigation data to be fused; obtaining the fused navigation data at the location of the target mobile object at the current analysis moment according to the target weight value. The present invention can make the acquired fused navigation data more reliable.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data fusion, and in particular to a multi-source navigation information data fusion analysis method and system. Background Art

[0002] Navigation information data can provide navigation and positioning services, optimize travel experience, enhance safety, improve production efficiency, and promote personal and social development; and currently, in order to improve navigation accuracy and reliability, optimize resource allocation, enhance response capabilities, and improve user experience, multi-source navigation information data is usually integrated, that is, different types of navigation information data are integrated, which is crucial to improving navigation accuracy and reliability, optimizing resource allocation, enhancing response capabilities, and improving user experience.

[0003] Currently, when fusing multi-source navigation information, that is, when fusing different types of navigation data, different types of navigation data are generally directly fused without considering the environmental interference of different types of navigation data. However, due to the different ways of collecting different types of navigation data, the environmental interference of different types of navigation data will be different, resulting in different reference values ​​of different types of navigation data. When fusing, if the reference value of different types of navigation data or the degree of environmental interference is not considered, the reliability of the navigation data obtained by the final fusion will be low, which may result in low navigation accuracy, navigation reliability, etc. Therefore, how to improve the reliability of multi-source navigation data fusion is an urgent problem to be solved. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a multi-source navigation information data fusion analysis method and system, and the technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a multi-source navigation information data fusion analysis method, comprising the following steps: obtaining a navigation data vector to be fused at a position of a target mobile object at a current analysis moment, a historical navigation data vector sequence, a feature mark value of each navigation data to be fused in the navigation data vector to be fused, and a feature mark value of each historical navigation data in a historical navigation data vector, wherein the navigation data vector is composed of A types of navigation data, and the historical navigation data vector belongs to the historical navigation data vector sequence;

[0006] According to the position of the target moving object at the current analysis moment, obtaining a first weight value of each navigation data to be fused in the navigation data vector to be fused;

[0007] obtaining a sequence of data points to be analyzed for each navigation data to be fused according to the navigation data vector to be fused, the historical navigation data vector, the characteristic mark value of the navigation data to be fused and the characteristic mark value of the historical navigation data; obtaining a stability characterization value for each navigation data to be fused according to the sequence of data points to be analyzed, and taking a ratio of the stability characterization value of the navigation data to be fused to a comprehensive stability characterization value as a second weight value corresponding to the navigation data to be fused, the comprehensive stability characterization value being the cumulative sum of the stability characterization values ​​of all the navigation data to be fused;

[0008] Obtaining a third weight value of each navigation data to be fused according to the historical navigation data in the historical navigation data vector;

[0009] Recording an average of the first weight value, the second weight value and the third weight value of each navigation data to be fused as a target weight value of the corresponding navigation data to be fused;

[0010] According to the target weight value, the fused navigation data at the position of the target moving object at the current analysis moment is obtained.

[0011] In a second aspect, an embodiment of the present invention provides a multi-source navigation information data fusion analysis system, including a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the above-mentioned multi-source navigation information data fusion analysis method.

[0012] Beneficial effect: The present invention obtains the first weight value of each navigation data to be fused in the navigation data vector according to the location of the target mobile object at the current analysis moment; then, according to the sequence of data points to be analyzed, the stability characterization value of each navigation data to be fused is obtained, and the ratio of the stability characterization value of the navigation data to be fused to the comprehensive stability characterization value is used as the second weight value of the corresponding navigation data to be fused; then, according to the historical navigation data in the historical navigation data vector, the third weight value of each navigation data to be fused is obtained; and the average of the first weight value, the second weight value and the third weight value of each navigation data to be fused is recorded as the target weight value of the corresponding navigation data to be fused; finally, according to the target weight value, the fused navigation data at the location of the target mobile object at the current analysis moment is obtained. The present invention can improve the reliability of fusing multi-source navigation data based on the obtained target weight value, that is, it can make the obtained fused navigation data more reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0014] Figure 1 The present invention is a flowchart of a multi-source navigation information data fusion analysis method. DETAILED DESCRIPTION

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the embodiments of the present invention.

[0016] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0017] This embodiment provides a multi-source navigation information data fusion analysis method, which is described in detail as follows:

[0018] like Figure 1 As shown, the multi-source navigation information data fusion analysis method includes the following steps:

[0019] Step S001, obtaining the navigation data vector to be fused, the historical navigation data vector sequence, the characteristic mark value of each navigation data to be fused in the navigation data vector to be fused, and the characteristic mark value of each historical navigation data in the historical navigation data vector at the position of the target mobile object at the current analysis moment.

[0020] The main purpose of this embodiment is to perform weighted fusion of different types of navigation data by analyzing the interference conditions of different types of navigation data and the reference value of different types of navigation data, so as to obtain reliable fused navigation data, that is, to improve the reliability of multi-source navigation information data fusion.

[0021] In addition, for ease of understanding, this embodiment will be analyzed by taking any moving object as an example and recorded as a target moving object. Moreover, the target moving object in this embodiment is an object that is moving, such as a car.

[0022] Then, the position of the target moving object at the current analysis moment and the preset starting position are obtained, and the position of the target moving object at the current analysis moment is recorded as the current position; in addition, in this embodiment, the preset starting position is the position of the target moving object before it starts moving; then, the time period for the target moving object to move from the preset starting position to the current position is obtained, and recorded as the moving time period of the target moving object; and in this embodiment, the preset starting position and each position of the target moving object during the moving process need to be determined according to the moving route of the target object. Therefore, in this embodiment, a preset moving route can be set, and the preset starting position is used as the starting position on the preset moving route, and the current position is used as the end position on the preset moving route. For example, if the preset moving route in this embodiment is any route from location 1 to location 2, then location 1 is the preset starting position and location 2 is the current position.

[0023] Then, this embodiment arranges to collect navigation data once at a preset time interval, that is, navigation data is collected once at a preset time interval during the process of the target moving object moving from a preset starting position to a current position, and this embodiment can obtain all data collection moments in the moving time period according to the preset time interval, and record all data collection moments in the moving time period as analysis moments, and record the number of analysis moments in the moving time period as N; and when setting the preset time interval, this embodiment requires that the last collection moment in the moving time period is the current analysis moment. For example, if the length of the moving time period is 10 minutes, then this embodiment can be arranged to collect navigation data every 10 seconds, and N at this time is 60.

[0024] Then, in this embodiment, all analysis moments except the current analysis moment in the moving time period are recorded as historical analysis moments, and then the navigation data vectors at the position of the target moving object at each historical analysis moment in the moving time period are obtained, and are recorded as historical navigation data vectors; then, all the acquired historical navigation data vectors are sorted in chronological order of acquisition time, and the sorted sequence is recorded as a historical navigation data vector sequence; in addition, each navigation data vector in this embodiment is composed of A types of navigation data, and in different navigation data vectors, the categories or types of navigation data located at the same position are consistent, that is, the bth historical navigation data in any historical navigation data vector and the bth navigation data to be fused in the navigation data vector to be fused belong to the same type of navigation data.

[0025] In specific applications, the implementer can set the type of navigation data to be collected at each analysis moment according to actual conditions. For example, in the present embodiment, it is set to obtain the GPS / Beidou navigation data, satellite navigation data and laser navigation data at the location of the target mobile object at each analysis moment, that is, the value of A in the present embodiment is 3, and then the vector constructed by the GPS / Beidou navigation data, satellite navigation data and laser navigation data at the location of the target mobile object at each analysis moment is recorded as the navigation data vector at the location of the target mobile object at the analysis moment.

[0026] In addition, GPS / Beidou navigation data, satellite navigation data, and laser navigation data are all acquired using the software or system carried by the target mobile object. For example, if the target mobile object in this embodiment is a car, then the GPS / Beidou navigation data can be acquired using the vehicle-mounted GPS / Beidou system.

[0027] Therefore, this embodiment can obtain the navigation data vector to be fused and the historical navigation data vector sequence through the above process; then this embodiment obtains the characteristic mark value of each navigation data in the navigation data vector, and the specific acquisition process is: for the a-th navigation data in any navigation data vector, a is used as the characteristic mark value of the a-th navigation data, that is, in different navigation data vectors, the characteristic mark values ​​of the navigation data located at the same position are consistent.

[0028] Therefore, this embodiment obtains the characteristic marking value of each navigation data to be fused in the navigation data vector to be fused and the characteristic marking value of each historical navigation data in the historical navigation data vector through the above process.

[0029] Step S002, according to the position of the target mobile object at the current analysis moment, obtain the first weight value of each navigation data to be fused in the navigation data vector to be fused; according to the navigation data vector to be fused, the historical navigation data vector, the characteristic mark value of the navigation data to be fused and the characteristic mark value of the historical navigation data, obtain the data point sequence to be analyzed of each navigation data to be fused; according to the data point sequence to be analyzed, obtain the stability characterization value of each navigation data to be fused, and use the ratio of the stability characterization value of the navigation data to be fused to the comprehensive stability characterization value as the second weight value of the corresponding navigation data to be fused; according to the historical navigation data in the historical navigation data vector, obtain the third weight value of each navigation data to be fused; the average of the first weight value, the second weight value and the third weight value of each navigation data to be fused is recorded as the target weight value of the corresponding navigation data to be fused.

[0030] Since the purpose of this embodiment is to fuse the collected navigation data of different types, that is, to fuse all the navigation data to be fused in the navigation data vector to be fused at the position of the target mobile object at the current analysis moment, but due to the different ways of collecting different types of navigation data, the different types of navigation data will be interfered with by the environment in different ways, and thus the reference values ​​of different types of navigation data will be different. When fusing, if the reference values ​​of different types of navigation data or the degree of interference by the environment are not considered, the reliability of the navigation data finally obtained by fusion will be low, which may lead to low navigation accuracy, navigation reliability, etc.; and in order to improve the reliability of fusing different types of navigation data, this embodiment will subsequently determine the target weight value of each navigation data to be fused by analyzing the different environmental interference conditions of different types of navigation data during collection and the stability of the data caused by the environmental interference, and subsequently all the navigation data to be fused will be weighted fused according to the target weight value of each navigation data to be fused, so as to obtain reliable fused navigation data.

[0031] Based on the above analysis, it can be known that the present embodiment needs to achieve weighted fusion of the navigation data to be fused by determining the target weight value of the navigation data to be fused, and the target weight value in the present embodiment is determined by the first weight value, the second weight value and the third weight value of the navigation data to be fused. Therefore, the present embodiment next needs to first obtain the first weight value, the second weight value and the third weight value of each navigation data to be fused.

[0032] First, according to the position of the target moving object at the current analysis moment, the first weight value of each navigation data to be fused in the navigation data vector to be fused is obtained, and the specific process of obtaining the first weight value of the navigation data to be fused is:

[0033] First, environmental information of the target mobile object's location at the current analysis moment is obtained, wherein the environmental information includes but is not limited to environmental information related to regional topography, environmental information related to regional weather, and environmental information related to electromagnetics; and the environmental information related to regional topography includes at least the longitude, latitude, and altitude of the corresponding location, the environmental information related to regional weather includes at least the temperature, humidity, and air pressure of the corresponding location, and the environmental information related to electromagnetics includes at least the electromagnetic frequency, charge quantity, and source power of the corresponding location.

[0034] In addition, the reason why the present embodiment acquires environmental information related to regional topography, environmental information related to regional weather, and environmental information related to regional electromagnetics is that the navigation data collected in the present embodiment are GPS / Beidou navigation data, satellite navigation data, and laser navigation data, respectively. Different regional topography will lead to different strengths of GPS / Beidou signals, that is, under different regional topography, the interference intensity when acquiring GPS / Beidou navigation data is different; and different regional electromagnetic intensities will lead to different strengths of satellite signals, that is, under different electromagnetic intensities, the interference intensity when acquiring satellite navigation data is different. Different degrees of intensity, for example, under high-intensity electromagnetic conditions, the satellite signal is weak, so at this time, the satellite navigation data is subject to greater interference from the environment, that is, the reference value of the satellite navigation data obtained at this time is smaller; and different regional weather will lead to different strengths of laser signals, that is, in different weather conditions, the interference intensity when acquiring laser navigation data is different, such as rain, fog, snow and other bad weather will scatter or absorb laser signals, thereby reducing the measurement accuracy of laser signals; based on the above analysis, it can be seen that different types of navigation data in different environments have different interference intensities, that is, different types of navigation data in different environments have different reference values.

[0035] Therefore, this embodiment will combine the neural network with the environmental information of the location of the target moving object at the current analysis moment on the basis of the above analysis to obtain the first weight value of each navigation data to be fused, specifically:

[0036] First, a first network model is constructed, and multiple landform information sample vectors of regional locations for training are obtained, wherein the landform information sample vectors are composed of data related to the regional landforms. Then, relevant staff members label each landform information sample vector, and the label information is the interference intensity. The first network model is trained based on the landform information sample vectors of each regional location for training and the landform information sample vector label information. The trained first network model is recorded as a first interference intensity analysis model, and the first interference intensity analysis model is mainly used to obtain the interference degree of GPS / Beidou navigation data.

[0037] Then, a second network model is constructed, and weather information sample vectors of multiple regional locations for training are obtained, wherein the weather information sample vectors are composed of data related to regional weather. Then, relevant staff labels each weather information sample vector, and the label information is the interference intensity. The second network model is trained based on the weather information sample vectors of each regional location used for training and the weather information sample vector label information. The trained second network model is recorded as a second interference intensity analysis model, and the second interference intensity analysis model is mainly used to obtain the interference degree of laser navigation data.

[0038] Afterwards, a third network model is constructed, and electromagnetic information sample vectors of multiple regional locations for training are obtained, wherein the electromagnetic information sample vectors are composed of electromagnetic-related data. Then, relevant staff labels each electromagnetic information sample vector, and the label information is the interference intensity. The third network model is trained based on the electromagnetic information sample vectors of each regional location for training and the label information of the electromagnetic information sample vectors. The trained third network model is recorded as a third interference intensity analysis model, and the third interference intensity analysis model is mainly used to obtain the interference degree of satellite navigation data.

[0039] Then, the environmental information at the location of the target mobile object at the current analysis moment is recorded as the environmental information to be analyzed, and the vector composed of all data related to the regional topography in the environmental information to be analyzed is input into the first interference intensity analysis model, and the output result of the first interference intensity analysis model is used as the interference degree of the navigation data to be fused belonging to the GPS / Beidou navigation data type; then, the vector composed of all data related to the regional weather in the environmental information to be analyzed is input into the second interference intensity analysis model, and the output result of the second interference intensity analysis model is used as the interference degree of the navigation data to be fused belonging to the laser navigation data type; thereafter, the vector composed of electromagnetic-related data in the environmental information to be analyzed is input into the third interference intensity analysis model, and the output result of the third interference intensity analysis model is used as the interference degree of the navigation data to be fused belonging to the satellite navigation data type.

[0040] Moreover, the networks in the above process are all neural networks with a fully connected FC structure, and the mean square error loss function and the cross entropy loss function are used for supervision during training. In this embodiment, the output value of the interference intensity analysis model ranges from 0 to 1, that is, the interference degree ranges from 0 to 1, and the larger the interference degree value, the greater the interference intensity of the corresponding navigation data to be fused, and also indicates that the corresponding navigation data to be fused has a smaller reference value when being fused. Therefore, when the interference degree value is larger, the first weight value of the corresponding navigation data to be fused should be smaller.

[0041] In addition, the training process of the network model in this embodiment is a well-known technology, so this embodiment will not be described in detail.

[0042] Therefore, this embodiment can obtain the interference intensity of each navigation data to be fused through the above process, and then record the difference between the preset first constant and the interference intensity of each navigation data to be fused as the first weight value of the corresponding navigation data to be fused. In specific applications, the implementer needs to set the preset first constant according to actual conditions. For example, this embodiment sets the preset first constant to constant 1.

[0043] Furthermore, when a certain type of navigation data is strongly interfered by the environment during collection, the stability of the collected navigation data may be poor. Therefore, in the present embodiment, the stability characterization value of the navigation data to be fused is analyzed to obtain the second weight value of the navigation data to be fused. The second weight value can further improve the reliability of the subsequently obtained fused navigation data. In the present embodiment, the specific process of obtaining the second weight value of the navigation data to be fused is as follows:

[0044] First, according to the navigation data vector to be fused, the historical navigation data vector, the characteristic mark value of the navigation data to be fused and the characteristic mark value of the historical navigation data, a sequence of data points to be analyzed of each navigation data to be fused is obtained; and for ease of understanding, the present embodiment will be described below by taking the acquisition process of the sequence of data points to be analyzed of any navigation data B to be fused in the navigation data vector to be fused as an example, that is, the acquisition process of the sequence of data points to be analyzed of the navigation data B to be fused is:

[0045] First, among all the historical navigation data vectors in the historical navigation data vector sequence, all the historical navigation data having the same feature mark value as the feature mark value of the navigation data B to be fused and a set constructed by the navigation data B to be fused are obtained, and recorded as the set to be sorted; then, all the navigation data in the sorted set are sorted in the order of the acquisition time, and the sequence obtained after the sorting is completed is recorded as the navigation data sequence to be mapped of the navigation data B to be fused; then, a UTM coordinate system is constructed, and the UTM coordinate system is a plane rectangular coordinate system, also known as a universal transverse Mercator grid system; then, each navigation data in the navigation data sequence to be mapped is mapped to the UTM coordinate system, and the data point corresponding to each navigation data in the navigation data sequence to be mapped is obtained in the UTM coordinate system, and the sequence constructed by the data points corresponding to each navigation data to be mapped in the navigation data sequence to be mapped is recorded as the data point sequence to be analyzed of the navigation data B to be fused, and the i-th data point in the data point sequence to be analyzed of the navigation data B to be fused is the data point corresponding to the i-th navigation data to be mapped in the navigation data sequence to be mapped; in addition, the navigation data in this embodiment are all three-dimensional data.

[0046] Therefore, the present embodiment can obtain the sequence of data points to be analyzed for each navigation data to be fused through the above process; and after obtaining the sequence of data points to be analyzed for navigation data B to be fused, the present embodiment will obtain the stability characterization value of each navigation data to be fused according to the sequence of data points to be analyzed. Similarly, for ease of understanding, the present embodiment will be described below by taking the process of obtaining the stability characterization value of navigation data B to be fused as an example, that is, the process of obtaining the stability characterization value of navigation data B to be fused is:

[0047] First, obtain the set of historical data point sequences corresponding to the data point sequence to be analyzed of the navigation data B to be fused and the preset length, and record the data point sequence to be analyzed of the navigation data B to be fused as the data point sequence to be analyzed F0, and record the set of historical data point sequences corresponding to the data point sequence to be analyzed F0 as the historical data point sequence set F1.

[0048] In a specific application, the implementer needs to set the preset length according to the length of the historical data point sequence. For example, if the number of data points in the historical data point sequence is L, then the integer value of the ratio of L to 10 is used as the preset length.

[0049] Then, each historical data point sequence of the historical data point sequence set F1 is divided according to the preset length to obtain a data point subsequence set corresponding to each historical data point sequence in the historical data point sequence set F1 and a first label value of each data point subsequence in the data point subsequence set; for example: if the number of historical data points in a historical data point sequence in the historical data point sequence set F1 is 100, and the preset length is 10, then the historical data point sequence can be evenly divided into 10 data point subsequences, and the set constructed by the 10 data point subsequences obtained by the division is the data point subsequence set corresponding to the historical data point sequence.

[0050] In addition, the process of obtaining the first mark value of each data point subsequence in the data point subsequence set is: for any data point subsequence h in the data point subsequence set corresponding to the historical data point sequence H0, if there are g data point subsequences in front of the data point subsequence h in the historical data point sequence H0, then the first mark value of the data point subsequence h is recorded as g+1, that is, the position of the data point subsequence h in the historical data point sequence H0 is the first mark value of the data point subsequence h, and the historical data point sequence H0 is any historical data point sequence in the historical data point sequence set F1.

[0051] Therefore, according to the above process, each historical data point sequence in the historical data point sequence set F1 corresponds to a data point subsequence set; then, in all the data point subsequence sets, all the data point subsequences with the same first label value are divided into the same set, and all the sequence sets obtained after the division are recorded as first subsequence sets, and then the first label value of the data point subsequence in each first subsequence set obtained is used as the second label value corresponding to the first subsequence set; and the number of first subsequence sets is the same as the number of data point subsequence sets, and the first label value of all data point subsequences in the first subsequence set is the same, and when the first label value is the same but they are different data point subsequences, it indicates that these data point subsequences belong to different historical data point sequences, but have the same position on the historical data point sequence.

[0052] Then, the weighted fusion sequence corresponding to each obtained first subsequence set and the third label value of the weighted fusion sequence are obtained, and the set constructed by the weighted fusion sequences corresponding to all first subsequence sets is recorded as the weighted fusion sequence set; then, the weighted fusion sequences in the weighted fusion sequence set are spliced ​​in order from small to large in order of the third label value, and the spliced ​​sequence is recorded as the target weighted fusion data point sequence of the historical data point sequence set F1; then, a univariate linear regression linear fitting is performed on the target weighted fusion data point sequence, and the straight line obtained by fitting is recorded as the first fitting straight line.

[0053] Next, a univariate linear regression linear fitting is performed on the data point sequence F0 to be analyzed, and the straight line obtained by fitting at this time is recorded as the second fitting straight line; then the absolute value of the difference between the slope of the first fitting straight line and the slope of the second fitting straight line is obtained, and recorded as the first difference; then the sum of the first difference and the preset first constant is obtained, and recorded as the second difference, and then the reciprocal of the second difference is obtained, and recorded as the ratio to be processed; then the difference between the preset first constant and the ratio to be processed is obtained, and recorded as the deviation characterization value of the navigation data B to be fused, and the reciprocal of the deviation characterization value is recorded as the stability characterization value of the navigation data B to be fused.

[0054] In addition, in this embodiment, performing univariate linear regression linear fitting on the sequence is a well-known technology, so it will not be described in detail in this embodiment.

[0055] In this embodiment, the process of obtaining the set of historical data point sequences corresponding to the sequence of data points to be analyzed of the navigation data B to be fused is as follows: all positions to be detected on the preset moving route are obtained, and then before the current analysis moment and within the preset historical time period, a set constructed by all moving objects passing through the preset moving route is recorded as the set of moving objects to be analyzed; and then, based on the set of moving objects to be analyzed, the set of historical data point sequences corresponding to the sequence of data points to be analyzed of the navigation data B to be fused is obtained.

[0056] In addition, in this embodiment, the implementer needs to set the preset historical time period according to the actual situation. For example, in this embodiment, the week before the current analysis time is used as the preset historical time period.

[0057] In this embodiment, the method for obtaining the position to be detected on the preset moving route is: for any position c on the preset moving route, if the position c belongs to the position of the target moving object at the historical analysis moment or belongs to the current position, then the position c is recorded as the position to be detected on the preset moving route, and in this embodiment, the starting position on the preset moving route is the position of the target moving object at the first historical analysis moment in the moving time period, and the end position on the preset moving route is the current position.

[0058] In this embodiment, according to the set of mobile objects to be analyzed, the process of obtaining the set of historical data point sequences corresponding to the sequence of data points to be analyzed of the navigation data B to be fused is as follows: for any mobile object C0 to be analyzed in the set of mobile objects to be analyzed: obtain the set of sequences to be processed D of the mobile object C0 to be analyzed and the data point sequences corresponding to each sequence to be processed in the set of sequences to be processed D, and then determine whether the navigation data in the d-th sequence to be processed in the set of sequences to be processed D and the navigation data B to be fused are of the same type of navigation data; if so, then the data point sequence corresponding to the d-th sequence to be processed is used as the historical data point sequence corresponding to the sequence of data points to be analyzed of the navigation data B to be fused; then the set constructed by all the historical data point sequences corresponding to the sequence of data points to be analyzed of the navigation data B to be fused is recorded as the set of historical data point sequences corresponding to the sequence of data points to be analyzed of the navigation data B to be fused, and the number of sequences in the set of historical data point sequences is consistent with the number of mobile objects to be analyzed.

[0059] In this embodiment, the weighted fusion sequence G1 corresponding to any first subsequence set G and the third label value of the weighted fusion sequence G1 are obtained by: recording all data point subsequences in the first subsequence set G as first subsequences, obtaining the initial credibility value of each first subsequence in the first subsequence set G, and recording the cumulative sum of the initial credibility values ​​of all first subsequences in the first subsequence set G as the comprehensive credibility value; then obtaining the ratio of the initial credibility value of each first subsequence to the comprehensive credibility value, and recording it as the normalized credibility value of the corresponding first subsequence; then recording the product of each first subsequence in the first subsequence set G and the normalized credibility value of the corresponding first subsequence as the second subsequence of the corresponding first subsequence, then obtaining a set constructed by the second subsequences of all first subsequences in the first subsequence set G, and recording it as the second subsequence set; then recording the sum of all second subsequences in the second subsequence set as the weighted fusion sequence corresponding to the first subsequence set G, and using the second label value of the first subsequence set G as the third label value of the weighted fusion sequence G1.

[0060] In the above, the process of obtaining the initial credibility value of each first subsequence in the first subsequence set G is as follows: perform linear fitting of univariate linear regression on each first subsequence in the first subsequence set G, and record the straight line obtained by fitting as the straight line to be analyzed corresponding to the first subsequence, and record the slope of the straight line to be analyzed of the first subsequence as the slope of the fitted straight line corresponding to the first subsequence; then obtain the mean of the slopes of the fitted straight lines of all the first subsequences in the first subsequence set G, and record it as the first mean; then obtain the absolute value of the difference between the slope of the fitted straight line of each first subsequence and the first mean, And record it as the characteristic index value of the corresponding first subsequence; then obtain the mean of the characteristic index values ​​of all first subsequences in the first subsequence set G, and record it as the second mean, and calculate the absolute value of the difference between the characteristic index value of each first subsequence and the second mean, and record it as the first difference index value of the corresponding first subsequence; then obtain the value after adding the first difference index value of each first subsequence and the preset first constant, and record it as the second difference index value of the corresponding first subsequence, and then obtain the reciprocal of the second difference index value of each first subsequence, and record it as the initial credibility value of the corresponding first subsequence.

[0061] In this embodiment, the method for obtaining the set of sequences D to be processed is as follows: first, the navigation data vectors of the mobile object C0 to be analyzed at each position to be detected on the preset moving route are obtained, and are all recorded as navigation data vectors to be extracted; then, a set constructed by all the obtained navigation data vectors to be extracted is recorded as the set of navigation data vectors to be extracted; then, among all the navigation data vectors to be extracted in the set of navigation data vectors to be extracted, the navigation data to be extracted belonging to the same type are divided into the same set, and all the sets obtained after the division are recorded as the set of navigation data to be sorted; then, each navigation data in the set of navigation data to be sorted is sorted according to the order of acquisition time, and the sequence after sorting is recorded as the sequence to be processed corresponding to the set of navigation data to be sorted, and the set constructed by the sequences to be processed of all the sets of navigation data to be sorted is recorded as the set of sequences to be processed of the mobile object C0 to be analyzed.

[0062] In this embodiment, a method for obtaining a data point sequence corresponding to each sequence to be processed in the set of sequences to be processed D is as follows: for the dth sequence to be processed in the set of sequences to be processed D, all navigation data in the dth sequence to be processed are mapped to the UTM coordinate system to obtain data points corresponding to each navigation data in the dth sequence to be processed, and a sequence constructed by the data points corresponding to all the navigation data in the dth sequence to be processed is recorded as the data point sequence corresponding to the dth sequence to be processed.

[0063] Therefore, this embodiment can obtain the stability characterization value of each navigation data to be fused through the above-mentioned process of obtaining the stability characterization value of the navigation data B to be fused, and the larger the stability characterization value of the navigation data to be fused, the lower the degree of environmental interference to the corresponding navigation data to be fused, that is, the higher the reference value of the corresponding navigation data to be fused.

[0064] After obtaining the stability characterization value of each navigation data to be fused, the second weight value of the navigation data to be fused is obtained according to the stability characterization value of each navigation data to be fused. The specific acquisition process is: the cumulative sum of the stability characterization values ​​of all the navigation data to be fused in the navigation data vector to be fused is recorded as the comprehensive stability characterization value, and the ratio of the stability characterization value of each navigation data to be fused to the comprehensive stability characterization value is used as the second weight value of the corresponding navigation data to be fused.

[0065] After obtaining the second weight value of the navigation data to be fused, in order to make the target weight value obtained subsequently more reliable, this embodiment then obtains the third weight value corresponding to each navigation data to be fused based on the historical navigation data in the historical navigation data vector. The specific process is as follows:

[0066] First, in the moving time period, select a historical analysis moment closest to the current analysis moment, record it as the nearest neighbor moment of the current analysis moment, and record the historical navigation data vector at the location of the target moving object at the nearest neighbor moment as the feature data vector. Then obtain the stability characterization value of each feature data in the feature data vector, and the method for obtaining the stability characterization value of the feature data is the same as the method for obtaining the stability characterization value of the navigation data to be fused, so it will not be described in detail.

[0067] Then, according to the stability characterization value of each feature data in the feature data vector, the stability change characterization value of each navigation data to be fused in the navigation data vector to be fused is obtained; and the cumulative sum of the stability change characterization values ​​of all the navigation data to be fused in the navigation data vector to be fused is recorded as the first comprehensive value; then the sum of the first comprehensive value and the preset first constant is obtained, and recorded as the second comprehensive value; then the ratio of the stability change characterization value of the navigation data to be fused to the second comprehensive value is obtained, and recorded as the characteristic ratio of the corresponding navigation data to be fused; then the inverse of the characteristic ratio of each navigation data to be fused is obtained, and recorded as the characteristic value of the corresponding navigation data to be fused, and then the normalization function Norm() is used to normalize the characteristic value of each navigation data to be fused, and the normalized value is recorded as the third weight value of the corresponding navigation data to be fused.

[0068] In addition, the method for obtaining the stability change characterization value of the navigation data to be fused is: for the navigation data B to be fused, in the feature data vector, the feature data whose feature mark value is the same as the feature mark value of the navigation data B to be fused is recorded as the first feature data of the navigation data B to be fused, and the absolute value of the difference between the stability characterization value of the first feature data and the stability characterization value of the navigation data B to be fused is recorded as the stability change characterization value of the navigation data B to be fused.

[0069] Therefore, this embodiment can obtain the third weight value of each navigation data to be fused according to the above process, and then record the average of the first weight value, the second weight value and the third weight value of each navigation data to be fused as the target weight value of the corresponding navigation data to be fused.

[0070] Therefore, this embodiment obtains the target weight value of each navigation data to be fused through the above process, and the larger the target weight value is, the lower the intensity of environmental interference when collecting the corresponding navigation data to be fused is, that is, the greater the reference value of the corresponding navigation data to be fused is.

[0071] Step S003: obtaining the fused navigation data at the location of the target moving object at the current analysis moment according to the target weight value.

[0072] Finally, this embodiment obtains the fused navigation data of the position of the target moving object at the current analysis moment according to the target weight value obtained above. The specific process is as follows:

[0073] First, the sum of the target weight values ​​of all navigation data to be fused in the navigation data vector to be fused is recorded as the third comprehensive value, and then the ratio of the target weight value of each navigation data to be fused to the third comprehensive value is obtained and recorded as the normalized weight value of the corresponding navigation data to be fused.

[0074] For the navigation data B to be fused, the product of the navigation data B to be fused and the normalized weight value of the navigation data B to be fused is recorded as the weighted navigation data corresponding to the navigation data B to be fused; and the sum of the weighted navigation data corresponding to all the navigation data to be fused in the navigation data vector to be fused is taken as the fused navigation data at the position of the target mobile object at the current analysis moment.

[0075] A multi-source navigation information data fusion analysis system of this embodiment includes a memory and a processor, and the processor executes a computer program stored in the memory to implement the above-mentioned multi-source navigation information data fusion analysis method.

[0076] In summary, this embodiment obtains the first weight value of each navigation data to be fused in the navigation data vector according to the position of the target mobile object at the current analysis moment; then, according to the sequence of data points to be analyzed, the stability characterization value of each navigation data to be fused is obtained, and the ratio of the stability characterization value of the navigation data to be fused to the comprehensive stability characterization value is used as the second weight value of the corresponding navigation data to be fused; then, according to the historical navigation data in the historical navigation data vector, the third weight value of each navigation data to be fused is obtained; and the average of the first weight value, the second weight value and the third weight value of each navigation data to be fused is recorded as the target weight value of the corresponding navigation data to be fused; finally, according to the target weight value, the fused navigation data at the position of the target mobile object at the current analysis moment is obtained. This embodiment can improve the reliability of fusing multi-source navigation data based on the obtained target weight value, that is, it can make the obtained fused navigation data more reliable.

[0077] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A multi-source navigation information data fusion analysis method, characterized in that: The method comprises the following steps: Acquire a navigation data vector to be fused, a sequence of historical navigation data vectors, a feature tag value of each navigation data to be fused in the navigation data vector to be fused, and a feature tag value of each historical navigation data in the historical navigation data vector at the position of the target mobile object at the current analysis moment, the navigation data vector being composed of A types of navigation data, and the historical navigation data vector belonging to the sequence of historical navigation data vectors; According to the position of the target moving object at the current analysis moment, obtaining a first weight value of each navigation data to be fused in the navigation data vector to be fused; Obtaining a sequence of data points to be analyzed for each navigation data to be fused according to the navigation data vector to be fused, the historical navigation data vector, the feature mark value of the navigation data to be fused and the feature mark value of the historical navigation data; According to the sequence of data points to be analyzed, a stability characterization value of each navigation data to be fused is obtained, and a ratio of the stability characterization value of the navigation data to be fused to a comprehensive stability characterization value is used as a second weight value corresponding to the navigation data to be fused, and the comprehensive stability characterization value is the cumulative sum of the stability characterization values ​​of all the navigation data to be fused; Obtaining a third weight value of each navigation data to be fused according to the historical navigation data in the historical navigation data vector; Recording an average of the first weight value, the second weight value and the third weight value of each navigation data to be fused as a target weight value of the corresponding navigation data to be fused; According to the target weight value, the fused navigation data at the position of the target moving object at the current analysis moment is obtained.

2. The multi-source navigation information data fusion analysis method according to claim 1, characterized in that: The method for acquiring the historical navigation data vector sequence comprises: The position of the target moving object at the current analysis moment is recorded as the current position, and the time period for the target moving object to move from the preset starting position to the current position is obtained and recorded as the moving time period, wherein the moving time period includes N analysis moments; and all other analysis moments in the moving time period except the current analysis moment are recorded as historical analysis moments; The navigation data vectors at the position of the target moving object at each historical analysis moment in the moving time period are obtained and recorded as historical navigation data vectors; all the historical navigation data vectors are sorted in chronological order to obtain a historical navigation data vector sequence.

3. The multi-source navigation information data fusion analysis method according to claim 1, characterized in that: The method for obtaining the characteristic mark value of the navigation data includes: For the ath navigation data in any navigation data vector, a is used as the characteristic mark value of the ath navigation data, and the bth historical navigation data in the historical navigation data vector and the bth navigation data to be fused in the navigation data vector to be fused belong to the same type of navigation data.

4. The multi-source navigation information data fusion analysis method according to claim 1, characterized in that: The method for obtaining the first weight value of each navigation data to be fused in the navigation data vector to be fused includes: Acquire environmental information at the location of the target mobile object at the current analysis moment, and record it as environmental information to be analyzed, input the environmental information to be analyzed into a trained interference intensity analysis model, and output the interference intensity of each navigation data to be fused in the navigation data vector to be fused; The difference between the preset first constant and the interference intensity of each navigation data to be fused is recorded as the first weight value corresponding to the navigation data to be fused.

5. The multi-source navigation information data fusion analysis method according to claim 2, characterized in that: The method for acquiring the sequence of data points to be analyzed of each navigation data to be fused comprises: For any navigation data B to be fused in the navigation data vector to be fused: Among all the historical navigation data vectors in the historical navigation data vector sequence, all the historical navigation data having the same feature tag value as the feature tag value of the navigation data B to be fused and a set constructed by the navigation data B to be fused are recorded as a set to be sorted; all the navigation data in the set to be sorted are sorted in the order of acquisition time to obtain a navigation data sequence to be mapped of the navigation data B to be fused; Construct a UTM coordinate system, map each navigation data in the navigation data sequence to be mapped to the UTM coordinate system, obtain the data point corresponding to each navigation data in the navigation data sequence to be mapped, and record the sequence constructed by the data points corresponding to each navigation data in the navigation data sequence to be mapped as the sequence of data points to be analyzed of the navigation data B to be fused.

6. A multi-source navigation information data fusion analysis method as claimed in claim 5, characterized in that: The method for obtaining the stability characterization value of each navigation data to be fused includes: Acquire a set of historical data point sequences corresponding to the to-be-analyzed data point sequences of each of the to-be-fused navigation data; For the navigation data B to be fused: Obtain a preset length, and use the preset length to divide each historical data point sequence in the historical data point sequence set F1 to obtain all data point subsequences corresponding to each historical data point sequence in the historical data point sequence set F1, and record the set constructed by all data point subsequences corresponding to the historical data point sequence in the set F1 as the data point subsequence set corresponding to the corresponding historical data point sequence, and obtain the first label value of each data point subsequence in the data point subsequence set; in all the data point subsequence sets, divide all data point subsequences with the same first label value into the same set, and record all sequence sets obtained after the division as the first subsequence set, and use the first label value of the data point subsequence in the first subsequence set as the second label value of the corresponding first subsequence set; the historical data point sequence set F1 is the historical data point sequence set corresponding to the data point sequence F0 to be analyzed, and the data point sequence F0 to be analyzed is the data point sequence to be analyzed of the navigation data B to be fused; Obtaining a weighted fusion sequence corresponding to the first subsequence set and a third label value of the weighted fusion sequence, and recording a set constructed by all weighted fusion sequences corresponding to the first subsequence set as a weighted fusion sequence set; sequentially splicing the weighted fusion sequences in the weighted fusion sequence set in order of the third label value from small to large, and recording the spliced ​​sequence as a target weighted fusion data point sequence of the historical data point sequence set F1; performing linear fitting on the target weighted fusion data point sequence, and recording a straight line obtained by fitting as a first fitting straight line; Performing linear fitting on the data point sequence F0 to be analyzed, and recording the straight line obtained by fitting as a second fitting straight line; recording the absolute value of the difference between the slope of the first fitting straight line and the slope of the second fitting straight line as a first difference, recording the sum of the first difference and a preset first constant as a second difference, and recording the reciprocal of the second difference as a ratio to be processed; recording the difference between the preset first constant and the ratio to be processed as a deviation characterization value of the navigation data B to be fused, and recording the reciprocal of the deviation characterization value as a stability characterization value of the navigation data B to be fused; The method for obtaining the first label value of each data point subsequence in the data point subsequence set includes: for any data point subsequence h in the data point subsequence set corresponding to the historical data point sequence H0, if there are g data point subsequences before the data point subsequence h in the historical data point sequence H0, then the first label value of the data point subsequence h is recorded as g+1, and the historical data point sequence H0 is any historical data point sequence in the historical data point sequence set F1; A method for obtaining a weighted fusion sequence G1 corresponding to any first subsequence set G and a third label value of the weighted fusion sequence G1, comprising: recording all data point subsequences in the first subsequence set G as first subsequences, obtaining initial credibility values ​​of each first subsequence in the first subsequence set G, recording the cumulative sum of the initial credibility values ​​of all first subsequences in the first subsequence set G as a comprehensive credibility value; recording the ratio of the initial credibility value of each first subsequence to the comprehensive credibility value as a normalized credibility value of the corresponding first subsequence; recording the product of each first subsequence in the first subsequence set G and the normalized credibility value of the corresponding first subsequence as a second subsequence of the corresponding first subsequence, recording a set constructed by the second subsequences of all first subsequences in the first subsequence set G as a second subsequence set; recording the sum of all second subsequences in the second subsequence set as the weighted fusion sequence G1 corresponding to the first subsequence set G, and using the second label value of the first subsequence set G as the third label value of the weighted fusion sequence G1; The method for obtaining the initial credibility value of each first subsequence in the first subsequence set G includes: performing linear fitting on each first subsequence in the first subsequence set G to obtain the slope of the fitted straight line of each first subsequence, recording the average of the slopes of the fitted straight lines of all first subsequences in the first subsequence set G as the first average; recording the absolute value of the difference between the slope of the fitted straight line of each first subsequence and the first average as the characteristic index value of the corresponding first subsequence; recording the average of the characteristic index values ​​of all first subsequences in the first subsequence set G as the second average; recording the absolute value of the difference between the characteristic index value of each first subsequence and the second average as the first difference index value of the corresponding first subsequence; and recording the reciprocal of the value obtained by adding the first difference index value of the first subsequence to a preset first constant as the initial credibility value of the corresponding first subsequence.

7. A multi-source navigation information data fusion analysis method as claimed in claim 6, characterized in that: The method for acquiring a set of historical data point sequences corresponding to the data point sequences to be analyzed of each navigation data to be fused comprises: Acquire a preset moving route, wherein the starting position on the preset moving route is the position of the target moving object at the first historical analysis moment in the moving time period, and the end position on the preset moving route is the position of the target moving object at the current analysis moment; For any position c on the preset moving route, if the position c belongs to the position of the target moving object at the historical analysis moment or belongs to the current position, the position c is recorded as the position to be detected on the preset moving route; Recording a set of all moving objects that have passed through the preset moving route before the current analysis moment and within the preset historical time period as a set of moving objects to be analyzed; For any mobile object C0 to be analyzed in the set of mobile objects to be analyzed: obtain a set of sequences to be processed D of the mobile object C0 to be analyzed and a data point sequence corresponding to each sequence to be processed in the set of sequences to be processed D; if it is determined that the navigation data in the d-th sequence to be processed in the set of sequences to be processed D and the navigation data to be fused B are of the same type of navigation data, then use the data point sequence corresponding to the d-th sequence to be processed as the historical data point sequence corresponding to the data point sequence F0 to be analyzed; and record the set constructed by all the historical data point sequences corresponding to the data point sequence F0 to be analyzed as the set of historical data point sequences corresponding to the data point sequence F0 to be analyzed; The method for acquiring the set of sequences to be processed D comprises: acquiring navigation data vectors at each position to be detected on the preset moving route of the mobile object to be analyzed C0, and recording them as navigation data vectors to be extracted; recording a set constructed by all the acquired navigation data vectors to be extracted as the set of navigation data vectors to be extracted; dividing the navigation data to be extracted belonging to the same type in all the navigation data vectors to be extracted in the set of navigation data vectors to be extracted into the same set, and recording all the sets obtained after the division as the set of navigation data to be sorted; sorting each navigation data in the set of navigation data to be sorted according to the order of acquisition time, recording the sequence after sorting as the sequence to be processed corresponding to the set of navigation data to be sorted, and recording the set constructed by the sequences to be processed of all the sets of navigation data to be sorted as the set of sequences to be processed D of the mobile object to be analyzed C0; The method for obtaining the data point sequence corresponding to each sequence to be processed in the set of sequences to be processed D comprises: for the dth sequence to be processed in the set of sequences to be processed D, mapping all navigation data in the dth sequence to be processed to the UTM coordinate system, obtaining the data point corresponding to each navigation data in the dth sequence to be processed, and recording the sequence constructed by the data points corresponding to all the navigation data in the dth sequence to be processed as the data point sequence corresponding to the dth sequence to be processed.

8. The multi-source navigation information data fusion analysis method according to claim 2, characterized in that: The method for obtaining the third weight value of each navigation data to be fused includes: In the moving time period, a historical analysis moment closest to the current analysis moment is selected and recorded as the nearest neighbor moment of the current analysis moment, and the historical navigation data vector at the position of the target moving object at the nearest neighbor moment is recorded as the feature data vector; the stability characterization value of each feature data in the feature data vector is obtained, and the method for obtaining the stability characterization value of the feature data is the same as the method for obtaining the stability characterization value of the navigation data to be fused; According to the stability characterization value of each feature data in the feature data vector, a stability change characterization value of each navigation data to be fused in the navigation data vector to be fused is obtained; the cumulative sum of the stability change characterization values ​​of all the navigation data to be fused in the navigation data vector to be fused is recorded as a first comprehensive value; the sum of the first comprehensive value and a preset first constant is recorded as a second comprehensive value, the ratio of the stability change characterization value of the navigation data to be fused to the second comprehensive value is recorded as a characteristic ratio value of the corresponding navigation data to be fused, the inverse of the characteristic ratio value of the navigation data to be fused is recorded as the characteristic value of the corresponding navigation data to be fused, and the normalized value of the characteristic value of the navigation data to be fused is recorded as a third weight value of the corresponding navigation data to be fused; The method for obtaining the stability change characterization value of the navigation data to be fused comprises: for any navigation data B to be fused in the navigation data vector to be fused, in the feature data vector, recording the feature data with the same feature mark value as the feature mark value of the navigation data B to be fused as the first feature data of the navigation data B to be fused, and recording the absolute value of the difference between the stability characterization value of the first feature data and the stability characterization value of the navigation data B to be fused as the stability change characterization value of the navigation data B to be fused.

9. The multi-source navigation information data fusion analysis method according to claim 1, characterized in that: The method for acquiring the fused navigation data at the location of the target moving object at the current analysis moment includes: Recording the sum of target weight values ​​of all navigation data to be fused in the navigation data vector to be fused as a third comprehensive value, and recording the ratio of the target weight value of each navigation data to be fused to the third comprehensive value as a normalized weight value of the corresponding navigation data to be fused; For the navigation data B to be fused, the product of the navigation data B to be fused and the normalized weight value of the navigation data B to be fused is recorded as the weighted navigation data corresponding to the navigation data B to be fused; the sum of the weighted navigation data corresponding to all the navigation data to be fused in the navigation data vector to be fused is taken as the fused navigation data at the position of the target mobile object at the current analysis moment.

10. A multi-source navigation information data fusion analysis system, comprising a memory and a processor, characterized in that: The processor executes the computer program stored in the memory to implement the multi-source navigation information data fusion analysis method as described in any one of claims 1-9.